diff --git "a/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb" "b/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb"
--- "a/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb"
+++ "b/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb"
@@ -3,13 +3,13 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "3174f701",
+   "id": "fb8bab66",
    "metadata": {
     "papermill": {
-     "duration": 0.005065,
-     "end_time": "2023-09-06T17:12:47.606560",
+     "duration": 0.004984,
+     "end_time": "2023-09-06T18:15:07.813560",
      "exception": false,
-     "start_time": "2023-09-06T17:12:47.601495",
+     "start_time": "2023-09-06T18:15:07.808576",
      "status": "completed"
     },
     "tags": []
@@ -25,13 +25,13 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "cb5debdd",
+   "id": "644a18dd",
    "metadata": {
     "papermill": {
-     "duration": 0.002115,
-     "end_time": "2023-09-06T17:12:47.612606",
+     "duration": 0.002407,
+     "end_time": "2023-09-06T18:15:07.820470",
      "exception": false,
-     "start_time": "2023-09-06T17:12:47.610491",
+     "start_time": "2023-09-06T18:15:07.818063",
      "status": "completed"
     },
     "tags": []
@@ -43,19 +43,19 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "41bbf98d",
+   "id": "88954417",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:12:47.618377Z",
-     "iopub.status.busy": "2023-09-06T17:12:47.618157Z",
-     "iopub.status.idle": "2023-09-06T17:12:48.494513Z",
-     "shell.execute_reply": "2023-09-06T17:12:48.493600Z"
+     "iopub.execute_input": "2023-09-06T18:15:07.826313Z",
+     "iopub.status.busy": "2023-09-06T18:15:07.826023Z",
+     "iopub.status.idle": "2023-09-06T18:15:08.710191Z",
+     "shell.execute_reply": "2023-09-06T18:15:08.709357Z"
     },
     "papermill": {
-     "duration": 0.881639,
-     "end_time": "2023-09-06T17:12:48.496472",
+     "duration": 0.889532,
+     "end_time": "2023-09-06T18:15:08.712219",
      "exception": false,
-     "start_time": "2023-09-06T17:12:47.614833",
+     "start_time": "2023-09-06T18:15:07.822687",
      "status": "completed"
     },
     "tags": []
@@ -83,19 +83,19 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "bc308e46",
+   "id": "54728414",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:12:48.506904Z",
-     "iopub.status.busy": "2023-09-06T17:12:48.506660Z",
-     "iopub.status.idle": "2023-09-06T17:12:50.610312Z",
-     "shell.execute_reply": "2023-09-06T17:12:50.609442Z"
+     "iopub.execute_input": "2023-09-06T18:15:08.723120Z",
+     "iopub.status.busy": "2023-09-06T18:15:08.722681Z",
+     "iopub.status.idle": "2023-09-06T18:15:10.844392Z",
+     "shell.execute_reply": "2023-09-06T18:15:10.843613Z"
     },
     "papermill": {
-     "duration": 2.110898,
-     "end_time": "2023-09-06T17:12:50.612132",
+     "duration": 2.129186,
+     "end_time": "2023-09-06T18:15:10.846223",
      "exception": false,
-     "start_time": "2023-09-06T17:12:48.501234",
+     "start_time": "2023-09-06T18:15:08.717037",
      "status": "completed"
     },
     "tags": []
@@ -118,19 +118,19 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "5ecce62b",
+   "id": "4e5c05c9",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:12:50.622765Z",
-     "iopub.status.busy": "2023-09-06T17:12:50.622510Z",
-     "iopub.status.idle": "2023-09-06T17:12:50.631551Z",
-     "shell.execute_reply": "2023-09-06T17:12:50.630955Z"
+     "iopub.execute_input": "2023-09-06T18:15:10.856132Z",
+     "iopub.status.busy": "2023-09-06T18:15:10.855690Z",
+     "iopub.status.idle": "2023-09-06T18:15:10.864690Z",
+     "shell.execute_reply": "2023-09-06T18:15:10.864101Z"
     },
     "papermill": {
-     "duration": 0.01615,
-     "end_time": "2023-09-06T17:12:50.633066",
+     "duration": 0.015147,
+     "end_time": "2023-09-06T18:15:10.866187",
      "exception": false,
-     "start_time": "2023-09-06T17:12:50.616916",
+     "start_time": "2023-09-06T18:15:10.851040",
      "status": "completed"
     },
     "tags": []
@@ -140,7 +140,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEEPSPEED_STRAT: deepspeed_stage_1\n",
+      "DEEPSPEED_STRAT:"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " deepspeed_stage_1\n",
       "ENABLE_WANDB: True\n",
       "GPU_DEVICES: auto\n",
       "DIR_NAME: L12-D2048-E1e-1-ctx4k\n",
@@ -197,19 +204,19 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "ecee273d",
+   "id": "9a735016",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:12:50.643057Z",
-     "iopub.status.busy": "2023-09-06T17:12:50.642933Z",
-     "iopub.status.idle": "2023-09-06T17:13:06.898900Z",
-     "shell.execute_reply": "2023-09-06T17:13:06.898162Z"
+     "iopub.execute_input": "2023-09-06T18:15:10.875858Z",
+     "iopub.status.busy": "2023-09-06T18:15:10.875465Z",
+     "iopub.status.idle": "2023-09-06T18:15:26.773342Z",
+     "shell.execute_reply": "2023-09-06T18:15:26.772573Z"
     },
     "papermill": {
-     "duration": 16.262552,
-     "end_time": "2023-09-06T17:13:06.900660",
+     "duration": 15.904517,
+     "end_time": "2023-09-06T18:15:26.775109",
      "exception": false,
-     "start_time": "2023-09-06T17:12:50.638108",
+     "start_time": "2023-09-06T18:15:10.870592",
      "status": "completed"
     },
     "tags": []
@@ -219,9 +226,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "--2023-09-06 17:12:50--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/v5r3-L12-D2048-E0_1-enwiki-4k.pth\r\n",
-      "Resolving huggingface.co (huggingface.co)... 13.33.33.55, 13.33.33.102, 13.33.33.110, ...\r\n",
-      "Connecting to huggingface.co (huggingface.co)|13.33.33.55|:443... connected.\r\n",
+      "--2023-09-06 18:15:10--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/v5r3-L12-D2048-E0_1-enwiki-4k.pth\r\n",
+      "Resolving huggingface.co (huggingface.co)... 13.33.33.110, 13.33.33.20, 13.33.33.55, ...\r\n",
+      "Connecting to huggingface.co (huggingface.co)|13.33.33.110|:443... connected.\r\n",
       "HTTP request sent, awaiting response... "
      ]
     },
@@ -230,8 +237,8 @@
      "output_type": "stream",
      "text": [
       "302 Found\r\n",
-      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/fcd2c54e435c74dc2a43bd3bbde6594de9c6937156caf9f72a77137ed3d49539?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L12-D2048-E0_1-enwiki-4k.pth%3B+filename%3D%22v5r3-L12-D2048-E0_1-enwiki-4k.pth%22%3B&Expires=1694279570&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDI3OTU3MH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkL2ZjZDJjNTRlNDM1Yzc0ZGMyYTQzYmQzYmJkZTY1OTRkZTljNjkzNzE1NmNhZjlmNzJhNzcxMzdlZDNkNDk1Mzk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=vlJUg9zPT-Ie2MebXI3t7Sfovkvk30xvNya0WqXvAogwISiGWpmGNd3IKa0rDNdEdrQ3uREbJSFhcam12E5VepvwzlhCsUFsI4W9YnOQ8JOVAtNH5fzk16zGizK7%7EtmvJszRMbwukNZOp6TGz4kqEQPgwAwv26tPs9mP2ATP59hiH30jVnK1yjYot7Y2UAC6vKBdF3%7E%7EZUsL-ZfcYL0lTLE7xPmtgafMs3DM-TJhA1wPXw2r-ByBDo2l6edDKcosW36ncjch5kT5XXrnmxEhX4Yll0kAYuwvfXZI2AsIfeopfeKyYhg0KKeAwrPaxHzAcfQSHQn%7EVIjtW-Ro-8XAUw__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
-      "--2023-09-06 17:12:51--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/fcd2c54e435c74dc2a43bd3bbde6594de9c6937156caf9f72a77137ed3d49539?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L12-D2048-E0_1-enwiki-4k.pth%3B+filename%3D%22v5r3-L12-D2048-E0_1-enwiki-4k.pth%22%3B&Expires=1694279570&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDI3OTU3MH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkL2ZjZDJjNTRlNDM1Yzc0ZGMyYTQzYmQzYmJkZTY1OTRkZTljNjkzNzE1NmNhZjlmNzJhNzcxMzdlZDNkNDk1Mzk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=vlJUg9zPT-Ie2MebXI3t7Sfovkvk30xvNya0WqXvAogwISiGWpmGNd3IKa0rDNdEdrQ3uREbJSFhcam12E5VepvwzlhCsUFsI4W9YnOQ8JOVAtNH5fzk16zGizK7%7EtmvJszRMbwukNZOp6TGz4kqEQPgwAwv26tPs9mP2ATP59hiH30jVnK1yjYot7Y2UAC6vKBdF3%7E%7EZUsL-ZfcYL0lTLE7xPmtgafMs3DM-TJhA1wPXw2r-ByBDo2l6edDKcosW36ncjch5kT5XXrnmxEhX4Yll0kAYuwvfXZI2AsIfeopfeKyYhg0KKeAwrPaxHzAcfQSHQn%7EVIjtW-Ro-8XAUw__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
+      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/fcd2c54e435c74dc2a43bd3bbde6594de9c6937156caf9f72a77137ed3d49539?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L12-D2048-E0_1-enwiki-4k.pth%3B+filename%3D%22v5r3-L12-D2048-E0_1-enwiki-4k.pth%22%3B&Expires=1694283311&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDI4MzMxMX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkL2ZjZDJjNTRlNDM1Yzc0ZGMyYTQzYmQzYmJkZTY1OTRkZTljNjkzNzE1NmNhZjlmNzJhNzcxMzdlZDNkNDk1Mzk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=umgcHAKKVfM%7Elnvkc01zRnwcLHn3wrQfHfl-f-B8cnLRauI-kG63DbJ3BWLUFwsnUXKFrGoEYt8IW3AjE2J9QanT4tt1Zh34ojm5pdkTt4PvrIoX0iCwHRRIJGgV9h%7EF%7EMpsuweAJiHAbk61U4GSdt3fnpVaAKUKKa-VNDcmS3LwTuOx3gQgTqbTc-9ZMz14QcAVZV%7EgGZO5D1Owr0g0db9eatciOvhG7%7EnN%7ES%7EQIhVVZENXFPv0Ej8Jr11N0lmHdGU%7EBXm0fqUL1lCSaAEwCoIF%7EGrG2gtP049PGM9tapGgm6-4y4HbfsNVIxH-iRn-c2lvkjCpUSIOpMzce6wNvA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
+      "--2023-09-06 18:15:11--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/fcd2c54e435c74dc2a43bd3bbde6594de9c6937156caf9f72a77137ed3d49539?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L12-D2048-E0_1-enwiki-4k.pth%3B+filename%3D%22v5r3-L12-D2048-E0_1-enwiki-4k.pth%22%3B&Expires=1694283311&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDI4MzMxMX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkL2ZjZDJjNTRlNDM1Yzc0ZGMyYTQzYmQzYmJkZTY1OTRkZTljNjkzNzE1NmNhZjlmNzJhNzcxMzdlZDNkNDk1Mzk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=umgcHAKKVfM%7Elnvkc01zRnwcLHn3wrQfHfl-f-B8cnLRauI-kG63DbJ3BWLUFwsnUXKFrGoEYt8IW3AjE2J9QanT4tt1Zh34ojm5pdkTt4PvrIoX0iCwHRRIJGgV9h%7EF%7EMpsuweAJiHAbk61U4GSdt3fnpVaAKUKKa-VNDcmS3LwTuOx3gQgTqbTc-9ZMz14QcAVZV%7EgGZO5D1Owr0g0db9eatciOvhG7%7EnN%7ES%7EQIhVVZENXFPv0Ej8Jr11N0lmHdGU%7EBXm0fqUL1lCSaAEwCoIF%7EGrG2gtP049PGM9tapGgm6-4y4HbfsNVIxH-iRn-c2lvkjCpUSIOpMzce6wNvA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
       "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... "
      ]
     },
@@ -239,8 +246,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "18.155.68.98, 18.155.68.128, 18.155.68.94, ...\r\n",
-      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.155.68.98|:443... connected.\r\n",
+      "18.155.68.128, 18.155.68.73, 18.155.68.98, ...\r\n",
+      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.155.68.128|:443... connected.\r\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "HTTP request sent, awaiting response... 200 OK\r\n",
       "Length: 1721187013 (1.6G) [binary/octet-stream]\r\n",
       "Saving to: ‘v5r3-L12-D2048-E0_1-enwiki-4k.pth’\r\n",
@@ -254,7 +267,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5r3-L12-D   1%[                    ]  21.42M   107MB/s               "
+      "         v5r3-L12-D   1%[                    ]  21.14M   106MB/s               "
      ]
     },
     {
@@ -262,7 +275,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5r3-L12-D2   2%[                    ]  43.83M   110MB/s               "
+      "        v5r3-L12-D2   2%[                    ]  43.53M   109MB/s               "
      ]
     },
     {
@@ -270,7 +283,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5r3-L12-D20   4%[                    ]  66.17M   110MB/s               "
+      "       v5r3-L12-D20   4%[                    ]  65.91M   110MB/s               "
      ]
     },
     {
@@ -278,7 +291,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5r3-L12-D204   5%[>                   ]  88.57M   111MB/s               "
+      "      v5r3-L12-D204   5%[>                   ]  88.31M   110MB/s               "
      ]
     },
     {
@@ -286,7 +299,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5r3-L12-D2048   6%[>                   ] 110.92M   111MB/s               "
+      "     v5r3-L12-D2048   6%[>                   ] 110.72M   111MB/s               "
      ]
     },
     {
@@ -294,7 +307,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5r3-L12-D2048-   8%[>                   ] 133.36M   111MB/s               "
+      "    v5r3-L12-D2048-   8%[>                   ] 133.11M   111MB/s               "
      ]
     },
     {
@@ -302,7 +315,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5r3-L12-D2048-E   9%[>                   ] 155.76M   111MB/s               "
+      "   v5r3-L12-D2048-E   9%[>                   ] 155.46M   111MB/s               "
      ]
     },
     {
@@ -310,7 +323,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5r3-L12-D2048-E0  10%[=>                  ] 178.16M   111MB/s               "
+      "  v5r3-L12-D2048-E0  10%[=>                  ] 177.86M   111MB/s               "
      ]
     },
     {
@@ -318,7 +331,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5r3-L12-D2048-E0_  12%[=>                  ] 200.56M   111MB/s               "
+      " v5r3-L12-D2048-E0_  12%[=>                  ] 200.27M   111MB/s               "
      ]
     },
     {
@@ -326,7 +339,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5r3-L12-D2048-E0_1  13%[=>                  ] 222.97M   111MB/s               "
+      "v5r3-L12-D2048-E0_1  13%[=>                  ] 222.66M   111MB/s               "
      ]
     },
     {
@@ -334,7 +347,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5r3-L12-D2048-E0_1-  14%[=>                  ] 244.89M   111MB/s               "
+      "5r3-L12-D2048-E0_1-  14%[=>                  ] 245.07M   111MB/s               "
      ]
     },
     {
@@ -342,7 +355,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "r3-L12-D2048-E0_1-e  16%[==>                 ] 267.32M   111MB/s               "
+      "r3-L12-D2048-E0_1-e  16%[==>                 ] 267.48M   111MB/s               "
      ]
     },
     {
@@ -350,7 +363,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "3-L12-D2048-E0_1-en  17%[==>                 ] 289.71M   111MB/s               "
+      "3-L12-D2048-E0_1-en  17%[==>                 ] 289.89M   111MB/s               "
      ]
     },
     {
@@ -358,7 +371,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L12-D2048-E0_1-enw  19%[==>                 ] 312.11M   111MB/s               "
+      "-L12-D2048-E0_1-enw  19%[==>                 ] 312.30M   112MB/s               "
      ]
     },
     {
@@ -366,7 +379,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L12-D2048-E0_1-enwi  20%[===>                ] 334.51M   111MB/s    eta 12s    "
+      "L12-D2048-E0_1-enwi  20%[===>                ] 334.71M   112MB/s    eta 12s    "
      ]
     },
     {
@@ -374,7 +387,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "12-D2048-E0_1-enwik  21%[===>                ] 356.91M   112MB/s    eta 12s    "
+      "12-D2048-E0_1-enwik  21%[===>                ] 357.11M   112MB/s    eta 12s    "
      ]
     },
     {
@@ -382,7 +395,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2-D2048-E0_1-enwiki  23%[===>                ] 379.31M   112MB/s    eta 12s    "
+      "2-D2048-E0_1-enwiki  23%[===>                ] 379.51M   112MB/s    eta 12s    "
      ]
     },
     {
@@ -390,7 +403,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D2048-E0_1-enwiki-  24%[===>                ] 401.72M   112MB/s    eta 12s    "
+      "-D2048-E0_1-enwiki-  24%[===>                ] 401.92M   112MB/s    eta 12s    "
      ]
     },
     {
@@ -398,7 +411,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D2048-E0_1-enwiki-4  25%[====>               ] 424.13M   112MB/s    eta 12s    "
+      "D2048-E0_1-enwiki-4  25%[====>               ] 424.32M   112MB/s    eta 12s    "
      ]
     },
     {
@@ -406,7 +419,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2048-E0_1-enwiki-4k  27%[====>               ] 446.53M   112MB/s    eta 11s    "
+      "2048-E0_1-enwiki-4k  27%[====>               ] 446.72M   112MB/s    eta 11s    "
      ]
     },
     {
@@ -414,7 +427,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "048-E0_1-enwiki-4k.  28%[====>               ] 468.94M   112MB/s    eta 11s    "
+      "048-E0_1-enwiki-4k.  28%[====>               ] 469.12M   112MB/s    eta 11s    "
      ]
     },
     {
@@ -422,7 +435,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "48-E0_1-enwiki-4k.p  29%[====>               ] 491.34M   112MB/s    eta 11s    "
+      "48-E0_1-enwiki-4k.p  29%[====>               ] 491.52M   112MB/s    eta 11s    "
      ]
     },
     {
@@ -430,7 +443,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "8-E0_1-enwiki-4k.pt  31%[=====>              ] 513.75M   112MB/s    eta 11s    "
+      "8-E0_1-enwiki-4k.pt  31%[=====>              ] 513.93M   112MB/s    eta 11s    "
      ]
     },
     {
@@ -438,7 +451,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-enwiki-4k.pth  32%[=====>              ] 536.15M   112MB/s    eta 11s    "
+      "-E0_1-enwiki-4k.pth  32%[=====>              ] 536.33M   112MB/s    eta 11s    "
      ]
     },
     {
@@ -446,7 +459,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-enwiki-4k.pth   34%[=====>              ] 558.51M   112MB/s    eta 10s    "
+      "E0_1-enwiki-4k.pth   34%[=====>              ] 558.73M   112MB/s    eta 10s    "
      ]
     },
     {
@@ -454,7 +467,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-enwiki-4k.pth    35%[======>             ] 580.91M   112MB/s    eta 10s    "
+      "0_1-enwiki-4k.pth    35%[======>             ] 581.14M   112MB/s    eta 10s    "
      ]
     },
     {
@@ -462,7 +475,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-enwiki-4k.pth     36%[======>             ] 603.30M   112MB/s    eta 10s    "
+      "_1-enwiki-4k.pth     36%[======>             ] 602.65M   112MB/s    eta 10s    "
      ]
     },
     {
@@ -470,7 +483,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1-enwiki-4k.pth      38%[======>             ] 625.71M   112MB/s    eta 10s    "
+      "1-enwiki-4k.pth      38%[======>             ] 624.87M   112MB/s    eta 10s    "
      ]
     },
     {
@@ -478,7 +491,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-enwiki-4k.pth       39%[======>             ] 648.10M   112MB/s    eta 10s    "
+      "-enwiki-4k.pth       39%[======>             ] 647.26M   112MB/s    eta 10s    "
      ]
     },
     {
@@ -486,7 +499,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "enwiki-4k.pth        40%[=======>            ] 670.50M   112MB/s    eta 9s     "
+      "enwiki-4k.pth        40%[=======>            ] 669.68M   112MB/s    eta 9s     "
      ]
     },
     {
@@ -494,7 +507,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "nwiki-4k.pth         42%[=======>            ] 692.78M   112MB/s    eta 9s     "
+      "nwiki-4k.pth         42%[=======>            ] 692.08M   112MB/s    eta 9s     "
      ]
     },
     {
@@ -502,7 +515,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "wiki-4k.pth          43%[=======>            ] 715.16M   112MB/s    eta 9s     "
+      "wiki-4k.pth          43%[=======>            ] 714.45M   112MB/s    eta 9s     "
      ]
     },
     {
@@ -510,7 +523,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "iki-4k.pth           44%[=======>            ] 737.57M   112MB/s    eta 9s     "
+      "iki-4k.pth           44%[=======>            ] 736.88M   112MB/s    eta 9s     "
      ]
     },
     {
@@ -518,7 +531,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "ki-4k.pth            46%[========>           ] 759.99M   112MB/s    eta 9s     "
+      "ki-4k.pth            46%[========>           ] 759.32M   112MB/s    eta 9s     "
      ]
     },
     {
@@ -526,7 +539,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "i-4k.pth             47%[========>           ] 782.39M   112MB/s    eta 8s     "
+      "i-4k.pth             47%[========>           ] 781.71M   112MB/s    eta 8s     "
      ]
     },
     {
@@ -534,7 +547,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-4k.pth              49%[========>           ] 804.80M   112MB/s    eta 8s     "
+      "-4k.pth              48%[========>           ] 804.12M   112MB/s    eta 8s     "
      ]
     },
     {
@@ -542,7 +555,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4k.pth               50%[=========>          ] 827.18M   112MB/s    eta 8s     "
+      "4k.pth               50%[=========>          ] 826.52M   112MB/s    eta 8s     "
      ]
     },
     {
@@ -550,7 +563,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "k.pth                51%[=========>          ] 849.60M   112MB/s    eta 8s     "
+      "k.pth                51%[=========>          ] 848.92M   112MB/s    eta 8s     "
      ]
     },
     {
@@ -558,7 +571,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      ".pth                 53%[=========>          ] 872.00M   112MB/s    eta 8s     "
+      ".pth                 53%[=========>          ] 871.34M   112MB/s    eta 8s     "
      ]
     },
     {
@@ -566,7 +579,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "pth                  54%[=========>          ] 894.41M   112MB/s    eta 7s     "
+      "pth                  54%[=========>          ] 893.74M   112MB/s    eta 7s     "
      ]
     },
     {
@@ -574,7 +587,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "th                   55%[==========>         ] 916.82M   112MB/s    eta 7s     "
+      "th                   55%[==========>         ] 916.15M   112MB/s    eta 7s     "
      ]
     },
     {
@@ -582,7 +595,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "h                    57%[==========>         ] 939.22M   112MB/s    eta 7s     "
+      "h                    57%[==========>         ] 938.55M   112MB/s    eta 7s     "
      ]
     },
     {
@@ -590,7 +603,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                     58%[==========>         ] 961.63M   112MB/s    eta 7s     "
+      "                     58%[==========>         ] 960.96M   112MB/s    eta 7s     "
      ]
     },
     {
@@ -598,7 +611,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                  v  59%[==========>         ] 984.03M   112MB/s    eta 7s     "
+      "                  v  59%[==========>         ] 983.35M   112MB/s    eta 7s     "
      ]
     },
     {
@@ -662,7 +675,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "          v5r3-L12-  69%[============>       ]   1.11G   103MB/s    eta 5s     "
+      "          v5r3-L12-  69%[============>       ]   1.11G   104MB/s    eta 5s     "
      ]
     },
     {
@@ -670,7 +683,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5r3-L12-D  70%[=============>      ]   1.13G   101MB/s    eta 5s     "
+      "         v5r3-L12-D  70%[=============>      ]   1.13G   105MB/s    eta 5s     "
      ]
     },
     {
@@ -678,7 +691,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5r3-L12-D2  71%[=============>      ]   1.14G  98.7MB/s    eta 5s     "
+      "        v5r3-L12-D2  72%[=============>      ]   1.16G   105MB/s    eta 5s     "
      ]
     },
     {
@@ -686,7 +699,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5r3-L12-D20  72%[=============>      ]   1.16G  96.7MB/s    eta 4s     "
+      "       v5r3-L12-D20  73%[=============>      ]   1.18G   104MB/s    eta 4s     "
      ]
     },
     {
@@ -694,7 +707,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5r3-L12-D204  73%[=============>      ]   1.17G  93.8MB/s    eta 4s     "
+      "      v5r3-L12-D204  74%[=============>      ]   1.20G   105MB/s    eta 4s     "
      ]
     },
     {
@@ -702,7 +715,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5r3-L12-D2048  74%[=============>      ]   1.19G  93.4MB/s    eta 4s     "
+      "     v5r3-L12-D2048  76%[==============>     ]   1.22G   105MB/s    eta 4s     "
      ]
     },
     {
@@ -710,7 +723,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5r3-L12-D2048-  75%[==============>     ]   1.21G  91.2MB/s    eta 4s     "
+      "    v5r3-L12-D2048-  77%[==============>     ]   1.24G   104MB/s    eta 4s     "
      ]
     },
     {
@@ -718,7 +731,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5r3-L12-D2048-E  76%[==============>     ]   1.22G  89.5MB/s    eta 4s     "
+      "   v5r3-L12-D2048-E  79%[==============>     ]   1.27G   105MB/s    eta 4s     "
      ]
     },
     {
@@ -726,7 +739,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5r3-L12-D2048-E0  77%[==============>     ]   1.24G  89.3MB/s    eta 3s     "
+      "  v5r3-L12-D2048-E0  80%[===============>    ]   1.29G   105MB/s    eta 3s     "
      ]
     },
     {
@@ -734,7 +747,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5r3-L12-D2048-E0_  78%[==============>     ]   1.26G  85.2MB/s    eta 3s     "
+      " v5r3-L12-D2048-E0_  81%[===============>    ]   1.31G   104MB/s    eta 3s     "
      ]
     },
     {
@@ -742,7 +755,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5r3-L12-D2048-E0_1  79%[==============>     ]   1.28G  85.1MB/s    eta 3s     "
+      "v5r3-L12-D2048-E0_1  83%[===============>    ]   1.33G   105MB/s    eta 3s     "
      ]
     },
     {
@@ -750,7 +763,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5r3-L12-D2048-E0_1-  81%[===============>    ]   1.30G  85.5MB/s    eta 3s     "
+      "5r3-L12-D2048-E0_1-  84%[===============>    ]   1.35G   105MB/s    eta 3s     "
      ]
     },
     {
@@ -758,7 +771,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "r3-L12-D2048-E0_1-e  82%[===============>    ]   1.32G  84.6MB/s    eta 3s     "
+      "r3-L12-D2048-E0_1-e  85%[================>   ]   1.38G   104MB/s    eta 3s     "
      ]
     },
     {
@@ -766,7 +779,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "3-L12-D2048-E0_1-en  83%[===============>    ]   1.34G  85.0MB/s    eta 3s     "
+      "3-L12-D2048-E0_1-en  87%[================>   ]   1.40G   103MB/s    eta 2s     "
      ]
     },
     {
@@ -774,7 +787,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L12-D2048-E0_1-enw  85%[================>   ]   1.37G  86.9MB/s    eta 3s     "
+      "-L12-D2048-E0_1-enw  88%[================>   ]   1.42G   110MB/s    eta 2s     "
      ]
     },
     {
@@ -782,7 +795,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L12-D2048-E0_1-enwi  86%[================>   ]   1.39G  92.5MB/s    eta 3s     "
+      "L12-D2048-E0_1-enwi  89%[================>   ]   1.44G   111MB/s    eta 2s     "
      ]
     },
     {
@@ -790,7 +803,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "12-D2048-E0_1-enwik  87%[================>   ]   1.41G  94.5MB/s    eta 3s     "
+      "12-D2048-E0_1-enwik  91%[=================>  ]   1.46G   111MB/s    eta 2s     "
      ]
     },
     {
@@ -798,7 +811,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2-D2048-E0_1-enwiki  89%[================>   ]   1.43G  96.2MB/s    eta 3s     "
+      "2-D2048-E0_1-enwiki  92%[=================>  ]   1.48G   110MB/s    eta 2s     "
      ]
     },
     {
@@ -806,7 +819,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D2048-E0_1-enwiki-  90%[=================>  ]   1.45G  99.5MB/s    eta 1s     "
+      "-D2048-E0_1-enwiki-  93%[=================>  ]   1.50G   110MB/s    eta 1s     "
      ]
     },
     {
@@ -814,7 +827,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D2048-E0_1-enwiki-4  92%[=================>  ]   1.47G   101MB/s    eta 1s     "
+      "D2048-E0_1-enwiki-4  95%[==================> ]   1.52G   110MB/s    eta 1s     "
      ]
     },
     {
@@ -822,7 +835,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2048-E0_1-enwiki-4k  93%[=================>  ]   1.50G   104MB/s    eta 1s     "
+      "2048-E0_1-enwiki-4k  96%[==================> ]   1.55G   110MB/s    eta 1s     "
      ]
     },
     {
@@ -830,7 +843,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "048-E0_1-enwiki-4k.  94%[=================>  ]   1.52G   105MB/s    eta 1s     "
+      "048-E0_1-enwiki-4k.  97%[==================> ]   1.57G   110MB/s    eta 1s     "
      ]
     },
     {
@@ -838,7 +851,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "48-E0_1-enwiki-4k.p  96%[==================> ]   1.54G   107MB/s    eta 1s     "
+      "48-E0_1-enwiki-4k.p  99%[==================> ]   1.59G   110MB/s    eta 1s     "
      ]
     },
     {
@@ -846,25 +859,9 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "8-E0_1-enwiki-4k.pt  97%[==================> ]   1.56G   107MB/s    eta 0s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-E0_1-enwiki-4k.pth  98%[==================> ]   1.58G   111MB/s    eta 0s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "v5r3-L12-D2048-E0_1 100%[===================>]   1.60G   112MB/s    in 15s     \r\n",
+      "v5r3-L12-D2048-E0_1 100%[===================>]   1.60G   110MB/s    in 15s     \r\n",
       "\r\n",
-      "2023-09-06 17:13:06 (106 MB/s) - ‘v5r3-L12-D2048-E0_1-enwiki-4k.pth’ saved [1721187013/1721187013]\r\n",
+      "2023-09-06 18:15:26 (110 MB/s) - ‘v5r3-L12-D2048-E0_1-enwiki-4k.pth’ saved [1721187013/1721187013]\r\n",
       "\r\n"
      ]
     },
@@ -872,9 +869,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "total 1.5G\r\n",
-      "drwxr-xr-x  2 root root    3 Sep  6 17:12 .\r\n",
-      "drwxr-xr-x 20 root root   24 Sep  6 17:12 ..\r\n",
+      "total 1.6G\r\n",
+      "drwxr-xr-x  2 root root    3 Sep  6 18:15 .\r\n",
+      "drwxr-xr-x 20 root root   24 Sep  6 18:15 ..\r\n",
       "-rw-r--r--  1 root root 1.7G Sep  6 15:04 v5r3-L12-D2048-E0_1-enwiki-4k.pth\r\n"
      ]
     }
@@ -891,13 +888,13 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "326602ab",
+   "id": "2b6d6b9e",
    "metadata": {
     "papermill": {
-     "duration": 0.005225,
-     "end_time": "2023-09-06T17:13:06.914108",
+     "duration": 0.005279,
+     "end_time": "2023-09-06T18:15:26.791307",
      "exception": false,
-     "start_time": "2023-09-06T17:13:06.908883",
+     "start_time": "2023-09-06T18:15:26.786028",
      "status": "completed"
     },
     "tags": []
@@ -909,19 +906,19 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "e3aa35e9",
+   "id": "ec611ca0",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:13:06.925901Z",
-     "iopub.status.busy": "2023-09-06T17:13:06.925655Z",
-     "iopub.status.idle": "2023-09-06T17:13:14.291842Z",
-     "shell.execute_reply": "2023-09-06T17:13:14.291053Z"
+     "iopub.execute_input": "2023-09-06T18:15:26.803278Z",
+     "iopub.status.busy": "2023-09-06T18:15:26.803020Z",
+     "iopub.status.idle": "2023-09-06T18:15:34.152162Z",
+     "shell.execute_reply": "2023-09-06T18:15:34.151364Z"
     },
     "papermill": {
-     "duration": 7.374402,
-     "end_time": "2023-09-06T17:13:14.293884",
+     "duration": 7.357428,
+     "end_time": "2023-09-06T18:15:34.154153",
      "exception": false,
-     "start_time": "2023-09-06T17:13:06.919482",
+     "start_time": "2023-09-06T18:15:26.796725",
      "status": "completed"
     },
     "tags": []
@@ -940,12 +937,12 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 223458.37 exa\r",
-      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 222084.37 exa\r\n",
+      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 229773.44 exa\r",
+      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 228347.58 exa\r\n",
       "\r",
       "Saving the dataset (0/1 shards):   0%|            | 0/76 [00:00<?, ? examples/s]\r",
-      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 19065.02 examples/s\r",
-      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 18534.05 examples/s\r\n"
+      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 19294.66 examples/s\r",
+      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 18752.11 examples/s\r\n"
      ]
     }
    ],
@@ -958,19 +955,19 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "1c53bd56",
+   "id": "45623796",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:13:14.310191Z",
-     "iopub.status.busy": "2023-09-06T17:13:14.309945Z",
-     "iopub.status.idle": "2023-09-06T17:35:39.099684Z",
-     "shell.execute_reply": "2023-09-06T17:35:39.098813Z"
+     "iopub.execute_input": "2023-09-06T18:15:34.170829Z",
+     "iopub.status.busy": "2023-09-06T18:15:34.170575Z",
+     "iopub.status.idle": "2023-09-06T18:37:51.518924Z",
+     "shell.execute_reply": "2023-09-06T18:37:51.518126Z"
     },
     "papermill": {
-     "duration": 1344.798073,
-     "end_time": "2023-09-06T17:35:39.101719",
+     "duration": 1337.357126,
+     "end_time": "2023-09-06T18:37:51.520884",
      "exception": false,
-     "start_time": "2023-09-06T17:13:14.303646",
+     "start_time": "2023-09-06T18:15:34.163758",
      "status": "completed"
     },
     "tags": []
@@ -980,7 +977,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:13:17,250] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:15:37,063] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -1002,9 +999,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1901440569\r\n",
+      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1209170682\r\n",
       "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 1901440569\r\n"
+      "Global seed set to 1209170682\r\n"
      ]
     },
     {
@@ -1019,11 +1016,11 @@
      "output_type": "stream",
      "text": [
       "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_171319-b0vmo30c\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_181539-sqg4ui8w\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5r3-L12-D2048-E0.1 - Enwiki-Instruct (train-ctx=4k, deepspeed_stage_1)\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/b0vmo30c\u001b[0m\r\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/sqg4ui8w\u001b[0m\r\n"
      ]
     },
     {
@@ -1066,21 +1063,21 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 225906.26 exa\r",
-      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 223980.21 exa\r\n",
+      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 231315.43 exa\r",
+      "Saving the dataset (1/1 shards): 100%|█| 14932/14932 [00:00<00:00, 229210.86 exa\r\n",
       "\r",
       "Saving the dataset (0/1 shards):   0%|            | 0/76 [00:00<?, ? examples/s]\r",
-      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 18962.94 examples/s\r",
-      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 18092.24 examples/s\r\n"
+      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 18919.05 examples/s\r",
+      "Saving the dataset (1/1 shards): 100%|█| 76/76 [00:00<00:00, 17983.03 examples/s\r\n",
+      "[rank: 0] Global seed set to 1209170682\r\n",
+      "initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1\r\n",
+      "[2023-09-06 18:15:49,924] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[rank: 0] Global seed set to 1901440569\r\n",
-      "initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1\r\n",
-      "[2023-09-06 17:13:30,164] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented\r\n",
       "Enabling DeepSpeed BF16.\r\n"
      ]
     },
@@ -1102,20 +1099,20 @@
       "    - lr_init:  4.000e-04 (0.0004)\r\n",
       "    - lr_final: 3.000e-04 (0.0003)\r\n",
       "\r\n",
-      "Using /root/.cache/torch_extensions/py310_cu118 as PyTorch extensions root...\r\n"
+      "Using /root/.cache/torch_extensions/py310_cu118 as PyTorch extensions root...\r\n",
+      "Detected CUDA files, patching ldflags\r\n",
+      "Emitting ninja build file /root/.cache/torch_extensions/py310_cu118/fused_adam/build.ninja...\r\n",
+      "Building extension module fused_adam...\r\n",
+      "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Detected CUDA files, patching ldflags\r\n",
-      "Emitting ninja build file /root/.cache/torch_extensions/py310_cu118/fused_adam/build.ninja...\r\n",
-      "Building extension module fused_adam...\r\n",
-      "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n",
       "ninja: no work to do.\r\n",
       "Loading extension module fused_adam...\r\n",
-      "Time to load fused_adam op: 0.06091904640197754 seconds\r\n",
+      "Time to load fused_adam op: 0.059059858322143555 seconds\r\n",
       "Loading `train_dataloader` to estimate number of stepping batches.\r\n"
      ]
     },
@@ -1159,44 +1156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%|                             | 1/14932 [00:04<18:52:50,  4.55s/it]\r",
-      "Epoch 0:   0%| | 1/14932 [00:04<18:53:05,  4.55s/it, v_num=o30c, train/loss=6.72"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:   0%| | 2/14932 [00:06<12:29:16,  3.01s/it, v_num=o30c, train/loss=6.72\r",
-      "Epoch 0:   0%| | 2/14932 [00:06<12:29:20,  3.01s/it, v_num=o30c, train/loss=5.22"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:   0%| | 3/14932 [00:06<9:14:29,  2.23s/it, v_num=o30c, train/loss=5.220\r",
-      "Epoch 0:   0%| | 3/14932 [00:06<9:14:33,  2.23s/it, v_num=o30c, train/loss=4.620"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:   0%| | 4/14932 [00:06<7:10:25,  1.73s/it, v_num=o30c, train/loss=4.620\r",
-      "Epoch 0:   0%| | 4/14932 [00:06<7:10:27,  1.73s/it, v_num=o30c, train/loss=3.560"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:   0%| | 5/14932 [00:07<6:19:34,  1.53s/it, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   0%| | 5/14932 [00:07<6:19:35,  1.53s/it, v_num=o30c, train/loss=5.560"
+      "Epoch 0:   0%|                             | 1/14932 [00:04<19:57:41,  4.81s/it]\r",
+      "Epoch 0:   0%| | 1/14932 [00:04<19:57:56,  4.81s/it, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -1204,8 +1165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 6/14932 [00:07<5:19:14,  1.28s/it, v_num=o30c, train/loss=5.560\r",
-      "Epoch 0:   0%| | 6/14932 [00:07<5:19:16,  1.28s/it, v_num=o30c, train/loss=5.410"
+      "Epoch 0:   0%| | 2/14932 [00:05<10:28:54,  2.53s/it, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:   0%| | 2/14932 [00:05<10:28:59,  2.53s/it, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -1213,8 +1174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 7/14932 [00:09<5:22:11,  1.30s/it, v_num=o30c, train/loss=5.410\r",
-      "Epoch 0:   0%| | 7/14932 [00:09<5:22:12,  1.30s/it, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   0%| | 3/14932 [00:06<8:53:36,  2.14s/it, v_num=ui8w, train/loss=4.660\r",
+      "Epoch 0:   0%| | 3/14932 [00:06<8:53:39,  2.14s/it, v_num=ui8w, train/loss=4.500"
      ]
     },
     {
@@ -1222,8 +1183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 8/14932 [00:09<5:00:15,  1.21s/it, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   0%| | 8/14932 [00:09<5:00:17,  1.21s/it, v_num=o30c, train/loss=4.560"
+      "Epoch 0:   0%| | 4/14932 [00:08<8:26:52,  2.04s/it, v_num=ui8w, train/loss=4.500\r",
+      "Epoch 0:   0%| | 4/14932 [00:08<8:26:58,  2.04s/it, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -1231,8 +1192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 9/14932 [00:09<4:28:52,  1.08s/it, v_num=o30c, train/loss=4.560\r",
-      "Epoch 0:   0%| | 9/14932 [00:09<4:28:53,  1.08s/it, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   0%| | 5/14932 [00:08<6:49:16,  1.65s/it, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   0%| | 5/14932 [00:08<6:49:19,  1.65s/it, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -1240,8 +1201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 10/14932 [00:09<4:03:37,  1.02it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   0%| | 10/14932 [00:09<4:03:38,  1.02it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:   0%| | 6/14932 [00:08<6:07:06,  1.48s/it, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   0%| | 6/14932 [00:08<6:07:07,  1.48s/it, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -1249,8 +1210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 11/14932 [00:09<3:43:06,  1.11it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:   0%| | 11/14932 [00:09<3:43:06,  1.11it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:   0%| | 7/14932 [00:08<5:17:02,  1.27s/it, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   0%| | 7/14932 [00:08<5:17:03,  1.27s/it, v_num=ui8w, train/loss=4.440"
      ]
     },
     {
@@ -1258,8 +1219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 12/14932 [00:10<3:37:28,  1.14it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:   0%| | 12/14932 [00:10<3:37:29,  1.14it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:   0%| | 8/14932 [00:08<4:39:33,  1.12s/it, v_num=ui8w, train/loss=4.440\r",
+      "Epoch 0:   0%| | 8/14932 [00:08<4:39:34,  1.12s/it, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -1267,8 +1228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 13/14932 [00:10<3:25:20,  1.21it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:   0%| | 13/14932 [00:10<3:25:21,  1.21it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:   0%| | 9/14932 [00:10<4:39:27,  1.12s/it, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   0%| | 9/14932 [00:10<4:39:28,  1.12s/it, v_num=ui8w, train/loss=6.340"
      ]
     },
     {
@@ -1276,8 +1237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 14/14932 [00:10<3:11:54,  1.30it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:   0%| | 14/14932 [00:10<3:11:55,  1.30it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:   0%| | 10/14932 [00:10<4:28:53,  1.08s/it, v_num=ui8w, train/loss=6.34\r",
+      "Epoch 0:   0%| | 10/14932 [00:10<4:28:54,  1.08s/it, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -1285,8 +1246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 15/14932 [00:10<3:00:16,  1.38it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:   0%| | 15/14932 [00:10<3:00:17,  1.38it/s, v_num=o30c, train/loss=5.62"
+      "Epoch 0:   0%| | 11/14932 [00:10<4:06:01,  1.01it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:   0%| | 11/14932 [00:10<4:06:02,  1.01it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -1294,8 +1255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 16/14932 [00:10<2:50:03,  1.46it/s, v_num=o30c, train/loss=5.62\r",
-      "Epoch 0:   0%| | 16/14932 [00:10<2:50:03,  1.46it/s, v_num=o30c, train/loss=6.16"
+      "Epoch 0:   0%| | 12/14932 [00:10<3:46:52,  1.10it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   0%| | 12/14932 [00:10<3:46:53,  1.10it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -1303,8 +1264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 17/14932 [00:11<2:41:07,  1.54it/s, v_num=o30c, train/loss=6.16\r",
-      "Epoch 0:   0%| | 17/14932 [00:11<2:41:07,  1.54it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:   0%| | 13/14932 [00:11<3:30:45,  1.18it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:   0%| | 13/14932 [00:11<3:30:46,  1.18it/s, v_num=ui8w, train/loss=6.66"
      ]
     },
     {
@@ -1312,8 +1273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 18/14932 [00:12<2:54:32,  1.42it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:   0%| | 18/14932 [00:12<2:54:35,  1.42it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:   0%| | 14/14932 [00:11<3:17:02,  1.26it/s, v_num=ui8w, train/loss=6.66\r",
+      "Epoch 0:   0%| | 14/14932 [00:11<3:17:03,  1.26it/s, v_num=ui8w, train/loss=5.69"
      ]
     },
     {
@@ -1321,8 +1282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 19/14932 [00:12<2:46:18,  1.49it/s, v_num=o30c, train/loss=4.94\r",
-      "Epoch 0:   0%| | 19/14932 [00:12<2:46:19,  1.49it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   0%| | 15/14932 [00:11<3:05:02,  1.34it/s, v_num=ui8w, train/loss=5.69\r",
+      "Epoch 0:   0%| | 15/14932 [00:11<3:05:03,  1.34it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -1330,8 +1291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 20/14932 [00:12<2:38:52,  1.56it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   0%| | 20/14932 [00:12<2:38:52,  1.56it/s, v_num=o30c, train/loss=5.81"
+      "Epoch 0:   0%| | 16/14932 [00:11<2:54:30,  1.42it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   0%| | 16/14932 [00:11<2:54:30,  1.42it/s, v_num=ui8w, train/loss=5.69"
      ]
     },
     {
@@ -1339,8 +1300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 21/14932 [00:12<2:32:07,  1.63it/s, v_num=o30c, train/loss=5.81\r",
-      "Epoch 0:   0%| | 21/14932 [00:12<2:32:07,  1.63it/s, v_num=o30c, train/loss=6.34"
+      "Epoch 0:   0%| | 17/14932 [00:11<2:53:02,  1.44it/s, v_num=ui8w, train/loss=5.69\r",
+      "Epoch 0:   0%| | 17/14932 [00:11<2:53:03,  1.44it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -1348,8 +1309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 22/14932 [00:12<2:26:45,  1.69it/s, v_num=o30c, train/loss=6.34\r",
-      "Epoch 0:   0%| | 22/14932 [00:12<2:26:47,  1.69it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:   0%| | 18/14932 [00:11<2:44:20,  1.51it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:   0%| | 18/14932 [00:11<2:44:21,  1.51it/s, v_num=ui8w, train/loss=5.38"
      ]
     },
     {
@@ -1357,8 +1318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 23/14932 [00:13<2:21:08,  1.76it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:   0%| | 23/14932 [00:13<2:21:08,  1.76it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:   0%| | 19/14932 [00:11<2:36:40,  1.59it/s, v_num=ui8w, train/loss=5.38\r",
+      "Epoch 0:   0%| | 19/14932 [00:11<2:36:40,  1.59it/s, v_num=ui8w, train/loss=7.69"
      ]
     },
     {
@@ -1366,8 +1327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 24/14932 [00:13<2:15:57,  1.83it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:   0%| | 24/14932 [00:13<2:15:58,  1.83it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:   0%| | 20/14932 [00:12<2:29:39,  1.66it/s, v_num=ui8w, train/loss=7.69\r",
+      "Epoch 0:   0%| | 20/14932 [00:12<2:29:40,  1.66it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -1375,8 +1336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 25/14932 [00:13<2:11:14,  1.89it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:   0%| | 25/14932 [00:13<2:11:14,  1.89it/s, v_num=o30c, train/loss=5.41"
+      "Epoch 0:   0%| | 21/14932 [00:12<2:23:22,  1.73it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:   0%| | 21/14932 [00:12<2:23:22,  1.73it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -1384,8 +1345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 26/14932 [00:13<2:06:52,  1.96it/s, v_num=o30c, train/loss=5.41\r",
-      "Epoch 0:   0%| | 26/14932 [00:13<2:06:53,  1.96it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:   0%| | 22/14932 [00:12<2:17:35,  1.81it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:   0%| | 22/14932 [00:12<2:17:36,  1.81it/s, v_num=ui8w, train/loss=5.38"
      ]
     },
     {
@@ -1393,8 +1354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 27/14932 [00:13<2:02:48,  2.02it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:   0%| | 27/14932 [00:13<2:02:48,  2.02it/s, v_num=o30c, train/loss=5.22"
+      "Epoch 0:   0%| | 23/14932 [00:12<2:12:20,  1.88it/s, v_num=ui8w, train/loss=5.38\r",
+      "Epoch 0:   0%| | 23/14932 [00:12<2:12:21,  1.88it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -1402,8 +1363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 28/14932 [00:13<1:59:03,  2.09it/s, v_num=o30c, train/loss=5.22\r",
-      "Epoch 0:   0%| | 28/14932 [00:13<1:59:04,  2.09it/s, v_num=o30c, train/loss=6.12"
+      "Epoch 0:   0%| | 24/14932 [00:12<2:07:33,  1.95it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:   0%| | 24/14932 [00:12<2:07:34,  1.95it/s, v_num=ui8w, train/loss=5.66"
      ]
     },
     {
@@ -1411,8 +1372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 29/14932 [00:13<1:56:07,  2.14it/s, v_num=o30c, train/loss=6.12\r",
-      "Epoch 0:   0%| | 29/14932 [00:13<1:56:08,  2.14it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:   0%| | 25/14932 [00:12<2:03:08,  2.02it/s, v_num=ui8w, train/loss=5.66\r",
+      "Epoch 0:   0%| | 25/14932 [00:12<2:03:09,  2.02it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -1420,8 +1381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 30/14932 [00:13<1:52:51,  2.20it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:   0%| | 30/14932 [00:13<1:52:51,  2.20it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   0%| | 26/14932 [00:13<2:04:29,  2.00it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:   0%| | 26/14932 [00:13<2:04:30,  2.00it/s, v_num=ui8w, train/loss=5.28"
      ]
     },
     {
@@ -1429,8 +1390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 31/14932 [00:13<1:49:47,  2.26it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:   0%| | 31/14932 [00:13<1:49:47,  2.26it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:   0%| | 27/14932 [00:13<2:00:30,  2.06it/s, v_num=ui8w, train/loss=5.28\r",
+      "Epoch 0:   0%| | 27/14932 [00:13<2:00:30,  2.06it/s, v_num=ui8w, train/loss=5.00"
      ]
     },
     {
@@ -1438,7 +1399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 32/14932 [00:13<1:47:25,  2.31it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:   0%| | 28/14932 [00:13<1:56:46,  2.13it/s, v_num=ui8w, train/loss=5.00\r",
+      "Epoch 0:   0%| | 28/14932 [00:13<1:56:47,  2.13it/s, v_num=ui8w, train/loss=5.00"
      ]
     },
     {
@@ -1446,7 +1408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 32/14932 [00:13<1:47:55,  2.30it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:   0%| | 29/14932 [00:13<1:53:21,  2.19it/s, v_num=ui8w, train/loss=5.00\r",
+      "Epoch 0:   0%| | 29/14932 [00:13<1:53:21,  2.19it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -1454,8 +1417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 33/14932 [00:13<1:45:08,  2.36it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:   0%| | 33/14932 [00:13<1:45:08,  2.36it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   0%| | 30/14932 [00:13<1:50:06,  2.26it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:   0%| | 30/14932 [00:13<1:50:07,  2.26it/s, v_num=ui8w, train/loss=5.25"
      ]
     },
     {
@@ -1463,8 +1426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 34/14932 [00:14<1:46:17,  2.34it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   0%| | 34/14932 [00:14<1:46:18,  2.34it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   0%| | 31/14932 [00:13<1:47:09,  2.32it/s, v_num=ui8w, train/loss=5.25\r",
+      "Epoch 0:   0%| | 31/14932 [00:13<1:47:10,  2.32it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -1472,8 +1435,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 35/14932 [00:14<1:43:45,  2.39it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   0%| | 35/14932 [00:14<1:43:45,  2.39it/s, v_num=o30c, train/loss=5.44"
+      "Epoch 0:   0%| | 32/14932 [00:13<1:44:55,  2.37it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -1481,8 +1443,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 36/14932 [00:14<1:41:21,  2.45it/s, v_num=o30c, train/loss=5.44\r",
-      "Epoch 0:   0%| | 36/14932 [00:14<1:41:21,  2.45it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:   0%| | 32/14932 [00:13<1:45:25,  2.36it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -1490,8 +1451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 37/14932 [00:14<1:39:09,  2.50it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:   0%| | 37/14932 [00:14<1:39:09,  2.50it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   0%| | 33/14932 [00:13<1:42:45,  2.42it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   0%| | 33/14932 [00:13<1:42:45,  2.42it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -1499,7 +1460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 38/14932 [00:14<1:36:59,  2.56it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   0%| | 34/14932 [00:13<1:40:14,  2.48it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   0%| | 34/14932 [00:13<1:40:14,  2.48it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -1507,7 +1469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 38/14932 [00:14<1:36:59,  2.56it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:   0%| | 35/14932 [00:13<1:37:56,  2.54it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:   0%| | 35/14932 [00:13<1:37:56,  2.54it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -1515,8 +1478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 39/14932 [00:14<1:34:56,  2.61it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:   0%| | 39/14932 [00:14<1:34:56,  2.61it/s, v_num=o30c, train/loss=5.25"
+      "Epoch 0:   0%| | 36/14932 [00:13<1:35:42,  2.59it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:   0%| | 36/14932 [00:13<1:35:43,  2.59it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -1524,8 +1487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 40/14932 [00:14<1:33:00,  2.67it/s, v_num=o30c, train/loss=5.25\r",
-      "Epoch 0:   0%| | 40/14932 [00:14<1:33:00,  2.67it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   0%| | 37/14932 [00:13<1:33:37,  2.65it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   0%| | 37/14932 [00:13<1:33:37,  2.65it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -1533,8 +1496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 41/14932 [00:15<1:31:09,  2.72it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   0%| | 41/14932 [00:15<1:31:09,  2.72it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:   0%| | 38/14932 [00:14<1:31:37,  2.71it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   0%| | 38/14932 [00:14<1:31:38,  2.71it/s, v_num=ui8w, train/loss=5.06"
      ]
     },
     {
@@ -1542,8 +1505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 42/14932 [00:15<1:29:25,  2.78it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:   0%| | 42/14932 [00:15<1:29:25,  2.78it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:   0%| | 39/14932 [00:14<1:29:44,  2.77it/s, v_num=ui8w, train/loss=5.06\r",
+      "Epoch 0:   0%| | 39/14932 [00:14<1:29:44,  2.77it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -1551,8 +1514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 43/14932 [00:15<1:27:45,  2.83it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:   0%| | 43/14932 [00:15<1:27:45,  2.83it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:   0%| | 40/14932 [00:14<1:27:54,  2.82it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:   0%| | 40/14932 [00:14<1:27:54,  2.82it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -1560,8 +1523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 44/14932 [00:15<1:26:10,  2.88it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:   0%| | 44/14932 [00:15<1:26:10,  2.88it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:   0%| | 41/14932 [00:14<1:26:12,  2.88it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:   0%| | 41/14932 [00:14<1:26:12,  2.88it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -1569,8 +1532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 45/14932 [00:15<1:24:40,  2.93it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:   0%| | 45/14932 [00:15<1:24:40,  2.93it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:   0%| | 42/14932 [00:14<1:24:35,  2.93it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   0%| | 42/14932 [00:14<1:24:35,  2.93it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -1578,8 +1541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 46/14932 [00:15<1:23:13,  2.98it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:   0%| | 46/14932 [00:15<1:23:14,  2.98it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:   0%| | 43/14932 [00:14<1:23:03,  2.99it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:   0%| | 43/14932 [00:14<1:23:03,  2.99it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -1587,8 +1550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 47/14932 [00:15<1:21:49,  3.03it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:   0%| | 47/14932 [00:15<1:21:49,  3.03it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:   0%| | 44/14932 [00:14<1:21:33,  3.04it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:   0%| | 44/14932 [00:14<1:21:34,  3.04it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -1596,8 +1559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 48/14932 [00:15<1:20:29,  3.08it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:   0%| | 48/14932 [00:15<1:20:29,  3.08it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:   0%| | 45/14932 [00:14<1:20:09,  3.10it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:   0%| | 45/14932 [00:14<1:20:09,  3.10it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -1605,8 +1568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 49/14932 [00:15<1:19:11,  3.13it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:   0%| | 49/14932 [00:15<1:19:11,  3.13it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:   0%| | 46/14932 [00:14<1:18:48,  3.15it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:   0%| | 46/14932 [00:14<1:18:48,  3.15it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -1614,8 +1577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 50/14932 [00:15<1:17:56,  3.18it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:   0%| | 50/14932 [00:15<1:17:56,  3.18it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   0%| | 47/14932 [00:14<1:17:31,  3.20it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:   0%| | 47/14932 [00:14<1:17:32,  3.20it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -1623,8 +1586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 51/14932 [00:15<1:16:42,  3.23it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   0%| | 51/14932 [00:15<1:16:42,  3.23it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:   0%| | 48/14932 [00:14<1:16:17,  3.25it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:   0%| | 48/14932 [00:14<1:16:17,  3.25it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -1632,8 +1595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 52/14932 [00:15<1:15:33,  3.28it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:   0%| | 52/14932 [00:15<1:15:33,  3.28it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:   0%| | 49/14932 [00:14<1:15:05,  3.30it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:   0%| | 49/14932 [00:14<1:15:05,  3.30it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -1641,8 +1604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 53/14932 [00:15<1:14:25,  3.33it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:   0%| | 53/14932 [00:15<1:14:25,  3.33it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:   0%| | 50/14932 [00:14<1:13:55,  3.35it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   0%| | 50/14932 [00:14<1:13:55,  3.35it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -1650,8 +1613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 54/14932 [00:15<1:13:21,  3.38it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:   0%| | 54/14932 [00:15<1:13:21,  3.38it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   0%| | 51/14932 [00:14<1:12:48,  3.41it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:   0%| | 51/14932 [00:14<1:12:48,  3.41it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -1659,8 +1622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 55/14932 [00:16<1:12:51,  3.40it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   0%| | 55/14932 [00:16<1:12:51,  3.40it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   0%| | 52/14932 [00:15<1:11:42,  3.46it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:   0%| | 52/14932 [00:15<1:11:42,  3.46it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -1668,8 +1631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 56/14932 [00:16<1:11:51,  3.45it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   0%| | 56/14932 [00:16<1:11:51,  3.45it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:   0%| | 53/14932 [00:15<1:10:40,  3.51it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   0%| | 53/14932 [00:15<1:10:40,  3.51it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -1677,8 +1640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 57/14932 [00:16<1:10:52,  3.50it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:   0%| | 57/14932 [00:16<1:10:52,  3.50it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:   0%| | 54/14932 [00:15<1:09:42,  3.56it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:   0%| | 54/14932 [00:15<1:09:42,  3.56it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -1686,7 +1649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 58/14932 [00:16<1:09:57,  3.54it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:   0%| | 55/14932 [00:15<1:08:45,  3.61it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:   0%| | 55/14932 [00:15<1:08:45,  3.61it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -1694,7 +1658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 58/14932 [00:16<1:09:57,  3.54it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:   0%| | 56/14932 [00:15<1:07:48,  3.66it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:   0%| | 56/14932 [00:15<1:07:49,  3.66it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -1702,8 +1667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 59/14932 [00:16<1:09:04,  3.59it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:   0%| | 59/14932 [00:16<1:09:04,  3.59it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:   0%| | 57/14932 [00:15<1:06:55,  3.70it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:   0%| | 57/14932 [00:15<1:06:55,  3.70it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -1711,8 +1676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 60/14932 [00:16<1:08:14,  3.63it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:   0%| | 60/14932 [00:16<1:08:14,  3.63it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:   0%| | 58/14932 [00:15<1:06:03,  3.75it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   0%| | 58/14932 [00:15<1:06:03,  3.75it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -1720,8 +1685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 61/14932 [00:16<1:07:23,  3.68it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:   0%| | 61/14932 [00:16<1:07:23,  3.68it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:   0%| | 59/14932 [00:15<1:05:13,  3.80it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:   0%| | 59/14932 [00:15<1:05:13,  3.80it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -1729,8 +1694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 62/14932 [00:16<1:06:35,  3.72it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:   0%| | 62/14932 [00:16<1:06:35,  3.72it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   0%| | 60/14932 [00:15<1:04:24,  3.85it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:   0%| | 60/14932 [00:15<1:04:24,  3.85it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -1738,8 +1703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 63/14932 [00:16<1:05:47,  3.77it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   0%| | 63/14932 [00:16<1:05:47,  3.77it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:   0%| | 61/14932 [00:15<1:03:38,  3.89it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:   0%| | 61/14932 [00:15<1:03:38,  3.89it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -1747,7 +1712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 64/14932 [00:16<1:05:15,  3.80it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:   0%| | 62/14932 [00:16<1:05:00,  3.81it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:   0%| | 62/14932 [00:16<1:05:00,  3.81it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -1755,7 +1721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 64/14932 [00:16<1:05:30,  3.78it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:   0%| | 63/14932 [00:16<1:04:13,  3.86it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:   0%| | 63/14932 [00:16<1:04:14,  3.86it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -1763,8 +1730,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 65/14932 [00:16<1:04:43,  3.83it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:   0%| | 65/14932 [00:16<1:04:44,  3.83it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:   0%| | 64/14932 [00:16<1:05:42,  3.77it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -1772,8 +1738,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 66/14932 [00:17<1:03:59,  3.87it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:   0%| | 66/14932 [00:17<1:04:00,  3.87it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:   0%| | 64/14932 [00:17<1:05:57,  3.76it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -1781,8 +1746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 67/14932 [00:17<1:03:32,  3.90it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:   0%| | 67/14932 [00:17<1:03:32,  3.90it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   0%| | 65/14932 [00:17<1:05:11,  3.80it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:   0%| | 65/14932 [00:17<1:05:11,  3.80it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -1790,8 +1755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 68/14932 [00:17<1:02:51,  3.94it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   0%| | 68/14932 [00:17<1:02:51,  3.94it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:   0%| | 66/14932 [00:17<1:04:27,  3.84it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:   0%| | 66/14932 [00:17<1:04:27,  3.84it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -1799,8 +1764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 69/14932 [00:17<1:02:11,  3.98it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:   0%| | 69/14932 [00:17<1:02:11,  3.98it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   0%| | 67/14932 [00:17<1:03:45,  3.89it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:   0%| | 67/14932 [00:17<1:03:45,  3.89it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -1808,8 +1773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 70/14932 [00:17<1:01:33,  4.02it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   0%| | 70/14932 [00:17<1:01:33,  4.02it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:   0%| | 68/14932 [00:17<1:03:03,  3.93it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:   0%| | 68/14932 [00:17<1:03:03,  3.93it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -1817,8 +1782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 71/14932 [00:17<1:00:55,  4.07it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:   0%| | 71/14932 [00:17<1:00:55,  4.06it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   0%| | 69/14932 [00:17<1:02:23,  3.97it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:   0%| | 69/14932 [00:17<1:02:23,  3.97it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -1826,8 +1791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 72/14932 [00:17<1:00:19,  4.11it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   0%| | 72/14932 [00:17<1:00:19,  4.11it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:   0%| | 70/14932 [00:17<1:01:44,  4.01it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:   0%| | 70/14932 [00:17<1:01:45,  4.01it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -1835,8 +1800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 73/14932 [00:17<59:43,  4.15it/s, v_num=o30c, train/loss=3.590]\r",
-      "Epoch 0:   0%| | 73/14932 [00:17<59:43,  4.15it/s, v_num=o30c, train/loss=4.160]"
+      "Epoch 0:   0%| | 71/14932 [00:17<1:01:07,  4.05it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:   0%| | 71/14932 [00:17<1:01:07,  4.05it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -1844,8 +1809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   0%| | 74/14932 [00:17<59:08,  4.19it/s, v_num=o30c, train/loss=4.160]\r",
-      "Epoch 0:   0%| | 74/14932 [00:17<59:08,  4.19it/s, v_num=o30c, train/loss=4.160]"
+      "Epoch 0:   0%| | 72/14932 [00:17<1:00:31,  4.09it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:   0%| | 72/14932 [00:17<1:00:31,  4.09it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -1853,8 +1818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 75/14932 [00:17<58:35,  4.23it/s, v_num=o30c, train/loss=4.160]\r",
-      "Epoch 0:   1%| | 75/14932 [00:17<58:35,  4.23it/s, v_num=o30c, train/loss=2.450]"
+      "Epoch 0:   0%| | 73/14932 [00:17<59:55,  4.13it/s, v_num=ui8w, train/loss=3.120]\r",
+      "Epoch 0:   0%| | 73/14932 [00:17<59:55,  4.13it/s, v_num=ui8w, train/loss=2.050]"
      ]
     },
     {
@@ -1862,8 +1827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 76/14932 [00:17<58:01,  4.27it/s, v_num=o30c, train/loss=2.450]\r",
-      "Epoch 0:   1%| | 76/14932 [00:17<58:01,  4.27it/s, v_num=o30c, train/loss=3.030]"
+      "Epoch 0:   0%| | 74/14932 [00:17<59:20,  4.17it/s, v_num=ui8w, train/loss=2.050]\r",
+      "Epoch 0:   0%| | 74/14932 [00:17<59:20,  4.17it/s, v_num=ui8w, train/loss=3.700]"
      ]
     },
     {
@@ -1871,8 +1836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 77/14932 [00:17<57:28,  4.31it/s, v_num=o30c, train/loss=3.030]\r",
-      "Epoch 0:   1%| | 77/14932 [00:17<57:28,  4.31it/s, v_num=o30c, train/loss=3.730]"
+      "Epoch 0:   1%| | 75/14932 [00:17<58:46,  4.21it/s, v_num=ui8w, train/loss=3.700]\r",
+      "Epoch 0:   1%| | 75/14932 [00:17<58:46,  4.21it/s, v_num=ui8w, train/loss=2.640]"
      ]
     },
     {
@@ -1880,8 +1845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 78/14932 [00:17<56:57,  4.35it/s, v_num=o30c, train/loss=3.730]\r",
-      "Epoch 0:   1%| | 78/14932 [00:17<56:57,  4.35it/s, v_num=o30c, train/loss=3.470]"
+      "Epoch 0:   1%| | 76/14932 [00:18<1:01:29,  4.03it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:   1%| | 76/14932 [00:18<1:01:29,  4.03it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -1889,8 +1854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 79/14932 [00:18<56:28,  4.38it/s, v_num=o30c, train/loss=3.470]\r",
-      "Epoch 0:   1%| | 79/14932 [00:18<56:28,  4.38it/s, v_num=o30c, train/loss=2.770]"
+      "Epoch 0:   1%| | 77/14932 [00:18<1:00:55,  4.06it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:   1%| | 77/14932 [00:18<1:00:55,  4.06it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -1898,8 +1863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 80/14932 [00:18<55:58,  4.42it/s, v_num=o30c, train/loss=2.770]\r",
-      "Epoch 0:   1%| | 80/14932 [00:18<55:58,  4.42it/s, v_num=o30c, train/loss=4.280]"
+      "Epoch 0:   1%| | 78/14932 [00:19<1:00:21,  4.10it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:   1%| | 78/14932 [00:19<1:00:21,  4.10it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -1907,8 +1872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 81/14932 [00:18<55:28,  4.46it/s, v_num=o30c, train/loss=4.280]\r",
-      "Epoch 0:   1%| | 81/14932 [00:18<55:28,  4.46it/s, v_num=o30c, train/loss=2.950]"
+      "Epoch 0:   1%| | 79/14932 [00:19<59:47,  4.14it/s, v_num=ui8w, train/loss=3.200]\r",
+      "Epoch 0:   1%| | 79/14932 [00:19<59:47,  4.14it/s, v_num=ui8w, train/loss=4.410]"
      ]
     },
     {
@@ -1916,8 +1881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 82/14932 [00:18<55:11,  4.48it/s, v_num=o30c, train/loss=2.950]\r",
-      "Epoch 0:   1%| | 82/14932 [00:18<55:11,  4.48it/s, v_num=o30c, train/loss=4.120]"
+      "Epoch 0:   1%| | 80/14932 [00:19<59:15,  4.18it/s, v_num=ui8w, train/loss=4.410]\r",
+      "Epoch 0:   1%| | 80/14932 [00:19<59:15,  4.18it/s, v_num=ui8w, train/loss=5.030]"
      ]
     },
     {
@@ -1925,8 +1890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 83/14932 [00:18<54:44,  4.52it/s, v_num=o30c, train/loss=4.120]\r",
-      "Epoch 0:   1%| | 83/14932 [00:18<54:44,  4.52it/s, v_num=o30c, train/loss=4.280]"
+      "Epoch 0:   1%| | 81/14932 [00:19<58:42,  4.22it/s, v_num=ui8w, train/loss=5.030]\r",
+      "Epoch 0:   1%| | 81/14932 [00:19<58:42,  4.22it/s, v_num=ui8w, train/loss=3.480]"
      ]
     },
     {
@@ -1934,8 +1899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 84/14932 [00:18<54:17,  4.56it/s, v_num=o30c, train/loss=4.280]\r",
-      "Epoch 0:   1%| | 84/14932 [00:18<54:17,  4.56it/s, v_num=o30c, train/loss=3.780]"
+      "Epoch 0:   1%| | 82/14932 [00:19<58:12,  4.25it/s, v_num=ui8w, train/loss=3.480]\r",
+      "Epoch 0:   1%| | 82/14932 [00:19<58:12,  4.25it/s, v_num=ui8w, train/loss=4.310]"
      ]
     },
     {
@@ -1943,8 +1908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 85/14932 [00:18<53:50,  4.60it/s, v_num=o30c, train/loss=3.780]\r",
-      "Epoch 0:   1%| | 85/14932 [00:18<53:50,  4.60it/s, v_num=o30c, train/loss=3.520]"
+      "Epoch 0:   1%| | 83/14932 [00:19<57:42,  4.29it/s, v_num=ui8w, train/loss=4.310]\r",
+      "Epoch 0:   1%| | 83/14932 [00:19<57:42,  4.29it/s, v_num=ui8w, train/loss=3.110]"
      ]
     },
     {
@@ -1952,8 +1917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 86/14932 [00:18<53:26,  4.63it/s, v_num=o30c, train/loss=3.520]\r",
-      "Epoch 0:   1%| | 86/14932 [00:18<53:26,  4.63it/s, v_num=o30c, train/loss=3.690]"
+      "Epoch 0:   1%| | 84/14932 [00:19<57:11,  4.33it/s, v_num=ui8w, train/loss=3.110]\r",
+      "Epoch 0:   1%| | 84/14932 [00:19<57:12,  4.33it/s, v_num=ui8w, train/loss=3.450]"
      ]
     },
     {
@@ -1961,8 +1926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 87/14932 [00:18<53:01,  4.67it/s, v_num=o30c, train/loss=3.690]\r",
-      "Epoch 0:   1%| | 87/14932 [00:18<53:02,  4.67it/s, v_num=o30c, train/loss=4.090]"
+      "Epoch 0:   1%| | 85/14932 [00:19<56:45,  4.36it/s, v_num=ui8w, train/loss=3.450]\r",
+      "Epoch 0:   1%| | 85/14932 [00:19<56:45,  4.36it/s, v_num=ui8w, train/loss=4.160]"
      ]
     },
     {
@@ -1970,8 +1935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 88/14932 [00:18<52:39,  4.70it/s, v_num=o30c, train/loss=4.090]\r",
-      "Epoch 0:   1%| | 88/14932 [00:18<52:39,  4.70it/s, v_num=o30c, train/loss=3.890]"
+      "Epoch 0:   1%| | 86/14932 [00:19<56:18,  4.39it/s, v_num=ui8w, train/loss=4.160]\r",
+      "Epoch 0:   1%| | 86/14932 [00:19<56:18,  4.39it/s, v_num=ui8w, train/loss=3.920]"
      ]
     },
     {
@@ -1979,8 +1944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 89/14932 [00:18<52:25,  4.72it/s, v_num=o30c, train/loss=3.890]\r",
-      "Epoch 0:   1%| | 89/14932 [00:18<52:25,  4.72it/s, v_num=o30c, train/loss=3.700]"
+      "Epoch 0:   1%| | 87/14932 [00:19<55:51,  4.43it/s, v_num=ui8w, train/loss=3.920]\r",
+      "Epoch 0:   1%| | 87/14932 [00:19<55:52,  4.43it/s, v_num=ui8w, train/loss=2.860]"
      ]
     },
     {
@@ -1988,8 +1953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 90/14932 [00:18<52:03,  4.75it/s, v_num=o30c, train/loss=3.700]\r",
-      "Epoch 0:   1%| | 90/14932 [00:18<52:03,  4.75it/s, v_num=o30c, train/loss=3.980]"
+      "Epoch 0:   1%| | 88/14932 [00:19<55:25,  4.46it/s, v_num=ui8w, train/loss=2.860]\r",
+      "Epoch 0:   1%| | 88/14932 [00:19<55:25,  4.46it/s, v_num=ui8w, train/loss=3.410]"
      ]
     },
     {
@@ -1997,8 +1962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 91/14932 [00:19<51:41,  4.79it/s, v_num=o30c, train/loss=3.980]\r",
-      "Epoch 0:   1%| | 91/14932 [00:19<51:41,  4.79it/s, v_num=o30c, train/loss=3.450]"
+      "Epoch 0:   1%| | 89/14932 [00:19<55:00,  4.50it/s, v_num=ui8w, train/loss=3.410]\r",
+      "Epoch 0:   1%| | 89/14932 [00:19<55:00,  4.50it/s, v_num=ui8w, train/loss=3.480]"
      ]
     },
     {
@@ -2006,8 +1971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 92/14932 [00:19<51:18,  4.82it/s, v_num=o30c, train/loss=3.450]\r",
-      "Epoch 0:   1%| | 92/14932 [00:19<51:18,  4.82it/s, v_num=o30c, train/loss=4.120]"
+      "Epoch 0:   1%| | 90/14932 [00:19<54:45,  4.52it/s, v_num=ui8w, train/loss=3.480]\r",
+      "Epoch 0:   1%| | 90/14932 [00:19<54:45,  4.52it/s, v_num=ui8w, train/loss=3.660]"
      ]
     },
     {
@@ -2015,8 +1980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 93/14932 [00:19<51:06,  4.84it/s, v_num=o30c, train/loss=4.120]\r",
-      "Epoch 0:   1%| | 93/14932 [00:19<51:06,  4.84it/s, v_num=o30c, train/loss=3.250]"
+      "Epoch 0:   1%| | 91/14932 [00:19<54:20,  4.55it/s, v_num=ui8w, train/loss=3.660]\r",
+      "Epoch 0:   1%| | 91/14932 [00:19<54:20,  4.55it/s, v_num=ui8w, train/loss=3.270]"
      ]
     },
     {
@@ -2024,8 +1989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 94/14932 [00:19<50:44,  4.87it/s, v_num=o30c, train/loss=3.250]\r",
-      "Epoch 0:   1%| | 94/14932 [00:19<50:44,  4.87it/s, v_num=o30c, train/loss=4.060]"
+      "Epoch 0:   1%| | 92/14932 [00:20<53:56,  4.59it/s, v_num=ui8w, train/loss=3.270]\r",
+      "Epoch 0:   1%| | 92/14932 [00:20<53:56,  4.59it/s, v_num=ui8w, train/loss=3.030]"
      ]
     },
     {
@@ -2033,8 +1998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 95/14932 [00:19<50:24,  4.91it/s, v_num=o30c, train/loss=4.060]\r",
-      "Epoch 0:   1%| | 95/14932 [00:19<50:24,  4.91it/s, v_num=o30c, train/loss=4.250]"
+      "Epoch 0:   1%| | 93/14932 [00:20<53:31,  4.62it/s, v_num=ui8w, train/loss=3.030]\r",
+      "Epoch 0:   1%| | 93/14932 [00:20<53:31,  4.62it/s, v_num=ui8w, train/loss=4.220]"
      ]
     },
     {
@@ -2042,8 +2007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 96/14932 [00:19<50:21,  4.91it/s, v_num=o30c, train/loss=4.250]\r",
-      "Epoch 0:   1%| | 96/14932 [00:19<50:21,  4.91it/s, v_num=o30c, train/loss=3.230]"
+      "Epoch 0:   1%| | 94/14932 [00:20<53:09,  4.65it/s, v_num=ui8w, train/loss=4.220]\r",
+      "Epoch 0:   1%| | 94/14932 [00:20<53:09,  4.65it/s, v_num=ui8w, train/loss=3.610]"
      ]
     },
     {
@@ -2051,8 +2016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 97/14932 [00:19<50:01,  4.94it/s, v_num=o30c, train/loss=3.230]\r",
-      "Epoch 0:   1%| | 97/14932 [00:19<50:01,  4.94it/s, v_num=o30c, train/loss=3.390]"
+      "Epoch 0:   1%| | 95/14932 [00:20<52:47,  4.68it/s, v_num=ui8w, train/loss=3.610]\r",
+      "Epoch 0:   1%| | 95/14932 [00:20<52:47,  4.68it/s, v_num=ui8w, train/loss=4.380]"
      ]
     },
     {
@@ -2060,8 +2025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 98/14932 [00:19<49:40,  4.98it/s, v_num=o30c, train/loss=3.390]\r",
-      "Epoch 0:   1%| | 98/14932 [00:19<49:40,  4.98it/s, v_num=o30c, train/loss=2.750]"
+      "Epoch 0:   1%| | 96/14932 [00:20<52:43,  4.69it/s, v_num=ui8w, train/loss=4.380]\r",
+      "Epoch 0:   1%| | 96/14932 [00:20<52:43,  4.69it/s, v_num=ui8w, train/loss=3.800]"
      ]
     },
     {
@@ -2069,8 +2034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 99/14932 [00:19<49:21,  5.01it/s, v_num=o30c, train/loss=2.750]\r",
-      "Epoch 0:   1%| | 99/14932 [00:19<49:21,  5.01it/s, v_num=o30c, train/loss=2.830]"
+      "Epoch 0:   1%| | 97/14932 [00:20<52:30,  4.71it/s, v_num=ui8w, train/loss=3.800]\r",
+      "Epoch 0:   1%| | 97/14932 [00:20<52:30,  4.71it/s, v_num=ui8w, train/loss=3.360]"
      ]
     },
     {
@@ -2078,8 +2043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 100/14932 [00:19<49:01,  5.04it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   1%| | 100/14932 [00:19<49:02,  5.04it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   1%| | 98/14932 [00:20<52:09,  4.74it/s, v_num=ui8w, train/loss=3.360]\r",
+      "Epoch 0:   1%| | 98/14932 [00:20<52:09,  4.74it/s, v_num=ui8w, train/loss=3.120]"
      ]
     },
     {
@@ -2087,8 +2052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 101/14932 [00:20<50:38,  4.88it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   1%| | 101/14932 [00:20<50:38,  4.88it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   1%| | 99/14932 [00:20<51:47,  4.77it/s, v_num=ui8w, train/loss=3.120]\r",
+      "Epoch 0:   1%| | 99/14932 [00:20<51:47,  4.77it/s, v_num=ui8w, train/loss=3.880]"
      ]
     },
     {
@@ -2096,8 +2061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 102/14932 [00:20<50:18,  4.91it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   1%| | 102/14932 [00:20<50:18,  4.91it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   1%| | 100/14932 [00:20<51:26,  4.80it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   1%| | 100/14932 [00:20<51:26,  4.80it/s, v_num=ui8w, train/loss=2.530"
      ]
     },
     {
@@ -2105,8 +2070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 103/14932 [00:20<49:58,  4.94it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   1%| | 103/14932 [00:20<49:58,  4.94it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   1%| | 101/14932 [00:20<51:06,  4.84it/s, v_num=ui8w, train/loss=2.530\r",
+      "Epoch 0:   1%| | 101/14932 [00:20<51:06,  4.84it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -2114,8 +2079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 104/14932 [00:20<49:40,  4.97it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   1%| | 104/14932 [00:20<49:40,  4.97it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   1%| | 102/14932 [00:20<50:47,  4.87it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   1%| | 102/14932 [00:20<50:47,  4.87it/s, v_num=ui8w, train/loss=2.860"
      ]
     },
     {
@@ -2123,8 +2088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 105/14932 [00:20<49:22,  5.01it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   1%| | 105/14932 [00:20<49:22,  5.01it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   1%| | 103/14932 [00:21<50:28,  4.90it/s, v_num=ui8w, train/loss=2.860\r",
+      "Epoch 0:   1%| | 103/14932 [00:21<50:28,  4.90it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -2132,8 +2097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 106/14932 [00:21<49:04,  5.04it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   1%| | 106/14932 [00:21<49:04,  5.04it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   1%| | 104/14932 [00:21<50:10,  4.93it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   1%| | 104/14932 [00:21<50:10,  4.93it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -2141,8 +2106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 107/14932 [00:21<49:58,  4.94it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   1%| | 107/14932 [00:21<49:58,  4.94it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   1%| | 105/14932 [00:21<49:51,  4.96it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   1%| | 105/14932 [00:21<49:51,  4.96it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -2150,8 +2115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 108/14932 [00:21<49:56,  4.95it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   1%| | 108/14932 [00:21<49:56,  4.95it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   1%| | 106/14932 [00:21<49:33,  4.99it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   1%| | 106/14932 [00:21<49:33,  4.99it/s, v_num=ui8w, train/loss=3.440"
      ]
     },
     {
@@ -2159,8 +2124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 109/14932 [00:21<49:37,  4.98it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   1%| | 109/14932 [00:21<49:37,  4.98it/s, v_num=o30c, train/loss=4.560"
+      "Epoch 0:   1%| | 107/14932 [00:21<49:16,  5.01it/s, v_num=ui8w, train/loss=3.440\r",
+      "Epoch 0:   1%| | 107/14932 [00:21<49:16,  5.01it/s, v_num=ui8w, train/loss=2.300"
      ]
     },
     {
@@ -2168,8 +2133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 110/14932 [00:21<49:19,  5.01it/s, v_num=o30c, train/loss=4.560\r",
-      "Epoch 0:   1%| | 110/14932 [00:21<49:19,  5.01it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   1%| | 108/14932 [00:21<48:58,  5.04it/s, v_num=ui8w, train/loss=2.300\r",
+      "Epoch 0:   1%| | 108/14932 [00:21<48:58,  5.04it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -2177,8 +2142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 111/14932 [00:22<49:02,  5.04it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   1%| | 111/14932 [00:22<49:02,  5.04it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   1%| | 109/14932 [00:21<48:41,  5.07it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   1%| | 109/14932 [00:21<48:42,  5.07it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -2186,8 +2151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 112/14932 [00:22<48:45,  5.07it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   1%| | 112/14932 [00:22<48:45,  5.07it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   1%| | 110/14932 [00:21<48:24,  5.10it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   1%| | 110/14932 [00:21<48:24,  5.10it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -2195,8 +2160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 113/14932 [00:22<48:28,  5.10it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   1%| | 113/14932 [00:22<48:28,  5.10it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   1%| | 111/14932 [00:21<48:07,  5.13it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   1%| | 111/14932 [00:21<48:07,  5.13it/s, v_num=ui8w, train/loss=1.770"
      ]
     },
     {
@@ -2204,8 +2169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 114/14932 [00:22<48:11,  5.13it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   1%| | 114/14932 [00:22<48:11,  5.13it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   1%| | 112/14932 [00:21<47:51,  5.16it/s, v_num=ui8w, train/loss=1.770\r",
+      "Epoch 0:   1%| | 112/14932 [00:21<47:51,  5.16it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -2213,8 +2178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 115/14932 [00:22<47:55,  5.15it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   1%| | 115/14932 [00:22<47:55,  5.15it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   1%| | 113/14932 [00:21<47:34,  5.19it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   1%| | 113/14932 [00:21<47:34,  5.19it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -2222,8 +2187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 116/14932 [00:22<47:39,  5.18it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   1%| | 116/14932 [00:22<47:39,  5.18it/s, v_num=o30c, train/loss=2.410"
+      "Epoch 0:   1%| | 114/14932 [00:21<47:19,  5.22it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   1%| | 114/14932 [00:21<47:19,  5.22it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -2231,8 +2196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 117/14932 [00:22<47:24,  5.21it/s, v_num=o30c, train/loss=2.410\r",
-      "Epoch 0:   1%| | 117/14932 [00:22<47:24,  5.21it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   1%| | 115/14932 [00:21<47:04,  5.25it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   1%| | 115/14932 [00:21<47:04,  5.25it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -2240,8 +2205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 118/14932 [00:22<47:08,  5.24it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   1%| | 118/14932 [00:22<47:08,  5.24it/s, v_num=o30c, train/loss=6.250"
+      "Epoch 0:   1%| | 116/14932 [00:21<46:48,  5.28it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   1%| | 116/14932 [00:21<46:48,  5.28it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -2249,8 +2214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 119/14932 [00:22<46:53,  5.27it/s, v_num=o30c, train/loss=6.250\r",
-      "Epoch 0:   1%| | 119/14932 [00:22<46:53,  5.27it/s, v_num=o30c, train/loss=3.980"
+      "Epoch 0:   1%| | 117/14932 [00:22<46:32,  5.30it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   1%| | 117/14932 [00:22<46:32,  5.30it/s, v_num=ui8w, train/loss=2.530"
      ]
     },
     {
@@ -2258,8 +2223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 120/14932 [00:22<46:37,  5.29it/s, v_num=o30c, train/loss=3.980\r",
-      "Epoch 0:   1%| | 120/14932 [00:22<46:37,  5.29it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   1%| | 118/14932 [00:22<46:18,  5.33it/s, v_num=ui8w, train/loss=2.530\r",
+      "Epoch 0:   1%| | 118/14932 [00:22<46:18,  5.33it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -2267,8 +2232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 121/14932 [00:22<46:23,  5.32it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   1%| | 121/14932 [00:22<46:23,  5.32it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   1%| | 119/14932 [00:22<46:03,  5.36it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   1%| | 119/14932 [00:22<46:03,  5.36it/s, v_num=ui8w, train/loss=5.060"
      ]
     },
     {
@@ -2276,8 +2241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 122/14932 [00:22<46:09,  5.35it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   1%| | 122/14932 [00:22<46:09,  5.35it/s, v_num=o30c, train/loss=2.840"
+      "Epoch 0:   1%| | 120/14932 [00:22<45:48,  5.39it/s, v_num=ui8w, train/loss=5.060\r",
+      "Epoch 0:   1%| | 120/14932 [00:22<45:48,  5.39it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -2285,8 +2250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 123/14932 [00:22<45:56,  5.37it/s, v_num=o30c, train/loss=2.840\r",
-      "Epoch 0:   1%| | 123/14932 [00:22<45:56,  5.37it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   1%| | 121/14932 [00:22<45:35,  5.42it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   1%| | 121/14932 [00:22<45:35,  5.42it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -2294,8 +2259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 124/14932 [00:22<45:42,  5.40it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   1%| | 124/14932 [00:22<45:42,  5.40it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   1%| | 122/14932 [00:22<45:21,  5.44it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   1%| | 122/14932 [00:22<45:21,  5.44it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -2303,8 +2268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 125/14932 [00:23<45:29,  5.43it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   1%| | 125/14932 [00:23<45:29,  5.43it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   1%| | 123/14932 [00:22<45:07,  5.47it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   1%| | 123/14932 [00:22<45:07,  5.47it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -2312,8 +2277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 126/14932 [00:23<45:16,  5.45it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   1%| | 126/14932 [00:23<45:16,  5.45it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   1%| | 124/14932 [00:22<44:54,  5.50it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   1%| | 124/14932 [00:22<44:54,  5.50it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -2321,8 +2286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 127/14932 [00:23<45:03,  5.48it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   1%| | 127/14932 [00:23<45:04,  5.48it/s, v_num=o30c, train/loss=3.840"
+      "Epoch 0:   1%| | 125/14932 [00:22<44:41,  5.52it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   1%| | 125/14932 [00:22<44:41,  5.52it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -2330,8 +2295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 128/14932 [00:23<45:04,  5.47it/s, v_num=o30c, train/loss=3.840\r",
-      "Epoch 0:   1%| | 128/14932 [00:23<45:04,  5.47it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   1%| | 126/14932 [00:22<44:28,  5.55it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   1%| | 126/14932 [00:22<44:28,  5.55it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -2339,8 +2304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 129/14932 [00:23<44:52,  5.50it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   1%| | 129/14932 [00:23<44:52,  5.50it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   1%| | 127/14932 [00:22<44:15,  5.58it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   1%| | 127/14932 [00:22<44:15,  5.58it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -2348,8 +2313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 130/14932 [00:23<44:39,  5.53it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   1%| | 130/14932 [00:23<44:39,  5.52it/s, v_num=o30c, train/loss=1.690"
+      "Epoch 0:   1%| | 128/14932 [00:22<44:16,  5.57it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   1%| | 128/14932 [00:22<44:16,  5.57it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -2357,8 +2322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 131/14932 [00:23<44:26,  5.55it/s, v_num=o30c, train/loss=1.690\r",
-      "Epoch 0:   1%| | 131/14932 [00:23<44:27,  5.55it/s, v_num=o30c, train/loss=2.780"
+      "Epoch 0:   1%| | 129/14932 [00:23<44:03,  5.60it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   1%| | 129/14932 [00:23<44:03,  5.60it/s, v_num=ui8w, train/loss=2.420"
      ]
     },
     {
@@ -2366,8 +2331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 132/14932 [00:23<44:14,  5.58it/s, v_num=o30c, train/loss=2.780\r",
-      "Epoch 0:   1%| | 132/14932 [00:23<44:14,  5.58it/s, v_num=o30c, train/loss=1.970"
+      "Epoch 0:   1%| | 130/14932 [00:23<43:57,  5.61it/s, v_num=ui8w, train/loss=2.420\r",
+      "Epoch 0:   1%| | 130/14932 [00:23<43:57,  5.61it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -2375,8 +2340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 133/14932 [00:23<44:02,  5.60it/s, v_num=o30c, train/loss=1.970\r",
-      "Epoch 0:   1%| | 133/14932 [00:23<44:02,  5.60it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   1%| | 131/14932 [00:23<43:52,  5.62it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   1%| | 131/14932 [00:23<43:52,  5.62it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -2384,8 +2349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 134/14932 [00:23<43:50,  5.63it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   1%| | 134/14932 [00:23<43:50,  5.63it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   1%| | 132/14932 [00:23<43:39,  5.65it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   1%| | 132/14932 [00:23<43:39,  5.65it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -2393,8 +2358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 135/14932 [00:23<43:38,  5.65it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   1%| | 135/14932 [00:23<43:38,  5.65it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   1%| | 133/14932 [00:23<43:28,  5.67it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   1%| | 133/14932 [00:23<43:28,  5.67it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -2402,8 +2367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 136/14932 [00:23<43:26,  5.68it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   1%| | 136/14932 [00:23<43:27,  5.68it/s, v_num=o30c, train/loss=5.250"
+      "Epoch 0:   1%| | 134/14932 [00:23<43:16,  5.70it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   1%| | 134/14932 [00:23<43:16,  5.70it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -2411,8 +2376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 137/14932 [00:24<43:15,  5.70it/s, v_num=o30c, train/loss=5.250\r",
-      "Epoch 0:   1%| | 137/14932 [00:24<43:15,  5.70it/s, v_num=o30c, train/loss=1.550"
+      "Epoch 0:   1%| | 135/14932 [00:23<43:04,  5.73it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   1%| | 135/14932 [00:23<43:04,  5.73it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -2420,8 +2385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 138/14932 [00:24<43:05,  5.72it/s, v_num=o30c, train/loss=1.550\r",
-      "Epoch 0:   1%| | 138/14932 [00:24<43:05,  5.72it/s, v_num=o30c, train/loss=4.500"
+      "Epoch 0:   1%| | 136/14932 [00:23<42:52,  5.75it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   1%| | 136/14932 [00:23<42:52,  5.75it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -2429,8 +2394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 139/14932 [00:24<42:54,  5.75it/s, v_num=o30c, train/loss=4.500\r",
-      "Epoch 0:   1%| | 139/14932 [00:24<42:54,  5.75it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   1%| | 137/14932 [00:23<42:40,  5.78it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   1%| | 137/14932 [00:23<42:40,  5.78it/s, v_num=ui8w, train/loss=2.910"
      ]
     },
     {
@@ -2438,8 +2403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 140/14932 [00:24<42:43,  5.77it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   1%| | 140/14932 [00:24<42:43,  5.77it/s, v_num=o30c, train/loss=3.940"
+      "Epoch 0:   1%| | 138/14932 [00:23<42:29,  5.80it/s, v_num=ui8w, train/loss=2.910\r",
+      "Epoch 0:   1%| | 138/14932 [00:23<42:29,  5.80it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -2447,8 +2412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 141/14932 [00:24<42:32,  5.79it/s, v_num=o30c, train/loss=3.940\r",
-      "Epoch 0:   1%| | 141/14932 [00:24<42:32,  5.79it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   1%| | 139/14932 [00:23<42:18,  5.83it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   1%| | 139/14932 [00:23<42:18,  5.83it/s, v_num=ui8w, train/loss=3.780"
      ]
     },
     {
@@ -2456,8 +2421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 142/14932 [00:24<42:21,  5.82it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   1%| | 142/14932 [00:24<42:21,  5.82it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   1%| | 140/14932 [00:23<42:06,  5.85it/s, v_num=ui8w, train/loss=3.780\r",
+      "Epoch 0:   1%| | 140/14932 [00:23<42:06,  5.85it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -2465,8 +2430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 143/14932 [00:24<42:10,  5.84it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   1%| | 143/14932 [00:24<42:11,  5.84it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   1%| | 141/14932 [00:23<41:56,  5.88it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   1%| | 141/14932 [00:23<41:56,  5.88it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -2474,8 +2439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 144/14932 [00:24<42:00,  5.87it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   1%| | 144/14932 [00:24<42:00,  5.87it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   1%| | 142/14932 [00:24<41:46,  5.90it/s, v_num=ui8w, train/loss=3.470\r",
+      "Epoch 0:   1%| | 142/14932 [00:24<41:46,  5.90it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -2483,8 +2448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 145/14932 [00:24<41:49,  5.89it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   1%| | 145/14932 [00:24<41:49,  5.89it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   1%| | 143/14932 [00:24<41:44,  5.91it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   1%| | 143/14932 [00:24<41:44,  5.91it/s, v_num=ui8w, train/loss=2.910"
      ]
     },
     {
@@ -2492,8 +2457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 146/14932 [00:24<41:39,  5.91it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   1%| | 146/14932 [00:24<41:39,  5.91it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   1%| | 144/14932 [00:24<41:34,  5.93it/s, v_num=ui8w, train/loss=2.910\r",
+      "Epoch 0:   1%| | 144/14932 [00:24<41:34,  5.93it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -2501,8 +2466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 147/14932 [00:24<41:29,  5.94it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   1%| | 147/14932 [00:24<41:29,  5.94it/s, v_num=o30c, train/loss=3.030"
+      "Epoch 0:   1%| | 145/14932 [00:24<41:24,  5.95it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   1%| | 145/14932 [00:24<41:24,  5.95it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -2510,8 +2475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 148/14932 [00:24<41:19,  5.96it/s, v_num=o30c, train/loss=3.030\r",
-      "Epoch 0:   1%| | 148/14932 [00:24<41:19,  5.96it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   1%| | 146/14932 [00:24<41:14,  5.97it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   1%| | 146/14932 [00:24<41:14,  5.97it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -2519,8 +2484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 149/14932 [00:24<41:09,  5.99it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   1%| | 149/14932 [00:24<41:09,  5.99it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   1%| | 147/14932 [00:24<41:05,  6.00it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   1%| | 147/14932 [00:24<41:06,  6.00it/s, v_num=ui8w, train/loss=2.660"
      ]
     },
     {
@@ -2528,8 +2493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 150/14932 [00:24<40:59,  6.01it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   1%| | 150/14932 [00:24<40:59,  6.01it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   1%| | 148/14932 [00:24<40:56,  6.02it/s, v_num=ui8w, train/loss=2.660\r",
+      "Epoch 0:   1%| | 148/14932 [00:24<40:56,  6.02it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -2537,8 +2502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 151/14932 [00:25<40:50,  6.03it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   1%| | 151/14932 [00:25<40:50,  6.03it/s, v_num=o30c, train/loss=4.560"
+      "Epoch 0:   1%| | 149/14932 [00:24<40:47,  6.04it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   1%| | 149/14932 [00:24<40:47,  6.04it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -2546,8 +2511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 152/14932 [00:25<40:41,  6.05it/s, v_num=o30c, train/loss=4.560\r",
-      "Epoch 0:   1%| | 152/14932 [00:25<40:41,  6.05it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   1%| | 150/14932 [00:24<40:38,  6.06it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   1%| | 150/14932 [00:24<40:38,  6.06it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -2555,8 +2520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 153/14932 [00:25<40:31,  6.08it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   1%| | 153/14932 [00:25<40:31,  6.08it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   1%| | 151/14932 [00:24<40:29,  6.08it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   1%| | 151/14932 [00:24<40:29,  6.08it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -2564,8 +2529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 154/14932 [00:25<40:22,  6.10it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   1%| | 154/14932 [00:25<40:22,  6.10it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   1%| | 152/14932 [00:24<40:20,  6.11it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   1%| | 152/14932 [00:24<40:20,  6.11it/s, v_num=ui8w, train/loss=4.470"
      ]
     },
     {
@@ -2573,8 +2538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 155/14932 [00:25<40:18,  6.11it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   1%| | 155/14932 [00:25<40:18,  6.11it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   1%| | 153/14932 [00:24<40:11,  6.13it/s, v_num=ui8w, train/loss=4.470\r",
+      "Epoch 0:   1%| | 153/14932 [00:24<40:11,  6.13it/s, v_num=ui8w, train/loss=5.000"
      ]
     },
     {
@@ -2582,8 +2547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 156/14932 [00:25<40:09,  6.13it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   1%| | 156/14932 [00:25<40:09,  6.13it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   1%| | 154/14932 [00:25<40:03,  6.15it/s, v_num=ui8w, train/loss=5.000\r",
+      "Epoch 0:   1%| | 154/14932 [00:25<40:03,  6.15it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -2591,8 +2556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 157/14932 [00:25<40:00,  6.15it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   1%| | 157/14932 [00:25<40:00,  6.15it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   1%| | 155/14932 [00:25<39:54,  6.17it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   1%| | 155/14932 [00:25<39:54,  6.17it/s, v_num=ui8w, train/loss=2.860"
      ]
     },
     {
@@ -2600,8 +2565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 158/14932 [00:25<39:51,  6.18it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   1%| | 158/14932 [00:25<39:52,  6.18it/s, v_num=o30c, train/loss=5.220"
+      "Epoch 0:   1%| | 156/14932 [00:25<39:45,  6.20it/s, v_num=ui8w, train/loss=2.860\r",
+      "Epoch 0:   1%| | 156/14932 [00:25<39:45,  6.19it/s, v_num=ui8w, train/loss=2.190"
      ]
     },
     {
@@ -2609,8 +2574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 159/14932 [00:25<39:43,  6.20it/s, v_num=o30c, train/loss=5.220\r",
-      "Epoch 0:   1%| | 159/14932 [00:25<39:43,  6.20it/s, v_num=o30c, train/loss=2.810"
+      "Epoch 0:   1%| | 157/14932 [00:25<39:36,  6.22it/s, v_num=ui8w, train/loss=2.190\r",
+      "Epoch 0:   1%| | 157/14932 [00:25<39:36,  6.22it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -2618,8 +2583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 160/14932 [00:25<39:46,  6.19it/s, v_num=o30c, train/loss=2.810\r",
-      "Epoch 0:   1%| | 160/14932 [00:25<39:46,  6.19it/s, v_num=o30c, train/loss=4.120"
+      "Epoch 0:   1%| | 158/14932 [00:25<39:27,  6.24it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   1%| | 158/14932 [00:25<39:27,  6.24it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -2627,8 +2592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 161/14932 [00:25<39:37,  6.21it/s, v_num=o30c, train/loss=4.120\r",
-      "Epoch 0:   1%| | 161/14932 [00:25<39:37,  6.21it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   1%| | 159/14932 [00:25<39:19,  6.26it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   1%| | 159/14932 [00:25<39:19,  6.26it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -2636,7 +2601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 162/14932 [00:25<39:29,  6.23it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   1%| | 160/14932 [00:25<39:21,  6.25it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   1%| | 160/14932 [00:25<39:21,  6.25it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -2644,7 +2610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 162/14932 [00:25<39:29,  6.23it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   1%| | 161/14932 [00:25<39:13,  6.28it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   1%| | 161/14932 [00:25<39:13,  6.28it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -2652,8 +2619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 163/14932 [00:26<39:21,  6.26it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   1%| | 163/14932 [00:26<39:21,  6.25it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   1%| | 162/14932 [00:25<39:04,  6.30it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   1%| | 162/14932 [00:25<39:04,  6.30it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -2661,8 +2628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 164/14932 [00:26<40:04,  6.14it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   1%| | 164/14932 [00:26<40:04,  6.14it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   1%| | 163/14932 [00:25<38:56,  6.32it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   1%| | 163/14932 [00:25<38:56,  6.32it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -2670,8 +2637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 165/14932 [00:26<39:55,  6.16it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   1%| | 165/14932 [00:26<39:55,  6.16it/s, v_num=o30c, train/loss=4.970"
+      "Epoch 0:   1%| | 164/14932 [00:25<38:48,  6.34it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   1%| | 164/14932 [00:25<38:48,  6.34it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -2679,8 +2646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 166/14932 [00:26<39:47,  6.18it/s, v_num=o30c, train/loss=4.970\r",
-      "Epoch 0:   1%| | 166/14932 [00:26<39:47,  6.18it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   1%| | 165/14932 [00:25<38:40,  6.36it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   1%| | 165/14932 [00:25<38:40,  6.36it/s, v_num=ui8w, train/loss=2.280"
      ]
     },
     {
@@ -2688,8 +2655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 167/14932 [00:26<39:38,  6.21it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   1%| | 167/14932 [00:26<39:38,  6.21it/s, v_num=o30c, train/loss=2.770"
+      "Epoch 0:   1%| | 166/14932 [00:26<38:33,  6.38it/s, v_num=ui8w, train/loss=2.280\r",
+      "Epoch 0:   1%| | 166/14932 [00:26<38:33,  6.38it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -2697,8 +2664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 168/14932 [00:26<39:30,  6.23it/s, v_num=o30c, train/loss=2.770\r",
-      "Epoch 0:   1%| | 168/14932 [00:26<39:30,  6.23it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   1%| | 167/14932 [00:26<38:25,  6.40it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   1%| | 167/14932 [00:26<38:25,  6.40it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -2706,8 +2673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 169/14932 [00:27<39:21,  6.25it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   1%| | 169/14932 [00:27<39:21,  6.25it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   1%| | 168/14932 [00:26<38:17,  6.43it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   1%| | 168/14932 [00:26<38:17,  6.43it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -2715,7 +2682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 170/14932 [00:27<39:13,  6.27it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   1%| | 169/14932 [00:26<38:10,  6.45it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   1%| | 169/14932 [00:26<38:10,  6.45it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -2723,7 +2691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 170/14932 [00:27<39:13,  6.27it/s, v_num=o30c, train/loss=2.410"
+      "Epoch 0:   1%| | 170/14932 [00:26<38:03,  6.47it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   1%| | 170/14932 [00:26<38:03,  6.47it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -2731,8 +2700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 171/14932 [00:27<39:06,  6.29it/s, v_num=o30c, train/loss=2.410\r",
-      "Epoch 0:   1%| | 171/14932 [00:27<39:06,  6.29it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   1%| | 171/14932 [00:26<37:55,  6.49it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   1%| | 171/14932 [00:26<37:55,  6.49it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -2740,8 +2709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 172/14932 [00:27<38:58,  6.31it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   1%| | 172/14932 [00:27<38:58,  6.31it/s, v_num=o30c, train/loss=2.220"
+      "Epoch 0:   1%| | 172/14932 [00:26<37:48,  6.51it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   1%| | 172/14932 [00:26<37:48,  6.51it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -2749,8 +2718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 173/14932 [00:27<38:50,  6.33it/s, v_num=o30c, train/loss=2.220\r",
-      "Epoch 0:   1%| | 173/14932 [00:27<38:50,  6.33it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   1%| | 173/14932 [00:26<37:41,  6.53it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   1%| | 173/14932 [00:26<37:41,  6.53it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -2758,8 +2727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 174/14932 [00:27<38:43,  6.35it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   1%| | 174/14932 [00:27<38:43,  6.35it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   1%| | 174/14932 [00:26<37:34,  6.55it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   1%| | 174/14932 [00:26<37:34,  6.55it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -2767,8 +2736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 175/14932 [00:27<38:36,  6.37it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   1%| | 175/14932 [00:27<38:36,  6.37it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   1%| | 175/14932 [00:26<37:27,  6.57it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   1%| | 175/14932 [00:26<37:27,  6.57it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -2776,8 +2745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 176/14932 [00:27<38:29,  6.39it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   1%| | 176/14932 [00:27<38:29,  6.39it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   1%| | 176/14932 [00:26<37:20,  6.59it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   1%| | 176/14932 [00:26<37:20,  6.59it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -2785,8 +2754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 177/14932 [00:27<38:22,  6.41it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   1%| | 177/14932 [00:27<38:22,  6.41it/s, v_num=o30c, train/loss=1.950"
+      "Epoch 0:   1%| | 177/14932 [00:26<37:13,  6.61it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   1%| | 177/14932 [00:26<37:13,  6.61it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -2794,8 +2763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 178/14932 [00:27<38:15,  6.43it/s, v_num=o30c, train/loss=1.950\r",
-      "Epoch 0:   1%| | 178/14932 [00:27<38:15,  6.43it/s, v_num=o30c, train/loss=2.360"
+      "Epoch 0:   1%| | 178/14932 [00:26<37:07,  6.62it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   1%| | 178/14932 [00:26<37:07,  6.62it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -2803,8 +2772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 179/14932 [00:27<38:08,  6.45it/s, v_num=o30c, train/loss=2.360\r",
-      "Epoch 0:   1%| | 179/14932 [00:27<38:08,  6.45it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   1%| | 179/14932 [00:26<37:00,  6.64it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   1%| | 179/14932 [00:26<37:00,  6.64it/s, v_num=ui8w, train/loss=3.390"
      ]
     },
     {
@@ -2812,8 +2781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 180/14932 [00:27<38:01,  6.46it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   1%| | 180/14932 [00:27<38:01,  6.46it/s, v_num=o30c, train/loss=1.340"
+      "Epoch 0:   1%| | 180/14932 [00:27<38:02,  6.46it/s, v_num=ui8w, train/loss=3.390\r",
+      "Epoch 0:   1%| | 180/14932 [00:27<38:02,  6.46it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -2821,7 +2790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 181/14932 [00:27<37:55,  6.48it/s, v_num=o30c, train/loss=1.340"
+      "Epoch 0:   1%| | 181/14932 [00:27<37:55,  6.48it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   1%| | 181/14932 [00:27<37:55,  6.48it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -2829,7 +2799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 181/14932 [00:27<37:55,  6.48it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   1%| | 182/14932 [00:27<37:48,  6.50it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   1%| | 182/14932 [00:27<37:48,  6.50it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -2837,8 +2808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 182/14932 [00:27<37:48,  6.50it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   1%| | 182/14932 [00:27<37:48,  6.50it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   1%| | 183/14932 [00:28<37:42,  6.52it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   1%| | 183/14932 [00:28<37:42,  6.52it/s, v_num=ui8w, train/loss=2.050"
      ]
     },
     {
@@ -2846,8 +2817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 183/14932 [00:28<37:41,  6.52it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   1%| | 183/14932 [00:28<37:41,  6.52it/s, v_num=o30c, train/loss=4.500"
+      "Epoch 0:   1%| | 184/14932 [00:28<37:35,  6.54it/s, v_num=ui8w, train/loss=2.050\r",
+      "Epoch 0:   1%| | 184/14932 [00:28<37:35,  6.54it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -2855,8 +2826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 184/14932 [00:28<37:35,  6.54it/s, v_num=o30c, train/loss=4.500\r",
-      "Epoch 0:   1%| | 184/14932 [00:28<37:35,  6.54it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   1%| | 185/14932 [00:28<37:29,  6.56it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   1%| | 185/14932 [00:28<37:29,  6.56it/s, v_num=ui8w, train/loss=3.080"
      ]
     },
     {
@@ -2864,8 +2835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 185/14932 [00:28<37:28,  6.56it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   1%| | 185/14932 [00:28<37:28,  6.56it/s, v_num=o30c, train/loss=2.450"
+      "Epoch 0:   1%| | 186/14932 [00:28<37:22,  6.57it/s, v_num=ui8w, train/loss=3.080\r",
+      "Epoch 0:   1%| | 186/14932 [00:28<37:22,  6.57it/s, v_num=ui8w, train/loss=3.300"
      ]
     },
     {
@@ -2873,8 +2844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 186/14932 [00:28<37:22,  6.58it/s, v_num=o30c, train/loss=2.450\r",
-      "Epoch 0:   1%| | 186/14932 [00:28<37:22,  6.58it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   1%| | 187/14932 [00:28<37:16,  6.59it/s, v_num=ui8w, train/loss=3.300\r",
+      "Epoch 0:   1%| | 187/14932 [00:28<37:17,  6.59it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -2882,8 +2853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 187/14932 [00:28<37:16,  6.59it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   1%| | 187/14932 [00:28<37:16,  6.59it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   1%| | 188/14932 [00:28<37:10,  6.61it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   1%| | 188/14932 [00:28<37:10,  6.61it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -2891,8 +2862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 188/14932 [00:28<37:09,  6.61it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   1%| | 188/14932 [00:28<37:09,  6.61it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   1%| | 189/14932 [00:28<37:04,  6.63it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   1%| | 189/14932 [00:28<37:04,  6.63it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -2900,8 +2871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 189/14932 [00:28<37:03,  6.63it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   1%| | 189/14932 [00:28<37:03,  6.63it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   1%| | 190/14932 [00:28<36:58,  6.64it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   1%| | 190/14932 [00:28<36:58,  6.64it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -2909,8 +2880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 190/14932 [00:28<36:58,  6.64it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   1%| | 190/14932 [00:28<36:58,  6.64it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   1%| | 191/14932 [00:28<36:52,  6.66it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   1%| | 191/14932 [00:28<36:52,  6.66it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -2918,8 +2889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 191/14932 [00:28<36:52,  6.66it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   1%| | 191/14932 [00:28<36:52,  6.66it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   1%| | 192/14932 [00:28<36:55,  6.65it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   1%| | 192/14932 [00:28<36:55,  6.65it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -2927,8 +2898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 192/14932 [00:28<36:55,  6.65it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   1%| | 192/14932 [00:28<36:55,  6.65it/s, v_num=o30c, train/loss=2.880"
+      "Epoch 0:   1%| | 193/14932 [00:28<36:48,  6.67it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   1%| | 193/14932 [00:28<36:48,  6.67it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -2936,8 +2907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 193/14932 [00:28<36:49,  6.67it/s, v_num=o30c, train/loss=2.880\r",
-      "Epoch 0:   1%| | 193/14932 [00:28<36:49,  6.67it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   1%| | 194/14932 [00:29<36:43,  6.69it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   1%| | 194/14932 [00:29<36:43,  6.69it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -2945,8 +2916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 194/14932 [00:29<36:43,  6.69it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   1%| | 194/14932 [00:29<36:43,  6.69it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   1%| | 195/14932 [00:29<36:37,  6.71it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   1%| | 195/14932 [00:29<36:37,  6.71it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -2954,8 +2925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 195/14932 [00:29<36:37,  6.71it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   1%| | 195/14932 [00:29<36:37,  6.71it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   1%| | 196/14932 [00:29<36:31,  6.72it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   1%| | 196/14932 [00:29<36:31,  6.72it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -2963,8 +2934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 196/14932 [00:29<36:36,  6.71it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   1%| | 196/14932 [00:29<36:36,  6.71it/s, v_num=o30c, train/loss=3.840"
+      "Epoch 0:   1%| | 197/14932 [00:29<36:30,  6.73it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   1%| | 197/14932 [00:29<36:30,  6.73it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -2972,8 +2943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 197/14932 [00:29<36:30,  6.73it/s, v_num=o30c, train/loss=3.840\r",
-      "Epoch 0:   1%| | 197/14932 [00:29<36:30,  6.73it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   1%| | 198/14932 [00:29<36:24,  6.75it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   1%| | 198/14932 [00:29<36:24,  6.75it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -2981,8 +2952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 198/14932 [00:29<36:24,  6.74it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   1%| | 198/14932 [00:29<36:24,  6.74it/s, v_num=o30c, train/loss=1.560"
+      "Epoch 0:   1%| | 199/14932 [00:29<36:18,  6.76it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   1%| | 199/14932 [00:29<36:18,  6.76it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -2990,8 +2961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 199/14932 [00:29<36:19,  6.76it/s, v_num=o30c, train/loss=1.560\r",
-      "Epoch 0:   1%| | 199/14932 [00:29<36:19,  6.76it/s, v_num=o30c, train/loss=3.800"
+      "Epoch 0:   1%| | 200/14932 [00:29<36:13,  6.78it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   1%| | 200/14932 [00:29<36:13,  6.78it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -2999,8 +2970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 200/14932 [00:29<36:13,  6.78it/s, v_num=o30c, train/loss=3.800\r",
-      "Epoch 0:   1%| | 200/14932 [00:29<36:13,  6.78it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   1%| | 201/14932 [00:29<36:07,  6.80it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   1%| | 201/14932 [00:29<36:07,  6.80it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -3008,8 +2979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 201/14932 [00:29<36:07,  6.80it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   1%| | 201/14932 [00:29<36:07,  6.80it/s, v_num=o30c, train/loss=2.660"
+      "Epoch 0:   1%| | 202/14932 [00:29<36:02,  6.81it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   1%| | 202/14932 [00:29<36:02,  6.81it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -3017,8 +2988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 202/14932 [00:29<36:02,  6.81it/s, v_num=o30c, train/loss=2.660\r",
-      "Epoch 0:   1%| | 202/14932 [00:29<36:02,  6.81it/s, v_num=o30c, train/loss=4.720"
+      "Epoch 0:   1%| | 203/14932 [00:29<36:01,  6.82it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   1%| | 203/14932 [00:29<36:01,  6.82it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -3026,8 +2997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 203/14932 [00:29<35:56,  6.83it/s, v_num=o30c, train/loss=4.720\r",
-      "Epoch 0:   1%| | 203/14932 [00:29<35:56,  6.83it/s, v_num=o30c, train/loss=4.780"
+      "Epoch 0:   1%| | 204/14932 [00:29<35:59,  6.82it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   1%| | 204/14932 [00:29<35:59,  6.82it/s, v_num=ui8w, train/loss=3.780"
      ]
     },
     {
@@ -3035,8 +3006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 204/14932 [00:29<35:52,  6.84it/s, v_num=o30c, train/loss=4.780\r",
-      "Epoch 0:   1%| | 204/14932 [00:29<35:52,  6.84it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   1%| | 205/14932 [00:30<35:58,  6.82it/s, v_num=ui8w, train/loss=3.780\r",
+      "Epoch 0:   1%| | 205/14932 [00:30<35:58,  6.82it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -3044,8 +3015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 205/14932 [00:29<35:46,  6.86it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   1%| | 205/14932 [00:29<35:46,  6.86it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   1%| | 206/14932 [00:30<35:53,  6.84it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   1%| | 206/14932 [00:30<35:53,  6.84it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -3053,8 +3024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 206/14932 [00:29<35:41,  6.88it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   1%| | 206/14932 [00:29<35:41,  6.88it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   1%| | 207/14932 [00:30<35:48,  6.85it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   1%| | 207/14932 [00:30<35:48,  6.85it/s, v_num=ui8w, train/loss=2.280"
      ]
     },
     {
@@ -3062,8 +3033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 207/14932 [00:30<35:36,  6.89it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   1%| | 207/14932 [00:30<35:36,  6.89it/s, v_num=o30c, train/loss=3.200"
+      "Epoch 0:   1%| | 208/14932 [00:30<35:42,  6.87it/s, v_num=ui8w, train/loss=2.280\r",
+      "Epoch 0:   1%| | 208/14932 [00:30<35:42,  6.87it/s, v_num=ui8w, train/loss=1.800"
      ]
     },
     {
@@ -3071,8 +3042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 208/14932 [00:30<35:30,  6.91it/s, v_num=o30c, train/loss=3.200\r",
-      "Epoch 0:   1%| | 208/14932 [00:30<35:30,  6.91it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   1%| | 209/14932 [00:30<35:37,  6.89it/s, v_num=ui8w, train/loss=1.800\r",
+      "Epoch 0:   1%| | 209/14932 [00:30<35:37,  6.89it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -3080,8 +3051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 209/14932 [00:30<35:25,  6.93it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   1%| | 209/14932 [00:30<35:25,  6.93it/s, v_num=o30c, train/loss=2.810"
+      "Epoch 0:   1%| | 210/14932 [00:30<35:32,  6.90it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   1%| | 210/14932 [00:30<35:32,  6.90it/s, v_num=ui8w, train/loss=4.530"
      ]
     },
     {
@@ -3089,8 +3060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 210/14932 [00:30<35:20,  6.94it/s, v_num=o30c, train/loss=2.810\r",
-      "Epoch 0:   1%| | 210/14932 [00:30<35:20,  6.94it/s, v_num=o30c, train/loss=4.380"
+      "Epoch 0:   1%| | 211/14932 [00:30<35:27,  6.92it/s, v_num=ui8w, train/loss=4.530\r",
+      "Epoch 0:   1%| | 211/14932 [00:30<35:27,  6.92it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -3098,8 +3069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 211/14932 [00:30<35:15,  6.96it/s, v_num=o30c, train/loss=4.380\r",
-      "Epoch 0:   1%| | 211/14932 [00:30<35:15,  6.96it/s, v_num=o30c, train/loss=1.910"
+      "Epoch 0:   1%| | 212/14932 [00:30<35:22,  6.94it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   1%| | 212/14932 [00:30<35:22,  6.94it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -3107,8 +3078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 212/14932 [00:30<35:10,  6.97it/s, v_num=o30c, train/loss=1.910\r",
-      "Epoch 0:   1%| | 212/14932 [00:30<35:10,  6.97it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   1%| | 213/14932 [00:30<35:17,  6.95it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   1%| | 213/14932 [00:30<35:17,  6.95it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -3116,8 +3087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 213/14932 [00:30<35:05,  6.99it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   1%| | 213/14932 [00:30<35:05,  6.99it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   1%| | 214/14932 [00:30<35:12,  6.97it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   1%| | 214/14932 [00:30<35:12,  6.97it/s, v_num=ui8w, train/loss=5.090"
      ]
     },
     {
@@ -3125,8 +3096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 214/14932 [00:30<35:00,  7.01it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   1%| | 214/14932 [00:30<35:00,  7.01it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   1%| | 215/14932 [00:30<35:07,  6.98it/s, v_num=ui8w, train/loss=5.090\r",
+      "Epoch 0:   1%| | 215/14932 [00:30<35:07,  6.98it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -3134,8 +3105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 215/14932 [00:30<34:55,  7.02it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   1%| | 215/14932 [00:30<34:55,  7.02it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   1%| | 216/14932 [00:30<35:02,  7.00it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   1%| | 216/14932 [00:30<35:02,  7.00it/s, v_num=ui8w, train/loss=2.380"
      ]
     },
     {
@@ -3143,8 +3114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 216/14932 [00:30<34:50,  7.04it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   1%| | 216/14932 [00:30<34:50,  7.04it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   1%| | 217/14932 [00:30<34:57,  7.02it/s, v_num=ui8w, train/loss=2.380\r",
+      "Epoch 0:   1%| | 217/14932 [00:30<34:57,  7.02it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -3152,8 +3123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 217/14932 [00:30<34:45,  7.06it/s, v_num=o30c, train/loss=2.380\r",
-      "Epoch 0:   1%| | 217/14932 [00:30<34:45,  7.06it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   1%| | 218/14932 [00:31<34:52,  7.03it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   1%| | 218/14932 [00:31<34:52,  7.03it/s, v_num=ui8w, train/loss=2.750"
      ]
     },
     {
@@ -3161,8 +3132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 218/14932 [00:30<34:40,  7.07it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   1%| | 218/14932 [00:30<34:40,  7.07it/s, v_num=o30c, train/loss=2.890"
+      "Epoch 0:   1%| | 219/14932 [00:31<34:47,  7.05it/s, v_num=ui8w, train/loss=2.750\r",
+      "Epoch 0:   1%| | 219/14932 [00:31<34:47,  7.05it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -3170,8 +3141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 219/14932 [00:30<34:40,  7.07it/s, v_num=o30c, train/loss=2.890\r",
-      "Epoch 0:   1%| | 219/14932 [00:30<34:40,  7.07it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   1%| | 220/14932 [00:31<34:42,  7.06it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   1%| | 220/14932 [00:31<34:42,  7.06it/s, v_num=ui8w, train/loss=4.500"
      ]
     },
     {
@@ -3179,8 +3150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 220/14932 [00:31<34:34,  7.09it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   1%| | 220/14932 [00:31<34:34,  7.09it/s, v_num=o30c, train/loss=3.980"
+      "Epoch 0:   1%| | 221/14932 [00:31<34:38,  7.08it/s, v_num=ui8w, train/loss=4.500\r",
+      "Epoch 0:   1%| | 221/14932 [00:31<34:38,  7.08it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -3188,8 +3159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 221/14932 [00:31<34:30,  7.11it/s, v_num=o30c, train/loss=3.980\r",
-      "Epoch 0:   1%| | 221/14932 [00:31<34:30,  7.11it/s, v_num=o30c, train/loss=1.910"
+      "Epoch 0:   1%| | 222/14932 [00:31<34:33,  7.09it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   1%| | 222/14932 [00:31<34:33,  7.09it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -3197,8 +3168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 222/14932 [00:31<34:25,  7.12it/s, v_num=o30c, train/loss=1.910\r",
-      "Epoch 0:   1%| | 222/14932 [00:31<34:25,  7.12it/s, v_num=o30c, train/loss=4.380"
+      "Epoch 0:   1%| | 223/14932 [00:31<34:28,  7.11it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   1%| | 223/14932 [00:31<34:28,  7.11it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -3206,8 +3177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   1%| | 223/14932 [00:31<34:21,  7.13it/s, v_num=o30c, train/loss=4.380\r",
-      "Epoch 0:   1%| | 223/14932 [00:31<34:21,  7.13it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   2%| | 224/14932 [00:31<34:31,  7.10it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   2%| | 224/14932 [00:31<34:31,  7.10it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -3215,8 +3186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 224/14932 [00:31<34:24,  7.12it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   2%| | 224/14932 [00:31<34:24,  7.12it/s, v_num=o30c, train/loss=2.890"
+      "Epoch 0:   2%| | 225/14932 [00:31<34:26,  7.12it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   2%| | 225/14932 [00:31<34:26,  7.12it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -3224,8 +3195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 225/14932 [00:31<34:19,  7.14it/s, v_num=o30c, train/loss=2.890\r",
-      "Epoch 0:   2%| | 225/14932 [00:31<34:19,  7.14it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   2%| | 226/14932 [00:31<34:21,  7.13it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   2%| | 226/14932 [00:31<34:21,  7.13it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -3233,8 +3204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 226/14932 [00:31<34:15,  7.16it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   2%| | 226/14932 [00:31<34:15,  7.16it/s, v_num=o30c, train/loss=2.700"
+      "Epoch 0:   2%| | 227/14932 [00:31<34:17,  7.15it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   2%| | 227/14932 [00:31<34:17,  7.15it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -3242,8 +3213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 227/14932 [00:31<34:10,  7.17it/s, v_num=o30c, train/loss=2.700\r",
-      "Epoch 0:   2%| | 227/14932 [00:31<34:10,  7.17it/s, v_num=o30c, train/loss=1.350"
+      "Epoch 0:   2%| | 228/14932 [00:31<34:12,  7.16it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   2%| | 228/14932 [00:31<34:12,  7.16it/s, v_num=ui8w, train/loss=4.810"
      ]
     },
     {
@@ -3251,8 +3222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 228/14932 [00:31<34:06,  7.19it/s, v_num=o30c, train/loss=1.350\r",
-      "Epoch 0:   2%| | 228/14932 [00:31<34:06,  7.19it/s, v_num=o30c, train/loss=1.530"
+      "Epoch 0:   2%| | 229/14932 [00:31<34:07,  7.18it/s, v_num=ui8w, train/loss=4.810\r",
+      "Epoch 0:   2%| | 229/14932 [00:31<34:07,  7.18it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -3260,8 +3231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 229/14932 [00:31<34:01,  7.20it/s, v_num=o30c, train/loss=1.530\r",
-      "Epoch 0:   2%| | 229/14932 [00:31<34:01,  7.20it/s, v_num=o30c, train/loss=2.470"
+      "Epoch 0:   2%| | 230/14932 [00:31<34:03,  7.20it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   2%| | 230/14932 [00:31<34:03,  7.20it/s, v_num=ui8w, train/loss=3.250"
      ]
     },
     {
@@ -3269,8 +3240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 230/14932 [00:31<33:57,  7.22it/s, v_num=o30c, train/loss=2.470\r",
-      "Epoch 0:   2%| | 230/14932 [00:31<33:57,  7.22it/s, v_num=o30c, train/loss=2.280"
+      "Epoch 0:   2%| | 231/14932 [00:32<33:58,  7.21it/s, v_num=ui8w, train/loss=3.250\r",
+      "Epoch 0:   2%| | 231/14932 [00:32<33:59,  7.21it/s, v_num=ui8w, train/loss=2.060"
      ]
     },
     {
@@ -3278,8 +3249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 231/14932 [00:31<33:52,  7.23it/s, v_num=o30c, train/loss=2.280\r",
-      "Epoch 0:   2%| | 231/14932 [00:31<33:52,  7.23it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   2%| | 232/14932 [00:32<34:28,  7.11it/s, v_num=ui8w, train/loss=2.060\r",
+      "Epoch 0:   2%| | 232/14932 [00:32<34:28,  7.11it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -3287,8 +3258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 232/14932 [00:32<33:48,  7.25it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   2%| | 232/14932 [00:32<33:48,  7.25it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   2%| | 233/14932 [00:32<34:23,  7.12it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   2%| | 233/14932 [00:32<34:23,  7.12it/s, v_num=ui8w, train/loss=2.110"
      ]
     },
     {
@@ -3296,8 +3267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 233/14932 [00:32<33:44,  7.26it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   2%| | 233/14932 [00:32<33:44,  7.26it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   2%| | 234/14932 [00:32<34:18,  7.14it/s, v_num=ui8w, train/loss=2.110\r",
+      "Epoch 0:   2%| | 234/14932 [00:32<34:18,  7.14it/s, v_num=ui8w, train/loss=5.060"
      ]
     },
     {
@@ -3305,8 +3276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 234/14932 [00:32<33:40,  7.28it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   2%| | 234/14932 [00:32<33:40,  7.28it/s, v_num=o30c, train/loss=2.220"
+      "Epoch 0:   2%| | 235/14932 [00:32<34:13,  7.16it/s, v_num=ui8w, train/loss=5.060\r",
+      "Epoch 0:   2%| | 235/14932 [00:32<34:13,  7.16it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -3314,8 +3285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 235/14932 [00:32<33:35,  7.29it/s, v_num=o30c, train/loss=2.220\r",
-      "Epoch 0:   2%| | 235/14932 [00:32<33:36,  7.29it/s, v_num=o30c, train/loss=2.340"
+      "Epoch 0:   2%| | 236/14932 [00:32<34:09,  7.17it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   2%| | 236/14932 [00:32<34:09,  7.17it/s, v_num=ui8w, train/loss=2.780"
      ]
     },
     {
@@ -3323,8 +3294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 236/14932 [00:32<33:32,  7.30it/s, v_num=o30c, train/loss=2.340\r",
-      "Epoch 0:   2%| | 236/14932 [00:32<33:32,  7.30it/s, v_num=o30c, train/loss=4.410"
+      "Epoch 0:   2%| | 237/14932 [00:32<34:04,  7.19it/s, v_num=ui8w, train/loss=2.780\r",
+      "Epoch 0:   2%| | 237/14932 [00:32<34:04,  7.19it/s, v_num=ui8w, train/loss=3.230"
      ]
     },
     {
@@ -3332,8 +3303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 237/14932 [00:32<33:28,  7.32it/s, v_num=o30c, train/loss=4.410\r",
-      "Epoch 0:   2%| | 237/14932 [00:32<33:28,  7.32it/s, v_num=o30c, train/loss=3.500"
+      "Epoch 0:   2%| | 238/14932 [00:33<34:12,  7.16it/s, v_num=ui8w, train/loss=3.230\r",
+      "Epoch 0:   2%| | 238/14932 [00:33<34:12,  7.16it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -3341,8 +3312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 238/14932 [00:32<33:24,  7.33it/s, v_num=o30c, train/loss=3.500\r",
-      "Epoch 0:   2%| | 238/14932 [00:32<33:24,  7.33it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   2%| | 239/14932 [00:33<34:08,  7.17it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   2%| | 239/14932 [00:33<34:08,  7.17it/s, v_num=ui8w, train/loss=3.770"
      ]
     },
     {
@@ -3350,8 +3321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 239/14932 [00:32<33:19,  7.35it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   2%| | 239/14932 [00:32<33:19,  7.35it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   2%| | 240/14932 [00:33<34:03,  7.19it/s, v_num=ui8w, train/loss=3.770\r",
+      "Epoch 0:   2%| | 240/14932 [00:33<34:03,  7.19it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -3359,8 +3330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 240/14932 [00:32<33:16,  7.36it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   2%| | 240/14932 [00:32<33:16,  7.36it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   2%| | 241/14932 [00:33<33:59,  7.20it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   2%| | 241/14932 [00:33<33:59,  7.20it/s, v_num=ui8w, train/loss=2.440"
      ]
     },
     {
@@ -3368,8 +3339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 241/14932 [00:32<33:11,  7.38it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   2%| | 241/14932 [00:32<33:12,  7.37it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   2%| | 242/14932 [00:33<33:54,  7.22it/s, v_num=ui8w, train/loss=2.440\r",
+      "Epoch 0:   2%| | 242/14932 [00:33<33:54,  7.22it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -3377,8 +3348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 242/14932 [00:32<33:08,  7.39it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   2%| | 242/14932 [00:32<33:08,  7.39it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   2%| | 243/14932 [00:33<33:50,  7.23it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   2%| | 243/14932 [00:33<33:50,  7.23it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -3386,8 +3357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 243/14932 [00:32<33:04,  7.40it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   2%| | 243/14932 [00:32<33:04,  7.40it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   2%| | 244/14932 [00:33<33:49,  7.24it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   2%| | 244/14932 [00:33<33:49,  7.24it/s, v_num=ui8w, train/loss=2.950"
      ]
     },
     {
@@ -3395,8 +3366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 244/14932 [00:32<33:04,  7.40it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   2%| | 244/14932 [00:32<33:04,  7.40it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   2%| | 245/14932 [00:33<33:45,  7.25it/s, v_num=ui8w, train/loss=2.950\r",
+      "Epoch 0:   2%| | 245/14932 [00:33<33:45,  7.25it/s, v_num=ui8w, train/loss=4.620"
      ]
     },
     {
@@ -3404,8 +3375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 245/14932 [00:33<33:00,  7.42it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   2%| | 245/14932 [00:33<33:00,  7.42it/s, v_num=o30c, train/loss=3.910"
+      "Epoch 0:   2%| | 246/14932 [00:33<33:41,  7.27it/s, v_num=ui8w, train/loss=4.620\r",
+      "Epoch 0:   2%| | 246/14932 [00:33<33:41,  7.27it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -3413,8 +3384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 246/14932 [00:33<32:56,  7.43it/s, v_num=o30c, train/loss=3.910\r",
-      "Epoch 0:   2%| | 246/14932 [00:33<32:56,  7.43it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   2%| | 247/14932 [00:33<33:36,  7.28it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   2%| | 247/14932 [00:33<33:36,  7.28it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -3422,8 +3393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 247/14932 [00:33<32:52,  7.44it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   2%| | 247/14932 [00:33<32:52,  7.44it/s, v_num=o30c, train/loss=2.580"
+      "Epoch 0:   2%| | 248/14932 [00:33<33:32,  7.29it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   2%| | 248/14932 [00:33<33:32,  7.29it/s, v_num=ui8w, train/loss=2.770"
      ]
     },
     {
@@ -3431,8 +3402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 248/14932 [00:33<32:48,  7.46it/s, v_num=o30c, train/loss=2.580\r",
-      "Epoch 0:   2%| | 248/14932 [00:33<32:48,  7.46it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   2%| | 249/14932 [00:34<33:28,  7.31it/s, v_num=ui8w, train/loss=2.770\r",
+      "Epoch 0:   2%| | 249/14932 [00:34<33:28,  7.31it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -3440,8 +3411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 249/14932 [00:33<32:44,  7.47it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   2%| | 249/14932 [00:33<32:44,  7.47it/s, v_num=o30c, train/loss=2.060"
+      "Epoch 0:   2%| | 250/14932 [00:34<33:24,  7.33it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   2%| | 250/14932 [00:34<33:24,  7.33it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -3449,8 +3420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 250/14932 [00:33<32:40,  7.49it/s, v_num=o30c, train/loss=2.060\r",
-      "Epoch 0:   2%| | 250/14932 [00:33<32:40,  7.49it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   2%| | 251/14932 [00:34<33:20,  7.34it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   2%| | 251/14932 [00:34<33:20,  7.34it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -3458,8 +3429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 251/14932 [00:33<32:36,  7.50it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   2%| | 251/14932 [00:33<32:36,  7.50it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   2%| | 252/14932 [00:34<33:15,  7.36it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   2%| | 252/14932 [00:34<33:15,  7.36it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -3467,8 +3438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 252/14932 [00:33<32:32,  7.52it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   2%| | 252/14932 [00:33<32:32,  7.52it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   2%| | 253/14932 [00:34<33:11,  7.37it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   2%| | 253/14932 [00:34<33:11,  7.37it/s, v_num=ui8w, train/loss=2.340"
      ]
     },
     {
@@ -3476,8 +3447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 253/14932 [00:33<32:28,  7.53it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   2%| | 253/14932 [00:33<32:28,  7.53it/s, v_num=o30c, train/loss=3.800"
+      "Epoch 0:   2%| | 254/14932 [00:34<33:07,  7.38it/s, v_num=ui8w, train/loss=2.340\r",
+      "Epoch 0:   2%| | 254/14932 [00:34<33:07,  7.38it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -3485,8 +3456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 254/14932 [00:33<32:25,  7.55it/s, v_num=o30c, train/loss=3.800\r",
-      "Epoch 0:   2%| | 254/14932 [00:33<32:25,  7.55it/s, v_num=o30c, train/loss=2.330"
+      "Epoch 0:   2%| | 255/14932 [00:34<33:03,  7.40it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 255/14932 [00:34<33:03,  7.40it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -3494,8 +3465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 255/14932 [00:33<32:22,  7.56it/s, v_num=o30c, train/loss=2.330\r",
-      "Epoch 0:   2%| | 255/14932 [00:33<32:22,  7.56it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   2%| | 256/14932 [00:34<33:06,  7.39it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   2%| | 256/14932 [00:34<33:06,  7.39it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -3503,7 +3474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 256/14932 [00:33<32:25,  7.54it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   2%| | 257/14932 [00:34<33:02,  7.40it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   2%| | 257/14932 [00:34<33:02,  7.40it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -3511,7 +3483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 256/14932 [00:33<32:25,  7.54it/s, v_num=o30c, train/loss=3.720"
+      "Epoch 0:   2%| | 258/14932 [00:34<32:58,  7.42it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   2%| | 258/14932 [00:34<32:58,  7.42it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -3519,8 +3492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 257/14932 [00:34<32:22,  7.56it/s, v_num=o30c, train/loss=3.720\r",
-      "Epoch 0:   2%| | 257/14932 [00:34<32:22,  7.56it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   2%| | 259/14932 [00:34<32:54,  7.43it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 259/14932 [00:34<32:54,  7.43it/s, v_num=ui8w, train/loss=2.360"
      ]
     },
     {
@@ -3528,8 +3501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 258/14932 [00:34<32:18,  7.57it/s, v_num=o30c, train/loss=2.380\r",
-      "Epoch 0:   2%| | 258/14932 [00:34<32:18,  7.57it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   2%| | 260/14932 [00:34<32:51,  7.44it/s, v_num=ui8w, train/loss=2.360\r",
+      "Epoch 0:   2%| | 260/14932 [00:34<32:51,  7.44it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -3537,8 +3510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 259/14932 [00:34<32:14,  7.58it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   2%| | 259/14932 [00:34<32:14,  7.58it/s, v_num=o30c, train/loss=1.600"
+      "Epoch 0:   2%| | 261/14932 [00:34<32:47,  7.46it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   2%| | 261/14932 [00:34<32:47,  7.46it/s, v_num=ui8w, train/loss=3.890"
      ]
     },
     {
@@ -3546,8 +3519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 260/14932 [00:34<32:11,  7.60it/s, v_num=o30c, train/loss=1.600\r",
-      "Epoch 0:   2%| | 260/14932 [00:34<32:11,  7.60it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   2%| | 262/14932 [00:35<32:43,  7.47it/s, v_num=ui8w, train/loss=3.890\r",
+      "Epoch 0:   2%| | 262/14932 [00:35<32:43,  7.47it/s, v_num=ui8w, train/loss=4.620"
      ]
     },
     {
@@ -3555,8 +3528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 261/14932 [00:34<32:07,  7.61it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   2%| | 261/14932 [00:34<32:07,  7.61it/s, v_num=o30c, train/loss=2.000"
+      "Epoch 0:   2%| | 263/14932 [00:35<32:40,  7.48it/s, v_num=ui8w, train/loss=4.620\r",
+      "Epoch 0:   2%| | 263/14932 [00:35<32:40,  7.48it/s, v_num=ui8w, train/loss=2.450"
      ]
     },
     {
@@ -3564,8 +3537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 262/14932 [00:34<32:04,  7.62it/s, v_num=o30c, train/loss=2.000\r",
-      "Epoch 0:   2%| | 262/14932 [00:34<32:04,  7.62it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   2%| | 264/14932 [00:35<32:36,  7.50it/s, v_num=ui8w, train/loss=2.450\r",
+      "Epoch 0:   2%| | 264/14932 [00:35<32:36,  7.50it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -3573,8 +3546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 263/14932 [00:34<32:01,  7.64it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   2%| | 263/14932 [00:34<32:01,  7.64it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   2%| | 265/14932 [00:35<32:33,  7.51it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   2%| | 265/14932 [00:35<32:33,  7.51it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -3582,8 +3555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 264/14932 [00:34<31:58,  7.65it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   2%| | 264/14932 [00:34<31:58,  7.65it/s, v_num=o30c, train/loss=2.410"
+      "Epoch 0:   2%| | 266/14932 [00:35<32:29,  7.52it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   2%| | 266/14932 [00:35<32:29,  7.52it/s, v_num=ui8w, train/loss=2.620"
      ]
     },
     {
@@ -3591,8 +3564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 265/14932 [00:34<31:54,  7.66it/s, v_num=o30c, train/loss=2.410\r",
-      "Epoch 0:   2%| | 265/14932 [00:34<31:54,  7.66it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   2%| | 267/14932 [00:35<32:25,  7.54it/s, v_num=ui8w, train/loss=2.620\r",
+      "Epoch 0:   2%| | 267/14932 [00:35<32:25,  7.54it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -3600,8 +3573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 266/14932 [00:34<31:51,  7.67it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   2%| | 266/14932 [00:34<31:51,  7.67it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   2%| | 268/14932 [00:35<32:29,  7.52it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   2%| | 268/14932 [00:35<32:29,  7.52it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -3609,8 +3582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 267/14932 [00:34<31:51,  7.67it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   2%| | 267/14932 [00:34<31:51,  7.67it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   2%| | 269/14932 [00:35<32:25,  7.54it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   2%| | 269/14932 [00:35<32:25,  7.54it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -3618,8 +3591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 268/14932 [00:34<31:47,  7.69it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   2%| | 268/14932 [00:34<31:47,  7.69it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   2%| | 270/14932 [00:35<32:21,  7.55it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   2%| | 270/14932 [00:35<32:21,  7.55it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -3627,8 +3600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 269/14932 [00:34<31:44,  7.70it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   2%| | 269/14932 [00:34<31:44,  7.70it/s, v_num=o30c, train/loss=3.280"
+      "Epoch 0:   2%| | 271/14932 [00:35<32:18,  7.56it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   2%| | 271/14932 [00:35<32:18,  7.56it/s, v_num=ui8w, train/loss=2.700"
      ]
     },
     {
@@ -3636,8 +3609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 270/14932 [00:35<31:41,  7.71it/s, v_num=o30c, train/loss=3.280\r",
-      "Epoch 0:   2%| | 270/14932 [00:35<31:41,  7.71it/s, v_num=o30c, train/loss=3.090"
+      "Epoch 0:   2%| | 272/14932 [00:35<32:18,  7.56it/s, v_num=ui8w, train/loss=2.700\r",
+      "Epoch 0:   2%| | 272/14932 [00:35<32:18,  7.56it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -3645,8 +3618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 271/14932 [00:35<31:38,  7.72it/s, v_num=o30c, train/loss=3.090\r",
-      "Epoch 0:   2%| | 271/14932 [00:35<31:38,  7.72it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   2%| | 273/14932 [00:36<32:14,  7.58it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   2%| | 273/14932 [00:36<32:14,  7.58it/s, v_num=ui8w, train/loss=2.440"
      ]
     },
     {
@@ -3654,8 +3627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 272/14932 [00:35<31:35,  7.73it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   2%| | 272/14932 [00:35<31:35,  7.73it/s, v_num=o30c, train/loss=3.840"
+      "Epoch 0:   2%| | 274/14932 [00:36<32:11,  7.59it/s, v_num=ui8w, train/loss=2.440\r",
+      "Epoch 0:   2%| | 274/14932 [00:36<32:11,  7.59it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -3663,8 +3636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 273/14932 [00:35<31:31,  7.75it/s, v_num=o30c, train/loss=3.840\r",
-      "Epoch 0:   2%| | 273/14932 [00:35<31:31,  7.75it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   2%| | 275/14932 [00:36<32:08,  7.60it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   2%| | 275/14932 [00:36<32:08,  7.60it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -3672,8 +3645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 274/14932 [00:35<31:28,  7.76it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   2%| | 274/14932 [00:35<31:28,  7.76it/s, v_num=o30c, train/loss=2.080"
+      "Epoch 0:   2%| | 276/14932 [00:36<32:04,  7.62it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   2%| | 276/14932 [00:36<32:04,  7.62it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -3681,8 +3654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 275/14932 [00:35<31:25,  7.77it/s, v_num=o30c, train/loss=2.080\r",
-      "Epoch 0:   2%| | 275/14932 [00:35<31:25,  7.77it/s, v_num=o30c, train/loss=5.560"
+      "Epoch 0:   2%| | 277/14932 [00:36<32:01,  7.63it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   2%| | 277/14932 [00:36<32:01,  7.63it/s, v_num=ui8w, train/loss=3.300"
      ]
     },
     {
@@ -3690,8 +3663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 276/14932 [00:35<31:22,  7.79it/s, v_num=o30c, train/loss=5.560\r",
-      "Epoch 0:   2%| | 276/14932 [00:35<31:22,  7.79it/s, v_num=o30c, train/loss=3.440"
+      "Epoch 0:   2%| | 278/14932 [00:36<31:58,  7.64it/s, v_num=ui8w, train/loss=3.300\r",
+      "Epoch 0:   2%| | 278/14932 [00:36<31:58,  7.64it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -3699,8 +3672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 277/14932 [00:35<31:22,  7.79it/s, v_num=o30c, train/loss=3.440\r",
-      "Epoch 0:   2%| | 277/14932 [00:35<31:22,  7.79it/s, v_num=o30c, train/loss=4.620"
+      "Epoch 0:   2%| | 279/14932 [00:36<31:54,  7.65it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   2%| | 279/14932 [00:36<31:54,  7.65it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -3708,8 +3681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 278/14932 [00:35<31:19,  7.80it/s, v_num=o30c, train/loss=4.620\r",
-      "Epoch 0:   2%| | 278/14932 [00:35<31:19,  7.80it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   2%| | 280/14932 [00:36<31:51,  7.67it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   2%| | 280/14932 [00:36<31:51,  7.67it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -3717,8 +3690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 279/14932 [00:35<31:16,  7.81it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   2%| | 279/14932 [00:35<31:16,  7.81it/s, v_num=o30c, train/loss=4.720"
+      "Epoch 0:   2%| | 281/14932 [00:36<31:48,  7.68it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   2%| | 281/14932 [00:36<31:48,  7.68it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -3726,8 +3699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 280/14932 [00:35<31:13,  7.82it/s, v_num=o30c, train/loss=4.720\r",
-      "Epoch 0:   2%| | 280/14932 [00:35<31:13,  7.82it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   2%| | 282/14932 [00:36<31:48,  7.68it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   2%| | 282/14932 [00:36<31:48,  7.68it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -3735,8 +3708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 281/14932 [00:35<31:10,  7.83it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   2%| | 281/14932 [00:35<31:10,  7.83it/s, v_num=o30c, train/loss=3.910"
+      "Epoch 0:   2%| | 283/14932 [00:36<31:44,  7.69it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   2%| | 283/14932 [00:36<31:44,  7.69it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -3744,8 +3717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 282/14932 [00:35<31:07,  7.85it/s, v_num=o30c, train/loss=3.910\r",
-      "Epoch 0:   2%| | 282/14932 [00:35<31:07,  7.85it/s, v_num=o30c, train/loss=1.540"
+      "Epoch 0:   2%| | 284/14932 [00:36<31:44,  7.69it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   2%| | 284/14932 [00:36<31:44,  7.69it/s, v_num=ui8w, train/loss=6.310"
      ]
     },
     {
@@ -3753,8 +3726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 283/14932 [00:36<31:04,  7.86it/s, v_num=o30c, train/loss=1.540\r",
-      "Epoch 0:   2%| | 283/14932 [00:36<31:04,  7.86it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   2%| | 285/14932 [00:37<31:47,  7.68it/s, v_num=ui8w, train/loss=6.310\r",
+      "Epoch 0:   2%| | 285/14932 [00:37<31:47,  7.68it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -3762,8 +3735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 284/14932 [00:36<31:01,  7.87it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   2%| | 284/14932 [00:36<31:01,  7.87it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   2%| | 286/14932 [00:37<31:44,  7.69it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 286/14932 [00:37<31:44,  7.69it/s, v_num=ui8w, train/loss=3.270"
      ]
     },
     {
@@ -3771,8 +3744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 285/14932 [00:36<30:57,  7.88it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   2%| | 285/14932 [00:36<30:57,  7.88it/s, v_num=o30c, train/loss=2.890"
+      "Epoch 0:   2%| | 287/14932 [00:37<31:40,  7.70it/s, v_num=ui8w, train/loss=3.270\r",
+      "Epoch 0:   2%| | 287/14932 [00:37<31:41,  7.70it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -3780,8 +3753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 286/14932 [00:36<30:55,  7.89it/s, v_num=o30c, train/loss=2.890\r",
-      "Epoch 0:   2%| | 286/14932 [00:36<30:55,  7.89it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   2%| | 288/14932 [00:37<31:43,  7.69it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   2%| | 288/14932 [00:37<31:43,  7.69it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -3789,8 +3762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 287/14932 [00:36<30:52,  7.91it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   2%| | 287/14932 [00:36<30:52,  7.91it/s, v_num=o30c, train/loss=2.910"
+      "Epoch 0:   2%| | 289/14932 [00:37<31:40,  7.71it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   2%| | 289/14932 [00:37<31:40,  7.71it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -3798,8 +3771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 288/14932 [00:36<30:55,  7.89it/s, v_num=o30c, train/loss=2.910\r",
-      "Epoch 0:   2%| | 288/14932 [00:36<30:55,  7.89it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   2%| | 290/14932 [00:37<31:37,  7.72it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   2%| | 290/14932 [00:37<31:37,  7.72it/s, v_num=ui8w, train/loss=4.560"
      ]
     },
     {
@@ -3807,8 +3780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 289/14932 [00:36<30:52,  7.91it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   2%| | 289/14932 [00:36<30:52,  7.91it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   2%| | 291/14932 [00:37<31:33,  7.73it/s, v_num=ui8w, train/loss=4.560\r",
+      "Epoch 0:   2%| | 291/14932 [00:37<31:33,  7.73it/s, v_num=ui8w, train/loss=2.770"
      ]
     },
     {
@@ -3816,7 +3789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 290/14932 [00:36<30:49,  7.92it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   2%| | 292/14932 [00:37<31:30,  7.74it/s, v_num=ui8w, train/loss=2.770\r",
+      "Epoch 0:   2%| | 292/14932 [00:37<31:30,  7.74it/s, v_num=ui8w, train/loss=2.500"
      ]
     },
     {
@@ -3824,7 +3798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 290/14932 [00:36<30:49,  7.92it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   2%| | 293/14932 [00:37<31:27,  7.76it/s, v_num=ui8w, train/loss=2.500\r",
+      "Epoch 0:   2%| | 293/14932 [00:37<31:27,  7.76it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -3832,8 +3807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 291/14932 [00:36<30:46,  7.93it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   2%| | 291/14932 [00:36<30:46,  7.93it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   2%| | 294/14932 [00:37<31:24,  7.77it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   2%| | 294/14932 [00:37<31:24,  7.77it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -3841,8 +3816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 292/14932 [00:36<30:43,  7.94it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   2%| | 292/14932 [00:36<30:43,  7.94it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   2%| | 295/14932 [00:37<31:21,  7.78it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   2%| | 295/14932 [00:37<31:21,  7.78it/s, v_num=ui8w, train/loss=3.950"
      ]
     },
     {
@@ -3850,8 +3825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 293/14932 [00:36<30:40,  7.95it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   2%| | 293/14932 [00:36<30:40,  7.95it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   2%| | 296/14932 [00:38<31:18,  7.79it/s, v_num=ui8w, train/loss=3.950\r",
+      "Epoch 0:   2%| | 296/14932 [00:38<31:18,  7.79it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -3859,8 +3834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 294/14932 [00:36<30:37,  7.96it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   2%| | 294/14932 [00:36<30:37,  7.96it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   2%| | 297/14932 [00:38<31:16,  7.80it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 297/14932 [00:38<31:16,  7.80it/s, v_num=ui8w, train/loss=4.310"
      ]
     },
     {
@@ -3868,8 +3843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 295/14932 [00:36<30:35,  7.98it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   2%| | 295/14932 [00:36<30:35,  7.98it/s, v_num=o30c, train/loss=2.330"
+      "Epoch 0:   2%| | 298/14932 [00:38<31:13,  7.81it/s, v_num=ui8w, train/loss=4.310\r",
+      "Epoch 0:   2%| | 298/14932 [00:38<31:13,  7.81it/s, v_num=ui8w, train/loss=2.890"
      ]
     },
     {
@@ -3877,8 +3852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 296/14932 [00:37<30:32,  7.99it/s, v_num=o30c, train/loss=2.330\r",
-      "Epoch 0:   2%| | 296/14932 [00:37<30:32,  7.99it/s, v_num=o30c, train/loss=2.050"
+      "Epoch 0:   2%| | 299/14932 [00:38<31:09,  7.83it/s, v_num=ui8w, train/loss=2.890\r",
+      "Epoch 0:   2%| | 299/14932 [00:38<31:09,  7.83it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -3886,8 +3861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 297/14932 [00:37<30:29,  8.00it/s, v_num=o30c, train/loss=2.050\r",
-      "Epoch 0:   2%| | 297/14932 [00:37<30:29,  8.00it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   2%| | 300/14932 [00:38<31:06,  7.84it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   2%| | 300/14932 [00:38<31:06,  7.84it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -3895,8 +3870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 298/14932 [00:37<30:27,  8.01it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   2%| | 298/14932 [00:37<30:27,  8.01it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   2%| | 301/14932 [00:38<31:04,  7.85it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   2%| | 301/14932 [00:38<31:04,  7.85it/s, v_num=ui8w, train/loss=2.140"
      ]
     },
     {
@@ -3904,8 +3879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 299/14932 [00:37<30:24,  8.02it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   2%| | 299/14932 [00:37<30:24,  8.02it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   2%| | 302/14932 [00:38<31:01,  7.86it/s, v_num=ui8w, train/loss=2.140\r",
+      "Epoch 0:   2%| | 302/14932 [00:38<31:01,  7.86it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -3913,8 +3888,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 300/14932 [00:37<30:22,  8.03it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   2%| | 300/14932 [00:37<30:22,  8.03it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   2%| | 303/14932 [00:38<30:58,  7.87it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -3922,8 +3896,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 301/14932 [00:37<30:19,  8.04it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   2%| | 301/14932 [00:37<30:19,  8.04it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   2%| | 303/14932 [00:38<30:58,  7.87it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -3931,8 +3904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 302/14932 [00:37<30:17,  8.05it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   2%| | 302/14932 [00:37<30:17,  8.05it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   2%| | 304/14932 [00:38<30:55,  7.88it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   2%| | 304/14932 [00:38<30:55,  7.88it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -3940,8 +3913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 303/14932 [00:37<30:14,  8.06it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   2%| | 303/14932 [00:37<30:14,  8.06it/s, v_num=o30c, train/loss=3.270"
+      "Epoch 0:   2%| | 305/14932 [00:38<30:52,  7.89it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   2%| | 305/14932 [00:38<30:52,  7.89it/s, v_num=ui8w, train/loss=3.580"
      ]
     },
     {
@@ -3949,8 +3922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 304/14932 [00:37<30:11,  8.07it/s, v_num=o30c, train/loss=3.270\r",
-      "Epoch 0:   2%| | 304/14932 [00:37<30:11,  8.07it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   2%| | 306/14932 [00:38<30:50,  7.91it/s, v_num=ui8w, train/loss=3.580\r",
+      "Epoch 0:   2%| | 306/14932 [00:38<30:50,  7.91it/s, v_num=ui8w, train/loss=3.770"
      ]
     },
     {
@@ -3958,8 +3931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 305/14932 [00:37<30:12,  8.07it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   2%| | 305/14932 [00:37<30:12,  8.07it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   2%| | 307/14932 [00:38<30:47,  7.92it/s, v_num=ui8w, train/loss=3.770\r",
+      "Epoch 0:   2%| | 307/14932 [00:38<30:47,  7.92it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -3967,8 +3940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 306/14932 [00:37<30:15,  8.06it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   2%| | 306/14932 [00:37<30:15,  8.06it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   2%| | 308/14932 [00:38<30:44,  7.93it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   2%| | 308/14932 [00:38<30:44,  7.93it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -3976,8 +3949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 307/14932 [00:38<30:13,  8.07it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   2%| | 307/14932 [00:38<30:13,  8.07it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   2%| | 309/14932 [00:38<30:41,  7.94it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   2%| | 309/14932 [00:38<30:41,  7.94it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -3985,8 +3958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 308/14932 [00:38<30:10,  8.08it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   2%| | 308/14932 [00:38<30:10,  8.08it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   2%| | 310/14932 [00:38<30:39,  7.95it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   2%| | 310/14932 [00:38<30:39,  7.95it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -3994,8 +3967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 309/14932 [00:38<30:07,  8.09it/s, v_num=o30c, train/loss=2.380\r",
-      "Epoch 0:   2%| | 309/14932 [00:38<30:07,  8.09it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   2%| | 311/14932 [00:39<30:36,  7.96it/s, v_num=ui8w, train/loss=2.030\r",
+      "Epoch 0:   2%| | 311/14932 [00:39<30:36,  7.96it/s, v_num=ui8w, train/loss=2.200"
      ]
     },
     {
@@ -4003,8 +3976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 310/14932 [00:38<30:05,  8.10it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   2%| | 310/14932 [00:38<30:05,  8.10it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   2%| | 312/14932 [00:39<30:33,  7.97it/s, v_num=ui8w, train/loss=2.200\r",
+      "Epoch 0:   2%| | 312/14932 [00:39<30:33,  7.97it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -4012,8 +3985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 311/14932 [00:38<30:02,  8.11it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   2%| | 311/14932 [00:38<30:02,  8.11it/s, v_num=o30c, train/loss=1.920"
+      "Epoch 0:   2%| | 313/14932 [00:39<30:30,  7.98it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   2%| | 313/14932 [00:39<30:30,  7.98it/s, v_num=ui8w, train/loss=2.200"
      ]
     },
     {
@@ -4021,8 +3994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 312/14932 [00:38<30:03,  8.11it/s, v_num=o30c, train/loss=1.920\r",
-      "Epoch 0:   2%| | 312/14932 [00:38<30:03,  8.11it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   2%| | 314/14932 [00:39<30:28,  7.99it/s, v_num=ui8w, train/loss=2.200\r",
+      "Epoch 0:   2%| | 314/14932 [00:39<30:28,  7.99it/s, v_num=ui8w, train/loss=2.440"
      ]
     },
     {
@@ -4030,8 +4003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 313/14932 [00:38<30:00,  8.12it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   2%| | 313/14932 [00:38<30:00,  8.12it/s, v_num=o30c, train/loss=4.500"
+      "Epoch 0:   2%| | 315/14932 [00:39<30:25,  8.01it/s, v_num=ui8w, train/loss=2.440\r",
+      "Epoch 0:   2%| | 315/14932 [00:39<30:25,  8.01it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -4039,8 +4012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 314/14932 [00:38<29:58,  8.13it/s, v_num=o30c, train/loss=4.500\r",
-      "Epoch 0:   2%| | 314/14932 [00:38<29:58,  8.13it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   2%| | 316/14932 [00:39<30:26,  8.00it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   2%| | 316/14932 [00:39<30:26,  8.00it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -4048,7 +4021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 315/14932 [00:38<29:55,  8.14it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   2%| | 317/14932 [00:39<30:23,  8.02it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   2%| | 317/14932 [00:39<30:23,  8.02it/s, v_num=ui8w, train/loss=3.250"
      ]
     },
     {
@@ -4056,7 +4030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 315/14932 [00:38<29:55,  8.14it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   2%| | 318/14932 [00:39<30:20,  8.03it/s, v_num=ui8w, train/loss=3.250\r",
+      "Epoch 0:   2%| | 318/14932 [00:39<30:20,  8.03it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -4064,8 +4039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 316/14932 [00:38<29:56,  8.14it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   2%| | 316/14932 [00:38<29:56,  8.14it/s, v_num=o30c, train/loss=4.620"
+      "Epoch 0:   2%| | 319/14932 [00:39<30:18,  8.04it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   2%| | 319/14932 [00:39<30:18,  8.04it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -4073,8 +4048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 317/14932 [00:38<29:53,  8.15it/s, v_num=o30c, train/loss=4.620\r",
-      "Epoch 0:   2%| | 317/14932 [00:38<29:53,  8.15it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   2%| | 320/14932 [00:39<30:20,  8.02it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   2%| | 320/14932 [00:39<30:20,  8.02it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -4082,8 +4057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 318/14932 [00:38<29:50,  8.16it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   2%| | 318/14932 [00:38<29:50,  8.16it/s, v_num=o30c, train/loss=2.620"
+      "Epoch 0:   2%| | 321/14932 [00:39<30:18,  8.04it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   2%| | 321/14932 [00:39<30:18,  8.04it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -4091,8 +4066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 319/14932 [00:39<29:48,  8.17it/s, v_num=o30c, train/loss=2.620\r",
-      "Epoch 0:   2%| | 319/14932 [00:39<29:48,  8.17it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   2%| | 322/14932 [00:40<30:15,  8.05it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 322/14932 [00:40<30:15,  8.05it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -4100,8 +4075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 320/14932 [00:39<29:51,  8.16it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   2%| | 320/14932 [00:39<29:51,  8.16it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   2%| | 323/14932 [00:40<30:13,  8.06it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   2%| | 323/14932 [00:40<30:13,  8.06it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -4109,8 +4084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 321/14932 [00:39<29:49,  8.17it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   2%| | 321/14932 [00:39<29:49,  8.17it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   2%| | 324/14932 [00:40<30:10,  8.07it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   2%| | 324/14932 [00:40<30:10,  8.07it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -4118,8 +4093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 322/14932 [00:39<29:46,  8.18it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   2%| | 322/14932 [00:39<29:46,  8.18it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   2%| | 325/14932 [00:40<30:11,  8.06it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   2%| | 325/14932 [00:40<30:11,  8.06it/s, v_num=ui8w, train/loss=4.530"
      ]
     },
     {
@@ -4127,8 +4102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 323/14932 [00:39<29:44,  8.19it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   2%| | 323/14932 [00:39<29:44,  8.19it/s, v_num=o30c, train/loss=2.700"
+      "Epoch 0:   2%| | 326/14932 [00:40<30:08,  8.07it/s, v_num=ui8w, train/loss=4.530\r",
+      "Epoch 0:   2%| | 326/14932 [00:40<30:08,  8.07it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -4136,8 +4111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 324/14932 [00:39<29:42,  8.20it/s, v_num=o30c, train/loss=2.700\r",
-      "Epoch 0:   2%| | 324/14932 [00:39<29:42,  8.20it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   2%| | 327/14932 [00:40<30:06,  8.08it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   2%| | 327/14932 [00:40<30:06,  8.08it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -4145,8 +4120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 325/14932 [00:39<29:39,  8.21it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   2%| | 325/14932 [00:39<29:39,  8.21it/s, v_num=o30c, train/loss=4.560"
+      "Epoch 0:   2%| | 328/14932 [00:40<30:04,  8.09it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   2%| | 328/14932 [00:40<30:04,  8.09it/s, v_num=ui8w, train/loss=2.560"
      ]
     },
     {
@@ -4154,8 +4129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 326/14932 [00:39<29:37,  8.22it/s, v_num=o30c, train/loss=4.560\r",
-      "Epoch 0:   2%| | 326/14932 [00:39<29:37,  8.22it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   2%| | 329/14932 [00:40<30:02,  8.10it/s, v_num=ui8w, train/loss=2.560\r",
+      "Epoch 0:   2%| | 329/14932 [00:40<30:02,  8.10it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -4163,8 +4138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 327/14932 [00:39<29:35,  8.23it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   2%| | 327/14932 [00:39<29:35,  8.23it/s, v_num=o30c, train/loss=2.140"
+      "Epoch 0:   2%| | 330/14932 [00:40<29:59,  8.11it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   2%| | 330/14932 [00:40<29:59,  8.11it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -4172,8 +4147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 328/14932 [00:39<29:35,  8.22it/s, v_num=o30c, train/loss=2.140\r",
-      "Epoch 0:   2%| | 328/14932 [00:39<29:35,  8.22it/s, v_num=o30c, train/loss=3.940"
+      "Epoch 0:   2%| | 331/14932 [00:40<29:57,  8.12it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   2%| | 331/14932 [00:40<29:57,  8.12it/s, v_num=ui8w, train/loss=1.440"
      ]
     },
     {
@@ -4181,8 +4156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 329/14932 [00:40<29:36,  8.22it/s, v_num=o30c, train/loss=3.940\r",
-      "Epoch 0:   2%| | 329/14932 [00:40<29:36,  8.22it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   2%| | 332/14932 [00:40<29:55,  8.13it/s, v_num=ui8w, train/loss=1.440\r",
+      "Epoch 0:   2%| | 332/14932 [00:40<29:55,  8.13it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -4190,8 +4165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 330/14932 [00:40<29:36,  8.22it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   2%| | 330/14932 [00:40<29:36,  8.22it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   2%| | 333/14932 [00:40<29:52,  8.14it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   2%| | 333/14932 [00:40<29:52,  8.14it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -4199,8 +4174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 331/14932 [00:40<29:34,  8.23it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   2%| | 331/14932 [00:40<29:34,  8.23it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   2%| | 334/14932 [00:40<29:50,  8.15it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   2%| | 334/14932 [00:40<29:50,  8.15it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -4208,8 +4183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 332/14932 [00:40<29:32,  8.24it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   2%| | 332/14932 [00:40<29:32,  8.24it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   2%| | 335/14932 [00:41<29:48,  8.16it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   2%| | 335/14932 [00:41<29:48,  8.16it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -4217,8 +4192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 333/14932 [00:40<29:29,  8.25it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   2%| | 333/14932 [00:40<29:29,  8.25it/s, v_num=o30c, train/loss=2.640"
+      "Epoch 0:   2%| | 336/14932 [00:41<29:46,  8.17it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   2%| | 336/14932 [00:41<29:46,  8.17it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -4226,8 +4201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 334/14932 [00:40<29:27,  8.26it/s, v_num=o30c, train/loss=2.640\r",
-      "Epoch 0:   2%| | 334/14932 [00:40<29:27,  8.26it/s, v_num=o30c, train/loss=2.880"
+      "Epoch 0:   2%| | 337/14932 [00:41<29:43,  8.18it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   2%| | 337/14932 [00:41<29:43,  8.18it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -4235,8 +4210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 335/14932 [00:40<29:28,  8.26it/s, v_num=o30c, train/loss=2.880\r",
-      "Epoch 0:   2%| | 335/14932 [00:40<29:28,  8.26it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   2%| | 338/14932 [00:41<29:41,  8.19it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   2%| | 338/14932 [00:41<29:41,  8.19it/s, v_num=ui8w, train/loss=2.200"
      ]
     },
     {
@@ -4244,8 +4219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 336/14932 [00:40<29:25,  8.27it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   2%| | 336/14932 [00:40<29:25,  8.27it/s, v_num=o30c, train/loss=1.800"
+      "Epoch 0:   2%| | 339/14932 [00:41<29:39,  8.20it/s, v_num=ui8w, train/loss=2.200\r",
+      "Epoch 0:   2%| | 339/14932 [00:41<29:39,  8.20it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -4253,8 +4228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 337/14932 [00:40<29:23,  8.28it/s, v_num=o30c, train/loss=1.800\r",
-      "Epoch 0:   2%| | 337/14932 [00:40<29:23,  8.28it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   2%| | 340/14932 [00:41<29:37,  8.21it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   2%| | 340/14932 [00:41<29:37,  8.21it/s, v_num=ui8w, train/loss=3.440"
      ]
     },
     {
@@ -4262,8 +4237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 338/14932 [00:40<29:21,  8.29it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   2%| | 338/14932 [00:40<29:21,  8.29it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   2%| | 341/14932 [00:41<29:34,  8.22it/s, v_num=ui8w, train/loss=3.440\r",
+      "Epoch 0:   2%| | 341/14932 [00:41<29:34,  8.22it/s, v_num=ui8w, train/loss=1.660"
      ]
     },
     {
@@ -4271,8 +4246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 339/14932 [00:40<29:19,  8.30it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   2%| | 339/14932 [00:40<29:19,  8.30it/s, v_num=o30c, train/loss=4.310"
+      "Epoch 0:   2%| | 342/14932 [00:41<29:32,  8.23it/s, v_num=ui8w, train/loss=1.660\r",
+      "Epoch 0:   2%| | 342/14932 [00:41<29:32,  8.23it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -4280,8 +4255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 340/14932 [00:40<29:16,  8.31it/s, v_num=o30c, train/loss=4.310\r",
-      "Epoch 0:   2%| | 340/14932 [00:40<29:16,  8.31it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   2%| | 343/14932 [00:41<29:30,  8.24it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   2%| | 343/14932 [00:41<29:30,  8.24it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -4289,8 +4264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 341/14932 [00:41<29:14,  8.31it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   2%| | 341/14932 [00:41<29:14,  8.31it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   2%| | 344/14932 [00:41<29:28,  8.25it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   2%| | 344/14932 [00:41<29:28,  8.25it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -4298,8 +4273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 342/14932 [00:41<29:12,  8.32it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   2%| | 342/14932 [00:41<29:12,  8.32it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   2%| | 345/14932 [00:41<29:26,  8.26it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   2%| | 345/14932 [00:41<29:26,  8.26it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -4307,8 +4282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 343/14932 [00:41<29:10,  8.33it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   2%| | 343/14932 [00:41<29:10,  8.33it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   2%| | 346/14932 [00:41<29:24,  8.27it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   2%| | 346/14932 [00:41<29:24,  8.27it/s, v_num=ui8w, train/loss=3.080"
      ]
     },
     {
@@ -4316,8 +4291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 344/14932 [00:41<29:08,  8.34it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   2%| | 344/14932 [00:41<29:08,  8.34it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   2%| | 347/14932 [00:41<29:22,  8.28it/s, v_num=ui8w, train/loss=3.080\r",
+      "Epoch 0:   2%| | 347/14932 [00:41<29:22,  8.28it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -4325,8 +4300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 345/14932 [00:41<29:06,  8.35it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   2%| | 345/14932 [00:41<29:06,  8.35it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   2%| | 348/14932 [00:42<29:20,  8.29it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   2%| | 348/14932 [00:42<29:20,  8.29it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -4334,8 +4309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 346/14932 [00:41<29:04,  8.36it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   2%| | 346/14932 [00:41<29:04,  8.36it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   2%| | 349/14932 [00:42<29:18,  8.29it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   2%| | 349/14932 [00:42<29:18,  8.29it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -4343,8 +4318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 347/14932 [00:41<29:02,  8.37it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   2%| | 347/14932 [00:41<29:02,  8.37it/s, v_num=o30c, train/loss=2.970"
+      "Epoch 0:   2%| | 350/14932 [00:42<29:15,  8.30it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   2%| | 350/14932 [00:42<29:15,  8.30it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -4352,8 +4327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 348/14932 [00:41<28:59,  8.38it/s, v_num=o30c, train/loss=2.970\r",
-      "Epoch 0:   2%| | 348/14932 [00:41<28:59,  8.38it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   2%| | 351/14932 [00:42<29:13,  8.31it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   2%| | 351/14932 [00:42<29:13,  8.31it/s, v_num=ui8w, train/loss=1.490"
      ]
     },
     {
@@ -4361,8 +4336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 349/14932 [00:41<28:58,  8.39it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   2%| | 349/14932 [00:41<28:58,  8.39it/s, v_num=o30c, train/loss=4.530"
+      "Epoch 0:   2%| | 352/14932 [00:42<29:16,  8.30it/s, v_num=ui8w, train/loss=1.490\r",
+      "Epoch 0:   2%| | 352/14932 [00:42<29:16,  8.30it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -4370,8 +4345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 350/14932 [00:41<28:55,  8.40it/s, v_num=o30c, train/loss=4.530\r",
-      "Epoch 0:   2%| | 350/14932 [00:41<28:55,  8.40it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   2%| | 353/14932 [00:42<29:14,  8.31it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   2%| | 353/14932 [00:42<29:14,  8.31it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -4379,8 +4354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 351/14932 [00:41<28:54,  8.41it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   2%| | 351/14932 [00:41<28:54,  8.41it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   2%| | 354/14932 [00:42<29:12,  8.32it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   2%| | 354/14932 [00:42<29:12,  8.32it/s, v_num=ui8w, train/loss=4.880"
      ]
     },
     {
@@ -4388,8 +4363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 352/14932 [00:41<28:56,  8.39it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   2%| | 352/14932 [00:41<28:56,  8.39it/s, v_num=o30c, train/loss=3.440"
+      "Epoch 0:   2%| | 355/14932 [00:42<29:10,  8.33it/s, v_num=ui8w, train/loss=4.880\r",
+      "Epoch 0:   2%| | 355/14932 [00:42<29:10,  8.33it/s, v_num=ui8w, train/loss=2.580"
      ]
     },
     {
@@ -4397,8 +4372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 353/14932 [00:42<28:54,  8.40it/s, v_num=o30c, train/loss=3.440\r",
-      "Epoch 0:   2%| | 353/14932 [00:42<28:54,  8.40it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   2%| | 356/14932 [00:42<29:08,  8.34it/s, v_num=ui8w, train/loss=2.580\r",
+      "Epoch 0:   2%| | 356/14932 [00:42<29:08,  8.34it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -4406,8 +4381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 354/14932 [00:42<28:52,  8.41it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   2%| | 354/14932 [00:42<28:52,  8.41it/s, v_num=o30c, train/loss=2.390"
+      "Epoch 0:   2%| | 357/14932 [00:42<29:06,  8.35it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   2%| | 357/14932 [00:42<29:06,  8.35it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -4415,8 +4390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 355/14932 [00:42<28:50,  8.42it/s, v_num=o30c, train/loss=2.390\r",
-      "Epoch 0:   2%| | 355/14932 [00:42<28:50,  8.42it/s, v_num=o30c, train/loss=2.620"
+      "Epoch 0:   2%| | 358/14932 [00:42<29:04,  8.36it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   2%| | 358/14932 [00:42<29:04,  8.36it/s, v_num=ui8w, train/loss=3.270"
      ]
     },
     {
@@ -4424,8 +4399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 356/14932 [00:42<28:48,  8.43it/s, v_num=o30c, train/loss=2.620\r",
-      "Epoch 0:   2%| | 356/14932 [00:42<28:48,  8.43it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   2%| | 359/14932 [00:42<29:02,  8.37it/s, v_num=ui8w, train/loss=3.270\r",
+      "Epoch 0:   2%| | 359/14932 [00:42<29:02,  8.37it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -4433,8 +4408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 357/14932 [00:42<28:46,  8.44it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   2%| | 357/14932 [00:42<28:46,  8.44it/s, v_num=o30c, train/loss=2.590"
+      "Epoch 0:   2%| | 360/14932 [00:42<29:00,  8.37it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   2%| | 360/14932 [00:42<29:00,  8.37it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -4442,8 +4417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 358/14932 [00:42<28:47,  8.44it/s, v_num=o30c, train/loss=2.590\r",
-      "Epoch 0:   2%| | 358/14932 [00:42<28:47,  8.44it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   2%| | 361/14932 [00:43<28:58,  8.38it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   2%| | 361/14932 [00:43<28:58,  8.38it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -4451,8 +4426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 359/14932 [00:42<28:45,  8.45it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   2%| | 359/14932 [00:42<28:45,  8.45it/s, v_num=o30c, train/loss=4.690"
+      "Epoch 0:   2%| | 362/14932 [00:43<28:56,  8.39it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   2%| | 362/14932 [00:43<28:56,  8.39it/s, v_num=ui8w, train/loss=2.380"
      ]
     },
     {
@@ -4460,8 +4435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 360/14932 [00:42<28:43,  8.45it/s, v_num=o30c, train/loss=4.690\r",
-      "Epoch 0:   2%| | 360/14932 [00:42<28:43,  8.45it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   2%| | 363/14932 [00:43<28:54,  8.40it/s, v_num=ui8w, train/loss=2.380\r",
+      "Epoch 0:   2%| | 363/14932 [00:43<28:54,  8.40it/s, v_num=ui8w, train/loss=4.530"
      ]
     },
     {
@@ -4469,8 +4444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 361/14932 [00:42<28:41,  8.46it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   2%| | 361/14932 [00:42<28:41,  8.46it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   2%| | 364/14932 [00:43<28:52,  8.41it/s, v_num=ui8w, train/loss=4.530\r",
+      "Epoch 0:   2%| | 364/14932 [00:43<28:52,  8.41it/s, v_num=ui8w, train/loss=3.580"
      ]
     },
     {
@@ -4478,8 +4453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 362/14932 [00:42<28:40,  8.47it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   2%| | 362/14932 [00:42<28:40,  8.47it/s, v_num=o30c, train/loss=1.760"
+      "Epoch 0:   2%| | 365/14932 [00:43<28:52,  8.41it/s, v_num=ui8w, train/loss=3.580\r",
+      "Epoch 0:   2%| | 365/14932 [00:43<28:52,  8.41it/s, v_num=ui8w, train/loss=4.470"
      ]
     },
     {
@@ -4487,8 +4462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 363/14932 [00:42<28:38,  8.48it/s, v_num=o30c, train/loss=1.760\r",
-      "Epoch 0:   2%| | 363/14932 [00:42<28:38,  8.48it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   2%| | 366/14932 [00:43<28:50,  8.42it/s, v_num=ui8w, train/loss=4.470\r",
+      "Epoch 0:   2%| | 366/14932 [00:43<28:50,  8.42it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -4496,8 +4471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 364/14932 [00:42<28:36,  8.49it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   2%| | 364/14932 [00:42<28:36,  8.49it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   2%| | 367/14932 [00:43<28:48,  8.42it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   2%| | 367/14932 [00:43<28:48,  8.42it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -4505,8 +4480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 365/14932 [00:42<28:34,  8.50it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   2%| | 365/14932 [00:42<28:34,  8.50it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   2%| | 368/14932 [00:43<28:47,  8.43it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   2%| | 368/14932 [00:43<28:47,  8.43it/s, v_num=ui8w, train/loss=3.250"
      ]
     },
     {
@@ -4514,8 +4489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 366/14932 [00:43<28:32,  8.50it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   2%| | 366/14932 [00:43<28:32,  8.50it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   2%| | 369/14932 [00:43<28:45,  8.44it/s, v_num=ui8w, train/loss=3.250\r",
+      "Epoch 0:   2%| | 369/14932 [00:43<28:45,  8.44it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -4523,8 +4498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 367/14932 [00:43<28:30,  8.51it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   2%| | 367/14932 [00:43<28:30,  8.51it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   2%| | 370/14932 [00:43<28:43,  8.45it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   2%| | 370/14932 [00:43<28:43,  8.45it/s, v_num=ui8w, train/loss=2.270"
      ]
     },
     {
@@ -4532,8 +4507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 368/14932 [00:43<28:28,  8.52it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   2%| | 368/14932 [00:43<28:29,  8.52it/s, v_num=o30c, train/loss=4.120"
+      "Epoch 0:   2%| | 371/14932 [00:43<28:41,  8.46it/s, v_num=ui8w, train/loss=2.270\r",
+      "Epoch 0:   2%| | 371/14932 [00:43<28:41,  8.46it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -4541,8 +4516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 369/14932 [00:43<28:27,  8.53it/s, v_num=o30c, train/loss=4.120\r",
-      "Epoch 0:   2%| | 369/14932 [00:43<28:27,  8.53it/s, v_num=o30c, train/loss=3.910"
+      "Epoch 0:   2%| | 372/14932 [00:43<28:39,  8.47it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   2%| | 372/14932 [00:43<28:39,  8.47it/s, v_num=ui8w, train/loss=4.440"
      ]
     },
     {
@@ -4550,8 +4525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 370/14932 [00:43<28:25,  8.54it/s, v_num=o30c, train/loss=3.910\r",
-      "Epoch 0:   2%| | 370/14932 [00:43<28:25,  8.54it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   2%| | 373/14932 [00:43<28:37,  8.48it/s, v_num=ui8w, train/loss=4.440\r",
+      "Epoch 0:   2%| | 373/14932 [00:43<28:37,  8.48it/s, v_num=ui8w, train/loss=2.520"
      ]
     },
     {
@@ -4559,8 +4534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 371/14932 [00:43<28:23,  8.55it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   2%| | 371/14932 [00:43<28:23,  8.55it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   3%| | 374/14932 [00:44<28:35,  8.49it/s, v_num=ui8w, train/loss=2.520\r",
+      "Epoch 0:   3%| | 374/14932 [00:44<28:35,  8.49it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -4568,8 +4543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 372/14932 [00:43<28:22,  8.55it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   2%| | 372/14932 [00:43<28:22,  8.55it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   3%| | 375/14932 [00:44<28:33,  8.49it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   3%| | 375/14932 [00:44<28:33,  8.49it/s, v_num=ui8w, train/loss=2.770"
      ]
     },
     {
@@ -4577,8 +4552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   2%| | 373/14932 [00:43<28:20,  8.56it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   2%| | 373/14932 [00:43<28:20,  8.56it/s, v_num=o30c, train/loss=2.720"
+      "Epoch 0:   3%| | 376/14932 [00:44<28:31,  8.50it/s, v_num=ui8w, train/loss=2.770\r",
+      "Epoch 0:   3%| | 376/14932 [00:44<28:31,  8.50it/s, v_num=ui8w, train/loss=3.080"
      ]
     },
     {
@@ -4586,8 +4561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 374/14932 [00:43<28:18,  8.57it/s, v_num=o30c, train/loss=2.720\r",
-      "Epoch 0:   3%| | 374/14932 [00:43<28:18,  8.57it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   3%| | 377/14932 [00:44<28:29,  8.51it/s, v_num=ui8w, train/loss=3.080\r",
+      "Epoch 0:   3%| | 377/14932 [00:44<28:29,  8.51it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -4595,8 +4570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 375/14932 [00:43<28:16,  8.58it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   3%| | 375/14932 [00:43<28:16,  8.58it/s, v_num=o30c, train/loss=2.810"
+      "Epoch 0:   3%| | 378/14932 [00:44<28:27,  8.52it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   3%| | 378/14932 [00:44<28:27,  8.52it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -4604,8 +4579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 376/14932 [00:43<28:14,  8.59it/s, v_num=o30c, train/loss=2.810\r",
-      "Epoch 0:   3%| | 376/14932 [00:43<28:14,  8.59it/s, v_num=o30c, train/loss=4.840"
+      "Epoch 0:   3%| | 379/14932 [00:44<28:26,  8.53it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   3%| | 379/14932 [00:44<28:26,  8.53it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -4613,8 +4588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 377/14932 [00:43<28:12,  8.60it/s, v_num=o30c, train/loss=4.840\r",
-      "Epoch 0:   3%| | 377/14932 [00:43<28:12,  8.60it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   3%| | 380/14932 [00:44<28:24,  8.54it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   3%| | 380/14932 [00:44<28:24,  8.54it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -4622,8 +4597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 378/14932 [00:43<28:11,  8.61it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   3%| | 378/14932 [00:43<28:11,  8.61it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   3%| | 381/14932 [00:44<28:22,  8.55it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   3%| | 381/14932 [00:44<28:22,  8.55it/s, v_num=ui8w, train/loss=2.550"
      ]
     },
     {
@@ -4631,8 +4606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 379/14932 [00:43<28:09,  8.61it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   3%| | 379/14932 [00:43<28:09,  8.61it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   3%| | 382/14932 [00:44<28:20,  8.55it/s, v_num=ui8w, train/loss=2.550\r",
+      "Epoch 0:   3%| | 382/14932 [00:44<28:20,  8.55it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -4640,8 +4615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 380/14932 [00:44<28:07,  8.62it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   3%| | 380/14932 [00:44<28:07,  8.62it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   3%| | 383/14932 [00:44<28:19,  8.56it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   3%| | 383/14932 [00:44<28:19,  8.56it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -4649,8 +4624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 381/14932 [00:44<28:05,  8.63it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   3%| | 381/14932 [00:44<28:05,  8.63it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   3%| | 384/14932 [00:44<28:21,  8.55it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   3%| | 384/14932 [00:44<28:21,  8.55it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -4658,8 +4633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 382/14932 [00:44<28:06,  8.63it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   3%| | 382/14932 [00:44<28:06,  8.63it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   3%| | 385/14932 [00:44<28:19,  8.56it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   3%| | 385/14932 [00:44<28:19,  8.56it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -4667,8 +4642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 383/14932 [00:45<28:43,  8.44it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   3%| | 383/14932 [00:45<28:43,  8.44it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   3%| | 386/14932 [00:45<28:18,  8.57it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   3%| | 386/14932 [00:45<28:18,  8.57it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -4676,8 +4651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 384/14932 [00:45<28:45,  8.43it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   3%| | 384/14932 [00:45<28:45,  8.43it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   3%| | 387/14932 [00:45<28:16,  8.57it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   3%| | 387/14932 [00:45<28:16,  8.57it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -4685,8 +4660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 385/14932 [00:45<28:43,  8.44it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   3%| | 385/14932 [00:45<28:43,  8.44it/s, v_num=o30c, train/loss=5.000"
+      "Epoch 0:   3%| | 388/14932 [00:45<28:14,  8.58it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   3%| | 388/14932 [00:45<28:14,  8.58it/s, v_num=ui8w, train/loss=1.960"
      ]
     },
     {
@@ -4694,8 +4669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 386/14932 [00:45<28:41,  8.45it/s, v_num=o30c, train/loss=5.000\r",
-      "Epoch 0:   3%| | 386/14932 [00:45<28:41,  8.45it/s, v_num=o30c, train/loss=3.270"
+      "Epoch 0:   3%| | 389/14932 [00:45<28:13,  8.59it/s, v_num=ui8w, train/loss=1.960\r",
+      "Epoch 0:   3%| | 389/14932 [00:45<28:13,  8.59it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -4703,8 +4678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 387/14932 [00:45<28:39,  8.46it/s, v_num=o30c, train/loss=3.270\r",
-      "Epoch 0:   3%| | 387/14932 [00:45<28:39,  8.46it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   3%| | 390/14932 [00:45<28:11,  8.60it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   3%| | 390/14932 [00:45<28:11,  8.60it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -4712,8 +4687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 388/14932 [00:45<28:38,  8.47it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   3%| | 388/14932 [00:45<28:38,  8.47it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   3%| | 391/14932 [00:45<28:09,  8.61it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   3%| | 391/14932 [00:45<28:09,  8.61it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -4721,8 +4696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 389/14932 [00:45<28:36,  8.47it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   3%| | 389/14932 [00:45<28:36,  8.47it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   3%| | 392/14932 [00:45<28:07,  8.62it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   3%| | 392/14932 [00:45<28:07,  8.62it/s, v_num=ui8w, train/loss=2.330"
      ]
     },
     {
@@ -4730,8 +4705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 390/14932 [00:46<28:43,  8.44it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   3%| | 390/14932 [00:46<28:43,  8.44it/s, v_num=o30c, train/loss=2.640"
+      "Epoch 0:   3%| | 393/14932 [00:45<28:06,  8.62it/s, v_num=ui8w, train/loss=2.330\r",
+      "Epoch 0:   3%| | 393/14932 [00:45<28:06,  8.62it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -4739,8 +4714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 391/14932 [00:46<28:41,  8.45it/s, v_num=o30c, train/loss=2.640\r",
-      "Epoch 0:   3%| | 391/14932 [00:46<28:41,  8.45it/s, v_num=o30c, train/loss=1.280"
+      "Epoch 0:   3%| | 394/14932 [00:45<28:06,  8.62it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   3%| | 394/14932 [00:45<28:06,  8.62it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -4748,8 +4723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 392/14932 [00:46<28:39,  8.45it/s, v_num=o30c, train/loss=1.280\r",
-      "Epoch 0:   3%| | 392/14932 [00:46<28:39,  8.45it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   3%| | 395/14932 [00:45<28:04,  8.63it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   3%| | 395/14932 [00:45<28:04,  8.63it/s, v_num=ui8w, train/loss=5.190"
      ]
     },
     {
@@ -4757,8 +4732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 393/14932 [00:46<28:37,  8.46it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   3%| | 393/14932 [00:46<28:37,  8.46it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   3%| | 396/14932 [00:45<28:02,  8.64it/s, v_num=ui8w, train/loss=5.190\r",
+      "Epoch 0:   3%| | 396/14932 [00:45<28:02,  8.64it/s, v_num=ui8w, train/loss=4.530"
      ]
     },
     {
@@ -4766,8 +4741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 394/14932 [00:46<28:35,  8.47it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   3%| | 394/14932 [00:46<28:36,  8.47it/s, v_num=o30c, train/loss=2.450"
+      "Epoch 0:   3%| | 397/14932 [00:45<28:01,  8.65it/s, v_num=ui8w, train/loss=4.530\r",
+      "Epoch 0:   3%| | 397/14932 [00:45<28:01,  8.65it/s, v_num=ui8w, train/loss=1.570"
      ]
     },
     {
@@ -4775,8 +4750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 395/14932 [00:46<28:34,  8.48it/s, v_num=o30c, train/loss=2.450\r",
-      "Epoch 0:   3%| | 395/14932 [00:46<28:34,  8.48it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   3%| | 398/14932 [00:45<27:59,  8.66it/s, v_num=ui8w, train/loss=1.570\r",
+      "Epoch 0:   3%| | 398/14932 [00:45<27:59,  8.66it/s, v_num=ui8w, train/loss=1.830"
      ]
     },
     {
@@ -4784,8 +4759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 396/14932 [00:46<28:32,  8.49it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   3%| | 396/14932 [00:46<28:32,  8.49it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   3%| | 399/14932 [00:46<27:57,  8.67it/s, v_num=ui8w, train/loss=1.830\r",
+      "Epoch 0:   3%| | 399/14932 [00:46<27:57,  8.67it/s, v_num=ui8w, train/loss=2.330"
      ]
     },
     {
@@ -4793,8 +4768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 397/14932 [00:46<28:30,  8.50it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   3%| | 397/14932 [00:46<28:30,  8.50it/s, v_num=o30c, train/loss=2.770"
+      "Epoch 0:   3%| | 400/14932 [00:46<27:55,  8.67it/s, v_num=ui8w, train/loss=2.330\r",
+      "Epoch 0:   3%| | 400/14932 [00:46<27:55,  8.67it/s, v_num=ui8w, train/loss=1.660"
      ]
     },
     {
@@ -4802,8 +4777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 398/14932 [00:46<28:29,  8.50it/s, v_num=o30c, train/loss=2.770\r",
-      "Epoch 0:   3%| | 398/14932 [00:46<28:29,  8.50it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   3%| | 401/14932 [00:46<27:53,  8.68it/s, v_num=ui8w, train/loss=1.660\r",
+      "Epoch 0:   3%| | 401/14932 [00:46<27:53,  8.68it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -4811,8 +4786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 399/14932 [00:46<28:27,  8.51it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   3%| | 399/14932 [00:46<28:27,  8.51it/s, v_num=o30c, train/loss=4.310"
+      "Epoch 0:   3%| | 402/14932 [00:46<27:51,  8.69it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   3%| | 402/14932 [00:46<27:51,  8.69it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -4820,8 +4795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 400/14932 [00:46<28:25,  8.52it/s, v_num=o30c, train/loss=4.310\r",
-      "Epoch 0:   3%| | 400/14932 [00:46<28:26,  8.52it/s, v_num=o30c, train/loss=3.910"
+      "Epoch 0:   3%| | 403/14932 [00:46<27:49,  8.70it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   3%| | 403/14932 [00:46<27:49,  8.70it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -4829,8 +4804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 401/14932 [00:47<28:24,  8.53it/s, v_num=o30c, train/loss=3.910\r",
-      "Epoch 0:   3%| | 401/14932 [00:47<28:24,  8.53it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   3%| | 404/14932 [00:46<27:47,  8.71it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   3%| | 404/14932 [00:46<27:47,  8.71it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -4838,8 +4813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 402/14932 [00:47<28:22,  8.53it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   3%| | 402/14932 [00:47<28:22,  8.53it/s, v_num=o30c, train/loss=4.310"
+      "Epoch 0:   3%| | 405/14932 [00:46<27:46,  8.72it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   3%| | 405/14932 [00:46<27:46,  8.72it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -4847,8 +4822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 403/14932 [00:47<28:21,  8.54it/s, v_num=o30c, train/loss=4.310\r",
-      "Epoch 0:   3%| | 403/14932 [00:47<28:21,  8.54it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   3%| | 406/14932 [00:46<27:44,  8.73it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   3%| | 406/14932 [00:46<27:44,  8.73it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -4856,8 +4831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 404/14932 [00:47<28:19,  8.55it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   3%| | 404/14932 [00:47<28:19,  8.55it/s, v_num=o30c, train/loss=2.970"
+      "Epoch 0:   3%| | 407/14932 [00:46<27:42,  8.73it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   3%| | 407/14932 [00:46<27:43,  8.73it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -4865,8 +4840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 405/14932 [00:47<28:17,  8.56it/s, v_num=o30c, train/loss=2.970\r",
-      "Epoch 0:   3%| | 405/14932 [00:47<28:17,  8.56it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   3%| | 408/14932 [00:46<27:41,  8.74it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   3%| | 408/14932 [00:46<27:41,  8.74it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -4874,8 +4849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 406/14932 [00:47<28:15,  8.56it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   3%| | 406/14932 [00:47<28:15,  8.56it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   3%| | 409/14932 [00:46<27:39,  8.75it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   3%| | 409/14932 [00:46<27:39,  8.75it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -4883,8 +4858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 407/14932 [00:47<28:16,  8.56it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   3%| | 407/14932 [00:47<28:16,  8.56it/s, v_num=o30c, train/loss=4.660"
+      "Epoch 0:   3%| | 410/14932 [00:46<27:38,  8.76it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   3%| | 410/14932 [00:46<27:38,  8.76it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -4892,8 +4867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 408/14932 [00:47<28:14,  8.57it/s, v_num=o30c, train/loss=4.660\r",
-      "Epoch 0:   3%| | 408/14932 [00:47<28:14,  8.57it/s, v_num=o30c, train/loss=2.440"
+      "Epoch 0:   3%| | 411/14932 [00:46<27:36,  8.77it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   3%| | 411/14932 [00:46<27:36,  8.77it/s, v_num=ui8w, train/loss=3.390"
      ]
     },
     {
@@ -4901,8 +4876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 409/14932 [00:47<28:12,  8.58it/s, v_num=o30c, train/loss=2.440\r",
-      "Epoch 0:   3%| | 409/14932 [00:47<28:12,  8.58it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   3%| | 412/14932 [00:46<27:34,  8.77it/s, v_num=ui8w, train/loss=3.390\r",
+      "Epoch 0:   3%| | 412/14932 [00:46<27:34,  8.77it/s, v_num=ui8w, train/loss=3.580"
      ]
     },
     {
@@ -4910,8 +4885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 410/14932 [00:47<28:11,  8.59it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   3%| | 410/14932 [00:47<28:11,  8.59it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   3%| | 413/14932 [00:47<27:33,  8.78it/s, v_num=ui8w, train/loss=3.580\r",
+      "Epoch 0:   3%| | 413/14932 [00:47<27:33,  8.78it/s, v_num=ui8w, train/loss=2.140"
      ]
     },
     {
@@ -4919,8 +4894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 411/14932 [00:47<28:09,  8.59it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   3%| | 411/14932 [00:47<28:09,  8.59it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   3%| | 414/14932 [00:47<27:31,  8.79it/s, v_num=ui8w, train/loss=2.140\r",
+      "Epoch 0:   3%| | 414/14932 [00:47<27:31,  8.79it/s, v_num=ui8w, train/loss=2.420"
      ]
     },
     {
@@ -4928,8 +4903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 412/14932 [00:47<28:07,  8.60it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   3%| | 412/14932 [00:47<28:07,  8.60it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   3%| | 415/14932 [00:47<27:29,  8.80it/s, v_num=ui8w, train/loss=2.420\r",
+      "Epoch 0:   3%| | 415/14932 [00:47<27:29,  8.80it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -4937,8 +4912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 413/14932 [00:47<28:06,  8.61it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   3%| | 413/14932 [00:47<28:06,  8.61it/s, v_num=o30c, train/loss=2.480"
+      "Epoch 0:   3%| | 416/14932 [00:47<27:32,  8.79it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   3%| | 416/14932 [00:47<27:32,  8.79it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -4946,8 +4921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 414/14932 [00:48<28:04,  8.62it/s, v_num=o30c, train/loss=2.480\r",
-      "Epoch 0:   3%| | 414/14932 [00:48<28:04,  8.62it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   3%| | 417/14932 [00:47<27:30,  8.79it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   3%| | 417/14932 [00:47<27:30,  8.79it/s, v_num=ui8w, train/loss=2.140"
      ]
     },
     {
@@ -4955,8 +4930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 415/14932 [00:48<28:02,  8.63it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   3%| | 415/14932 [00:48<28:02,  8.63it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   3%| | 418/14932 [00:47<27:28,  8.80it/s, v_num=ui8w, train/loss=2.140\r",
+      "Epoch 0:   3%| | 418/14932 [00:47<27:28,  8.80it/s, v_num=ui8w, train/loss=3.890"
      ]
     },
     {
@@ -4964,8 +4939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 416/14932 [00:48<28:05,  8.61it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   3%| | 416/14932 [00:48<28:05,  8.61it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   3%| | 419/14932 [00:47<27:27,  8.81it/s, v_num=ui8w, train/loss=3.890\r",
+      "Epoch 0:   3%| | 419/14932 [00:47<27:27,  8.81it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -4973,8 +4948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 417/14932 [00:48<28:03,  8.62it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   3%| | 417/14932 [00:48<28:03,  8.62it/s, v_num=o30c, train/loss=4.530"
+      "Epoch 0:   3%| | 420/14932 [00:47<27:25,  8.82it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   3%| | 420/14932 [00:47<27:25,  8.82it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -4982,8 +4957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 418/14932 [00:48<28:01,  8.63it/s, v_num=o30c, train/loss=4.530\r",
-      "Epoch 0:   3%| | 418/14932 [00:48<28:01,  8.63it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   3%| | 421/14932 [00:47<27:24,  8.83it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   3%| | 421/14932 [00:47<27:24,  8.83it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -4991,8 +4966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 419/14932 [00:48<28:00,  8.64it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   3%| | 419/14932 [00:48<28:00,  8.64it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   3%| | 422/14932 [00:47<27:22,  8.83it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   3%| | 422/14932 [00:47<27:22,  8.83it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -5000,8 +4975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 420/14932 [00:48<27:58,  8.65it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   3%| | 420/14932 [00:48<27:58,  8.65it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   3%| | 423/14932 [00:47<27:21,  8.84it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   3%| | 423/14932 [00:47<27:21,  8.84it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -5009,8 +4984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 421/14932 [00:48<27:56,  8.65it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   3%| | 421/14932 [00:48<27:56,  8.65it/s, v_num=o30c, train/loss=3.380"
+      "Epoch 0:   3%| | 424/14932 [00:47<27:19,  8.85it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   3%| | 424/14932 [00:47<27:19,  8.85it/s, v_num=ui8w, train/loss=3.920"
      ]
     },
     {
@@ -5018,8 +4993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 422/14932 [00:48<27:55,  8.66it/s, v_num=o30c, train/loss=3.380\r",
-      "Epoch 0:   3%| | 422/14932 [00:48<27:55,  8.66it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   3%| | 425/14932 [00:47<27:17,  8.86it/s, v_num=ui8w, train/loss=3.920\r",
+      "Epoch 0:   3%| | 425/14932 [00:47<27:17,  8.86it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -5027,8 +5002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 423/14932 [00:48<27:53,  8.67it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   3%| | 423/14932 [00:48<27:53,  8.67it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   3%| | 426/14932 [00:48<27:16,  8.86it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   3%| | 426/14932 [00:48<27:16,  8.86it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -5036,8 +5011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 424/14932 [00:48<27:52,  8.68it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   3%| | 424/14932 [00:48<27:52,  8.68it/s, v_num=o30c, train/loss=2.250"
+      "Epoch 0:   3%| | 427/14932 [00:48<27:15,  8.87it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   3%| | 427/14932 [00:48<27:15,  8.87it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -5045,8 +5020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 425/14932 [00:48<27:50,  8.69it/s, v_num=o30c, train/loss=2.250\r",
-      "Epoch 0:   3%| | 425/14932 [00:48<27:50,  8.69it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   3%| | 428/14932 [00:48<27:13,  8.88it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   3%| | 428/14932 [00:48<27:13,  8.88it/s, v_num=ui8w, train/loss=2.110"
      ]
     },
     {
@@ -5054,8 +5029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 426/14932 [00:49<27:48,  8.69it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   3%| | 426/14932 [00:49<27:48,  8.69it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   3%| | 429/14932 [00:48<27:12,  8.89it/s, v_num=ui8w, train/loss=2.110\r",
+      "Epoch 0:   3%| | 429/14932 [00:48<27:12,  8.89it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -5063,8 +5038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 427/14932 [00:49<27:47,  8.70it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   3%| | 427/14932 [00:49<27:47,  8.70it/s, v_num=o30c, train/loss=1.480"
+      "Epoch 0:   3%| | 430/14932 [00:48<27:10,  8.89it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   3%| | 430/14932 [00:48<27:10,  8.89it/s, v_num=ui8w, train/loss=2.620"
      ]
     },
     {
@@ -5072,8 +5047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 428/14932 [00:49<27:45,  8.71it/s, v_num=o30c, train/loss=1.480\r",
-      "Epoch 0:   3%| | 428/14932 [00:49<27:45,  8.71it/s, v_num=o30c, train/loss=2.470"
+      "Epoch 0:   3%| | 431/14932 [00:48<27:09,  8.90it/s, v_num=ui8w, train/loss=2.620\r",
+      "Epoch 0:   3%| | 431/14932 [00:48<27:09,  8.90it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -5081,8 +5056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 429/14932 [00:49<27:44,  8.71it/s, v_num=o30c, train/loss=2.470\r",
-      "Epoch 0:   3%| | 429/14932 [00:49<27:44,  8.71it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   3%| | 432/14932 [00:48<27:07,  8.91it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   3%| | 432/14932 [00:48<27:07,  8.91it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -5090,8 +5065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 430/14932 [00:49<27:42,  8.72it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   3%| | 430/14932 [00:49<27:42,  8.72it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   3%| | 433/14932 [00:48<27:05,  8.92it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   3%| | 433/14932 [00:48<27:05,  8.92it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -5099,8 +5074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 431/14932 [00:49<27:41,  8.73it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   3%| | 431/14932 [00:49<27:41,  8.73it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   3%| | 434/14932 [00:48<27:04,  8.93it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   3%| | 434/14932 [00:48<27:04,  8.92it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -5108,8 +5083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 432/14932 [00:49<27:39,  8.74it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   3%| | 432/14932 [00:49<27:39,  8.74it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   3%| | 435/14932 [00:48<27:03,  8.93it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   3%| | 435/14932 [00:48<27:03,  8.93it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -5117,8 +5092,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 433/14932 [00:49<27:38,  8.74it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   3%| | 433/14932 [00:49<27:38,  8.74it/s, v_num=o30c, train/loss=2.440"
+      "Epoch 0:   3%| | 436/14932 [00:48<27:01,  8.94it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -5126,8 +5100,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 434/14932 [00:49<27:36,  8.75it/s, v_num=o30c, train/loss=2.440\r",
-      "Epoch 0:   3%| | 434/14932 [00:49<27:36,  8.75it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   3%| | 436/14932 [00:48<27:01,  8.94it/s, v_num=ui8w, train/loss=3.580"
      ]
     },
     {
@@ -5135,8 +5108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 435/14932 [00:49<27:35,  8.76it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   3%| | 435/14932 [00:49<27:35,  8.76it/s, v_num=o30c, train/loss=2.550"
+      "Epoch 0:   3%| | 437/14932 [00:48<27:00,  8.95it/s, v_num=ui8w, train/loss=3.580\r",
+      "Epoch 0:   3%| | 437/14932 [00:48<27:00,  8.95it/s, v_num=ui8w, train/loss=4.440"
      ]
     },
     {
@@ -5144,8 +5117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 436/14932 [00:49<27:33,  8.77it/s, v_num=o30c, train/loss=2.550\r",
-      "Epoch 0:   3%| | 436/14932 [00:49<27:33,  8.76it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   3%| | 438/14932 [00:48<26:58,  8.95it/s, v_num=ui8w, train/loss=4.440\r",
+      "Epoch 0:   3%| | 438/14932 [00:48<26:58,  8.95it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -5153,8 +5126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 437/14932 [00:49<27:32,  8.77it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   3%| | 437/14932 [00:49<27:32,  8.77it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   3%| | 439/14932 [00:48<26:57,  8.96it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   3%| | 439/14932 [00:48<26:57,  8.96it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -5162,8 +5135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 438/14932 [00:49<27:30,  8.78it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   3%| | 438/14932 [00:49<27:30,  8.78it/s, v_num=o30c, train/loss=2.590"
+      "Epoch 0:   3%| | 440/14932 [00:49<26:55,  8.97it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   3%| | 440/14932 [00:49<26:55,  8.97it/s, v_num=ui8w, train/loss=4.780"
      ]
     },
     {
@@ -5171,8 +5144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 439/14932 [00:49<27:29,  8.79it/s, v_num=o30c, train/loss=2.590\r",
-      "Epoch 0:   3%| | 439/14932 [00:49<27:29,  8.79it/s, v_num=o30c, train/loss=2.470"
+      "Epoch 0:   3%| | 441/14932 [00:49<26:54,  8.98it/s, v_num=ui8w, train/loss=4.780\r",
+      "Epoch 0:   3%| | 441/14932 [00:49<26:54,  8.98it/s, v_num=ui8w, train/loss=1.430"
      ]
     },
     {
@@ -5180,8 +5153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 440/14932 [00:50<27:27,  8.79it/s, v_num=o30c, train/loss=2.470\r",
-      "Epoch 0:   3%| | 440/14932 [00:50<27:27,  8.79it/s, v_num=o30c, train/loss=2.660"
+      "Epoch 0:   3%| | 442/14932 [00:49<26:52,  8.98it/s, v_num=ui8w, train/loss=1.430\r",
+      "Epoch 0:   3%| | 442/14932 [00:49<26:52,  8.98it/s, v_num=ui8w, train/loss=1.400"
      ]
     },
     {
@@ -5189,8 +5162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 441/14932 [00:50<27:26,  8.80it/s, v_num=o30c, train/loss=2.660\r",
-      "Epoch 0:   3%| | 441/14932 [00:50<27:26,  8.80it/s, v_num=o30c, train/loss=4.970"
+      "Epoch 0:   3%| | 443/14932 [00:49<26:51,  8.99it/s, v_num=ui8w, train/loss=1.400\r",
+      "Epoch 0:   3%| | 443/14932 [00:49<26:51,  8.99it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -5198,8 +5171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 442/14932 [00:50<27:25,  8.81it/s, v_num=o30c, train/loss=4.970\r",
-      "Epoch 0:   3%| | 442/14932 [00:50<27:25,  8.81it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   3%| | 444/14932 [00:49<26:50,  9.00it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   3%| | 444/14932 [00:49<26:50,  9.00it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -5207,8 +5180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 443/14932 [00:50<27:23,  8.82it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   3%| | 443/14932 [00:50<27:23,  8.82it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   3%| | 445/14932 [00:49<26:48,  9.01it/s, v_num=ui8w, train/loss=2.030\r",
+      "Epoch 0:   3%| | 445/14932 [00:49<26:48,  9.01it/s, v_num=ui8w, train/loss=2.750"
      ]
     },
     {
@@ -5216,8 +5189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 444/14932 [00:50<27:22,  8.82it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   3%| | 444/14932 [00:50<27:22,  8.82it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   3%| | 446/14932 [00:49<26:47,  9.01it/s, v_num=ui8w, train/loss=2.750\r",
+      "Epoch 0:   3%| | 446/14932 [00:49<26:47,  9.01it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -5225,8 +5198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 445/14932 [00:50<27:20,  8.83it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   3%| | 445/14932 [00:50<27:20,  8.83it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   3%| | 447/14932 [00:49<26:45,  9.02it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   3%| | 447/14932 [00:49<26:45,  9.02it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -5234,8 +5207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 446/14932 [00:50<27:19,  8.84it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   3%| | 446/14932 [00:50<27:19,  8.84it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   3%| | 448/14932 [00:49<26:48,  9.01it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   3%| | 448/14932 [00:49<26:48,  9.01it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -5243,8 +5216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 447/14932 [00:50<27:17,  8.84it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   3%| | 447/14932 [00:50<27:17,  8.84it/s, v_num=o30c, train/loss=2.860"
+      "Epoch 0:   3%| | 449/14932 [00:49<26:46,  9.02it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   3%| | 449/14932 [00:49<26:46,  9.02it/s, v_num=ui8w, train/loss=2.360"
      ]
     },
     {
@@ -5252,8 +5225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 448/14932 [00:50<27:20,  8.83it/s, v_num=o30c, train/loss=2.860\r",
-      "Epoch 0:   3%| | 448/14932 [00:50<27:20,  8.83it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   3%| | 450/14932 [00:49<26:44,  9.02it/s, v_num=ui8w, train/loss=2.360\r",
+      "Epoch 0:   3%| | 450/14932 [00:49<26:44,  9.02it/s, v_num=ui8w, train/loss=3.440"
      ]
     },
     {
@@ -5261,8 +5234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 449/14932 [00:50<27:18,  8.84it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   3%| | 449/14932 [00:50<27:18,  8.84it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   3%| | 451/14932 [00:49<26:43,  9.03it/s, v_num=ui8w, train/loss=3.440\r",
+      "Epoch 0:   3%| | 451/14932 [00:49<26:43,  9.03it/s, v_num=ui8w, train/loss=2.110"
      ]
     },
     {
@@ -5270,8 +5243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 450/14932 [00:50<27:17,  8.84it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   3%| | 450/14932 [00:50<27:17,  8.84it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   3%| | 452/14932 [00:50<26:42,  9.04it/s, v_num=ui8w, train/loss=2.110\r",
+      "Epoch 0:   3%| | 452/14932 [00:50<26:42,  9.04it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -5279,8 +5252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 451/14932 [00:50<27:16,  8.85it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   3%| | 451/14932 [00:50<27:16,  8.85it/s, v_num=o30c, train/loss=2.720"
+      "Epoch 0:   3%| | 453/14932 [00:50<26:40,  9.04it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   3%| | 453/14932 [00:50<26:40,  9.04it/s, v_num=ui8w, train/loss=2.230"
      ]
     },
     {
@@ -5288,8 +5261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 452/14932 [00:51<27:14,  8.86it/s, v_num=o30c, train/loss=2.720\r",
-      "Epoch 0:   3%| | 452/14932 [00:51<27:14,  8.86it/s, v_num=o30c, train/loss=2.250"
+      "Epoch 0:   3%| | 454/14932 [00:50<26:39,  9.05it/s, v_num=ui8w, train/loss=2.230\r",
+      "Epoch 0:   3%| | 454/14932 [00:50<26:39,  9.05it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -5297,8 +5270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 453/14932 [00:51<27:13,  8.86it/s, v_num=o30c, train/loss=2.250\r",
-      "Epoch 0:   3%| | 453/14932 [00:51<27:13,  8.86it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   3%| | 455/14932 [00:50<26:38,  9.06it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   3%| | 455/14932 [00:50<26:38,  9.06it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -5306,8 +5279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 454/14932 [00:51<27:12,  8.87it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   3%| | 454/14932 [00:51<27:12,  8.87it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   3%| | 456/14932 [00:50<26:36,  9.07it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   3%| | 456/14932 [00:50<26:36,  9.07it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -5315,8 +5288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 455/14932 [00:51<27:10,  8.88it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   3%| | 455/14932 [00:51<27:10,  8.88it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   3%| | 457/14932 [00:50<26:35,  9.07it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   3%| | 457/14932 [00:50<26:35,  9.07it/s, v_num=ui8w, train/loss=1.700"
      ]
     },
     {
@@ -5324,8 +5297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 456/14932 [00:51<27:09,  8.89it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   3%| | 456/14932 [00:51<27:09,  8.89it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   3%| | 458/14932 [00:50<26:34,  9.08it/s, v_num=ui8w, train/loss=1.700\r",
+      "Epoch 0:   3%| | 458/14932 [00:50<26:34,  9.08it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -5333,8 +5306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 457/14932 [00:51<27:07,  8.89it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   3%| | 457/14932 [00:51<27:07,  8.89it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   3%| | 459/14932 [00:50<26:32,  9.09it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   3%| | 459/14932 [00:50<26:32,  9.09it/s, v_num=ui8w, train/loss=1.370"
      ]
     },
     {
@@ -5342,8 +5315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 458/14932 [00:51<27:06,  8.90it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   3%| | 458/14932 [00:51<27:06,  8.90it/s, v_num=o30c, train/loss=2.840"
+      "Epoch 0:   3%| | 460/14932 [00:50<26:31,  9.09it/s, v_num=ui8w, train/loss=1.370\r",
+      "Epoch 0:   3%| | 460/14932 [00:50<26:31,  9.09it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -5351,8 +5324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 459/14932 [00:51<27:04,  8.91it/s, v_num=o30c, train/loss=2.840\r",
-      "Epoch 0:   3%| | 459/14932 [00:51<27:04,  8.91it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   3%| | 461/14932 [00:50<26:30,  9.10it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   3%| | 461/14932 [00:50<26:30,  9.10it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -5360,8 +5333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 460/14932 [00:51<27:03,  8.91it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   3%| | 460/14932 [00:51<27:03,  8.91it/s, v_num=o30c, train/loss=2.410"
+      "Epoch 0:   3%| | 462/14932 [00:50<26:28,  9.11it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   3%| | 462/14932 [00:50<26:28,  9.11it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -5369,8 +5342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 461/14932 [00:51<27:01,  8.92it/s, v_num=o30c, train/loss=2.410\r",
-      "Epoch 0:   3%| | 461/14932 [00:51<27:01,  8.92it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   3%| | 463/14932 [00:50<26:27,  9.11it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   3%| | 463/14932 [00:50<26:27,  9.11it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -5378,8 +5351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 462/14932 [00:51<27:00,  8.93it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   3%| | 462/14932 [00:51<27:00,  8.93it/s, v_num=o30c, train/loss=2.550"
+      "Epoch 0:   3%| | 464/14932 [00:50<26:25,  9.12it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   3%| | 464/14932 [00:50<26:25,  9.12it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -5387,8 +5360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 463/14932 [00:51<26:59,  8.94it/s, v_num=o30c, train/loss=2.550\r",
-      "Epoch 0:   3%| | 463/14932 [00:51<26:59,  8.94it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   3%| | 465/14932 [00:50<26:24,  9.13it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   3%| | 465/14932 [00:50<26:24,  9.13it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -5396,8 +5369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 464/14932 [00:51<26:57,  8.94it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   3%| | 464/14932 [00:51<26:57,  8.94it/s, v_num=o30c, train/loss=2.250"
+      "Epoch 0:   3%| | 466/14932 [00:51<26:23,  9.14it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   3%| | 466/14932 [00:51<26:23,  9.14it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -5405,8 +5378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 465/14932 [00:51<26:56,  8.95it/s, v_num=o30c, train/loss=2.250\r",
-      "Epoch 0:   3%| | 465/14932 [00:51<26:56,  8.95it/s, v_num=o30c, train/loss=2.270"
+      "Epoch 0:   3%| | 467/14932 [00:51<26:22,  9.14it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   3%| | 467/14932 [00:51<26:22,  9.14it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -5414,8 +5387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 466/14932 [00:52<26:54,  8.96it/s, v_num=o30c, train/loss=2.270\r",
-      "Epoch 0:   3%| | 466/14932 [00:52<26:54,  8.96it/s, v_num=o30c, train/loss=3.200"
+      "Epoch 0:   3%| | 468/14932 [00:51<26:20,  9.15it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   3%| | 468/14932 [00:51<26:20,  9.15it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -5423,8 +5396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 467/14932 [00:52<26:53,  8.96it/s, v_num=o30c, train/loss=3.200\r",
-      "Epoch 0:   3%| | 467/14932 [00:52<26:53,  8.96it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   3%| | 469/14932 [00:51<26:19,  9.16it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   3%| | 469/14932 [00:51<26:19,  9.16it/s, v_num=ui8w, train/loss=1.380"
      ]
     },
     {
@@ -5432,8 +5405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 468/14932 [00:52<26:52,  8.97it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   3%| | 468/14932 [00:52<26:52,  8.97it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   3%| | 470/14932 [00:51<26:18,  9.16it/s, v_num=ui8w, train/loss=1.380\r",
+      "Epoch 0:   3%| | 470/14932 [00:51<26:18,  9.16it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -5441,8 +5414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 469/14932 [00:52<26:51,  8.98it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   3%| | 469/14932 [00:52<26:51,  8.98it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   3%| | 471/14932 [00:51<26:17,  9.17it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   3%| | 471/14932 [00:51<26:17,  9.17it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -5450,8 +5423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 470/14932 [00:52<26:49,  8.98it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   3%| | 470/14932 [00:52<26:49,  8.98it/s, v_num=o30c, train/loss=2.810"
+      "Epoch 0:   3%| | 472/14932 [00:51<26:15,  9.18it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   3%| | 472/14932 [00:51<26:15,  9.18it/s, v_num=ui8w, train/loss=2.360"
      ]
     },
     {
@@ -5459,8 +5432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 471/14932 [00:52<26:48,  8.99it/s, v_num=o30c, train/loss=2.810\r",
-      "Epoch 0:   3%| | 471/14932 [00:52<26:48,  8.99it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   3%| | 473/14932 [00:51<26:14,  9.18it/s, v_num=ui8w, train/loss=2.360\r",
+      "Epoch 0:   3%| | 473/14932 [00:51<26:14,  9.18it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -5468,8 +5441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 472/14932 [00:52<26:47,  9.00it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   3%| | 472/14932 [00:52<26:47,  9.00it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   3%| | 474/14932 [00:51<26:12,  9.19it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   3%| | 474/14932 [00:51<26:12,  9.19it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -5477,8 +5450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 473/14932 [00:52<26:46,  9.00it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   3%| | 473/14932 [00:52<26:46,  9.00it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   3%| | 475/14932 [00:51<26:11,  9.20it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   3%| | 475/14932 [00:51<26:11,  9.20it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -5486,8 +5459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 474/14932 [00:52<26:44,  9.01it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   3%| | 474/14932 [00:52<26:44,  9.01it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   3%| | 476/14932 [00:51<26:10,  9.20it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   3%| | 476/14932 [00:51<26:10,  9.20it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -5495,8 +5468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 475/14932 [00:52<26:43,  9.02it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   3%| | 475/14932 [00:52<26:43,  9.02it/s, v_num=o30c, train/loss=2.060"
+      "Epoch 0:   3%| | 477/14932 [00:51<26:09,  9.21it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   3%| | 477/14932 [00:51<26:09,  9.21it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -5504,8 +5477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 476/14932 [00:52<26:42,  9.02it/s, v_num=o30c, train/loss=2.060\r",
-      "Epoch 0:   3%| | 476/14932 [00:52<26:42,  9.02it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   3%| | 478/14932 [00:51<26:08,  9.22it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   3%| | 478/14932 [00:51<26:08,  9.22it/s, v_num=ui8w, train/loss=4.280"
      ]
     },
     {
@@ -5513,8 +5486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 477/14932 [00:52<26:41,  9.03it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   3%| | 477/14932 [00:52<26:41,  9.03it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   3%| | 479/14932 [00:51<26:08,  9.21it/s, v_num=ui8w, train/loss=4.280\r",
+      "Epoch 0:   3%| | 479/14932 [00:51<26:08,  9.21it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -5522,8 +5495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 478/14932 [00:52<26:39,  9.03it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   3%| | 478/14932 [00:52<26:39,  9.03it/s, v_num=o30c, train/loss=1.810"
+      "Epoch 0:   3%| | 480/14932 [00:52<26:10,  9.20it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   3%| | 480/14932 [00:52<26:10,  9.20it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -5531,8 +5504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 479/14932 [00:52<26:38,  9.04it/s, v_num=o30c, train/loss=1.810\r",
-      "Epoch 0:   3%| | 479/14932 [00:52<26:38,  9.04it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   3%| | 481/14932 [00:52<26:09,  9.21it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   3%| | 481/14932 [00:52<26:09,  9.21it/s, v_num=ui8w, train/loss=2.310"
      ]
     },
     {
@@ -5540,7 +5513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 480/14932 [00:53<26:40,  9.03it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   3%| | 482/14932 [00:52<26:08,  9.22it/s, v_num=ui8w, train/loss=2.310\r",
+      "Epoch 0:   3%| | 482/14932 [00:52<26:08,  9.22it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -5548,7 +5522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 480/14932 [00:53<26:40,  9.03it/s, v_num=o30c, train/loss=1.940"
+      "Epoch 0:   3%| | 483/14932 [00:52<26:06,  9.22it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   3%| | 483/14932 [00:52<26:06,  9.22it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -5556,8 +5531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 481/14932 [00:53<26:39,  9.04it/s, v_num=o30c, train/loss=1.940\r",
-      "Epoch 0:   3%| | 481/14932 [00:53<26:39,  9.04it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   3%| | 484/14932 [00:52<26:05,  9.23it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   3%| | 484/14932 [00:52<26:05,  9.23it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -5565,8 +5540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 482/14932 [00:53<26:37,  9.04it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   3%| | 482/14932 [00:53<26:37,  9.04it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   3%| | 485/14932 [00:52<26:04,  9.24it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   3%| | 485/14932 [00:52<26:04,  9.24it/s, v_num=ui8w, train/loss=3.890"
      ]
     },
     {
@@ -5574,8 +5549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 483/14932 [00:53<26:36,  9.05it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   3%| | 483/14932 [00:53<26:36,  9.05it/s, v_num=o30c, train/loss=3.440"
+      "Epoch 0:   3%| | 486/14932 [00:52<26:02,  9.24it/s, v_num=ui8w, train/loss=3.890\r",
+      "Epoch 0:   3%| | 486/14932 [00:52<26:02,  9.24it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -5583,8 +5558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 484/14932 [00:53<26:35,  9.06it/s, v_num=o30c, train/loss=3.440\r",
-      "Epoch 0:   3%| | 484/14932 [00:53<26:35,  9.06it/s, v_num=o30c, train/loss=3.720"
+      "Epoch 0:   3%| | 487/14932 [00:52<26:01,  9.25it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   3%| | 487/14932 [00:52<26:01,  9.25it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -5592,8 +5567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 485/14932 [00:53<26:34,  9.06it/s, v_num=o30c, train/loss=3.720\r",
-      "Epoch 0:   3%| | 485/14932 [00:53<26:34,  9.06it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   3%| | 488/14932 [00:52<26:00,  9.26it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   3%| | 488/14932 [00:52<26:00,  9.26it/s, v_num=ui8w, train/loss=3.230"
      ]
     },
     {
@@ -5601,8 +5576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 486/14932 [00:53<26:36,  9.05it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   3%| | 486/14932 [00:53<26:36,  9.05it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   3%| | 489/14932 [00:52<25:59,  9.26it/s, v_num=ui8w, train/loss=3.230\r",
+      "Epoch 0:   3%| | 489/14932 [00:52<25:59,  9.26it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -5610,8 +5585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 487/14932 [00:53<26:37,  9.04it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   3%| | 487/14932 [00:53<26:37,  9.04it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   3%| | 490/14932 [00:52<25:57,  9.27it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   3%| | 490/14932 [00:52<25:57,  9.27it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -5619,8 +5594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 488/14932 [00:53<26:35,  9.05it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   3%| | 488/14932 [00:53<26:35,  9.05it/s, v_num=o30c, train/loss=3.110"
+      "Epoch 0:   3%| | 491/14932 [00:52<25:57,  9.27it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   3%| | 491/14932 [00:52<25:57,  9.27it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -5628,8 +5603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 489/14932 [00:53<26:34,  9.06it/s, v_num=o30c, train/loss=3.110\r",
-      "Epoch 0:   3%| | 489/14932 [00:54<26:34,  9.06it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   3%| | 492/14932 [00:53<25:56,  9.28it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   3%| | 492/14932 [00:53<25:56,  9.28it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -5637,8 +5612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 490/14932 [00:54<26:35,  9.05it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   3%| | 490/14932 [00:54<26:35,  9.05it/s, v_num=o30c, train/loss=4.410"
+      "Epoch 0:   3%| | 493/14932 [00:53<25:54,  9.29it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   3%| | 493/14932 [00:53<25:54,  9.29it/s, v_num=ui8w, train/loss=2.200"
      ]
     },
     {
@@ -5646,8 +5621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 491/14932 [00:54<26:34,  9.06it/s, v_num=o30c, train/loss=4.410\r",
-      "Epoch 0:   3%| | 491/14932 [00:54<26:34,  9.06it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   3%| | 494/14932 [00:53<25:53,  9.29it/s, v_num=ui8w, train/loss=2.200\r",
+      "Epoch 0:   3%| | 494/14932 [00:53<25:53,  9.29it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -5655,8 +5630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 492/14932 [00:54<26:33,  9.06it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   3%| | 492/14932 [00:54<26:33,  9.06it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   3%| | 495/14932 [00:53<25:52,  9.30it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   3%| | 495/14932 [00:53<25:52,  9.30it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -5664,8 +5639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 493/14932 [00:54<26:32,  9.07it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   3%| | 493/14932 [00:54<26:32,  9.07it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   3%| | 496/14932 [00:53<25:51,  9.31it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   3%| | 496/14932 [00:53<25:51,  9.31it/s, v_num=ui8w, train/loss=3.800"
      ]
     },
     {
@@ -5673,8 +5648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 494/14932 [00:54<26:31,  9.07it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   3%| | 494/14932 [00:54<26:31,  9.07it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   3%| | 497/14932 [00:53<25:49,  9.31it/s, v_num=ui8w, train/loss=3.800\r",
+      "Epoch 0:   3%| | 497/14932 [00:53<25:49,  9.31it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -5682,8 +5657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 495/14932 [00:54<26:30,  9.08it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   3%| | 495/14932 [00:54<26:30,  9.08it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   3%| | 498/14932 [00:53<25:48,  9.32it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   3%| | 498/14932 [00:53<25:48,  9.32it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -5691,8 +5666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 496/14932 [00:54<26:28,  9.09it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   3%| | 496/14932 [00:54<26:28,  9.09it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   3%| | 499/14932 [00:53<25:47,  9.33it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   3%| | 499/14932 [00:53<25:47,  9.33it/s, v_num=ui8w, train/loss=2.390"
      ]
     },
     {
@@ -5700,8 +5675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 497/14932 [00:54<26:27,  9.09it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   3%| | 497/14932 [00:54<26:27,  9.09it/s, v_num=o30c, train/loss=3.500"
+      "Epoch 0:   3%| | 500/14932 [00:53<25:46,  9.33it/s, v_num=ui8w, train/loss=2.390\r",
+      "Epoch 0:   3%| | 500/14932 [00:53<25:46,  9.33it/s, v_num=ui8w, train/loss=2.170"
      ]
     },
     {
@@ -5709,8 +5684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 498/14932 [00:54<26:26,  9.10it/s, v_num=o30c, train/loss=3.500\r",
-      "Epoch 0:   3%| | 498/14932 [00:54<26:26,  9.10it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   3%| | 501/14932 [00:53<25:45,  9.34it/s, v_num=ui8w, train/loss=2.170\r",
+      "Epoch 0:   3%| | 501/14932 [00:53<25:45,  9.34it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -5718,8 +5693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 499/14932 [00:54<26:25,  9.10it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   3%| | 499/14932 [00:54<26:25,  9.10it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   3%| | 502/14932 [00:53<25:43,  9.35it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   3%| | 502/14932 [00:53<25:43,  9.35it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -5727,8 +5702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 500/14932 [00:54<26:24,  9.11it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   3%| | 500/14932 [00:54<26:24,  9.11it/s, v_num=o30c, train/loss=1.750"
+      "Epoch 0:   3%| | 503/14932 [00:53<25:42,  9.35it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   3%| | 503/14932 [00:53<25:42,  9.35it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -5736,8 +5711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 501/14932 [00:55<26:24,  9.11it/s, v_num=o30c, train/loss=1.750\r",
-      "Epoch 0:   3%| | 501/14932 [00:55<26:24,  9.11it/s, v_num=o30c, train/loss=4.530"
+      "Epoch 0:   3%| | 504/14932 [00:53<25:41,  9.36it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   3%| | 504/14932 [00:53<25:41,  9.36it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -5745,8 +5720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 502/14932 [00:55<26:23,  9.11it/s, v_num=o30c, train/loss=4.530\r",
-      "Epoch 0:   3%| | 502/14932 [00:55<26:23,  9.11it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   3%| | 505/14932 [00:53<25:41,  9.36it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   3%| | 505/14932 [00:53<25:41,  9.36it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -5754,8 +5729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 503/14932 [00:55<26:22,  9.12it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   3%| | 503/14932 [00:55<26:22,  9.12it/s, v_num=o30c, train/loss=3.520"
+      "Epoch 0:   3%| | 506/14932 [00:54<25:40,  9.36it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   3%| | 506/14932 [00:54<25:40,  9.36it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -5763,8 +5738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 504/14932 [00:55<26:21,  9.13it/s, v_num=o30c, train/loss=3.520\r",
-      "Epoch 0:   3%| | 504/14932 [00:55<26:21,  9.13it/s, v_num=o30c, train/loss=2.670"
+      "Epoch 0:   3%| | 507/14932 [00:54<25:39,  9.37it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   3%| | 507/14932 [00:54<25:39,  9.37it/s, v_num=ui8w, train/loss=2.890"
      ]
     },
     {
@@ -5772,8 +5747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 505/14932 [00:55<26:19,  9.13it/s, v_num=o30c, train/loss=2.670\r",
-      "Epoch 0:   3%| | 505/14932 [00:55<26:19,  9.13it/s, v_num=o30c, train/loss=1.460"
+      "Epoch 0:   3%| | 508/14932 [00:54<25:38,  9.38it/s, v_num=ui8w, train/loss=2.890\r",
+      "Epoch 0:   3%| | 508/14932 [00:54<25:38,  9.38it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -5781,8 +5756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 506/14932 [00:55<26:18,  9.14it/s, v_num=o30c, train/loss=1.460\r",
-      "Epoch 0:   3%| | 506/14932 [00:55<26:18,  9.14it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   3%| | 509/14932 [00:54<25:37,  9.38it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   3%| | 509/14932 [00:54<25:37,  9.38it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -5790,8 +5765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 507/14932 [00:55<26:17,  9.14it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   3%| | 507/14932 [00:55<26:17,  9.14it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   3%| | 510/14932 [00:54<25:35,  9.39it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   3%| | 510/14932 [00:54<25:35,  9.39it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -5799,8 +5774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 508/14932 [00:55<26:16,  9.15it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   3%| | 508/14932 [00:55<26:16,  9.15it/s, v_num=o30c, train/loss=2.330"
+      "Epoch 0:   3%| | 511/14932 [00:54<25:34,  9.40it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   3%| | 511/14932 [00:54<25:34,  9.40it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -5808,8 +5783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 509/14932 [00:55<26:15,  9.16it/s, v_num=o30c, train/loss=2.330\r",
-      "Epoch 0:   3%| | 509/14932 [00:55<26:15,  9.16it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   3%| | 512/14932 [00:54<25:37,  9.38it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   3%| | 512/14932 [00:54<25:37,  9.38it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -5817,8 +5792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 510/14932 [00:55<26:13,  9.16it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   3%| | 510/14932 [00:55<26:13,  9.16it/s, v_num=o30c, train/loss=2.270"
+      "Epoch 0:   3%| | 513/14932 [00:54<25:35,  9.39it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   3%| | 513/14932 [00:54<25:35,  9.39it/s, v_num=ui8w, train/loss=4.560"
      ]
     },
     {
@@ -5826,8 +5801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 511/14932 [00:55<26:12,  9.17it/s, v_num=o30c, train/loss=2.270\r",
-      "Epoch 0:   3%| | 511/14932 [00:55<26:12,  9.17it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   3%| | 514/14932 [00:54<25:34,  9.39it/s, v_num=ui8w, train/loss=4.560\r",
+      "Epoch 0:   3%| | 514/14932 [00:54<25:34,  9.39it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -5835,8 +5810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 512/14932 [00:55<26:15,  9.16it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   3%| | 512/14932 [00:55<26:15,  9.16it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   3%| | 515/14932 [00:54<25:33,  9.40it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   3%| | 515/14932 [00:54<25:33,  9.40it/s, v_num=ui8w, train/loss=1.920"
      ]
     },
     {
@@ -5844,8 +5819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 513/14932 [00:55<26:13,  9.16it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   3%| | 513/14932 [00:55<26:13,  9.16it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   3%| | 516/14932 [00:54<25:32,  9.41it/s, v_num=ui8w, train/loss=1.920\r",
+      "Epoch 0:   3%| | 516/14932 [00:54<25:32,  9.41it/s, v_num=ui8w, train/loss=2.160"
      ]
     },
     {
@@ -5853,8 +5828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 514/14932 [00:56<26:12,  9.17it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   3%| | 514/14932 [00:56<26:12,  9.17it/s, v_num=o30c, train/loss=3.840"
+      "Epoch 0:   3%| | 517/14932 [00:54<25:31,  9.41it/s, v_num=ui8w, train/loss=2.160\r",
+      "Epoch 0:   3%| | 517/14932 [00:54<25:31,  9.41it/s, v_num=ui8w, train/loss=2.270"
      ]
     },
     {
@@ -5862,8 +5837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 515/14932 [00:56<26:11,  9.17it/s, v_num=o30c, train/loss=3.840\r",
-      "Epoch 0:   3%| | 515/14932 [00:56<26:11,  9.17it/s, v_num=o30c, train/loss=3.520"
+      "Epoch 0:   3%| | 518/14932 [00:54<25:29,  9.42it/s, v_num=ui8w, train/loss=2.270\r",
+      "Epoch 0:   3%| | 518/14932 [00:54<25:29,  9.42it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -5871,8 +5846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 516/14932 [00:56<26:10,  9.18it/s, v_num=o30c, train/loss=3.520\r",
-      "Epoch 0:   3%| | 516/14932 [00:56<26:10,  9.18it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   3%| | 519/14932 [00:55<25:28,  9.43it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   3%| | 519/14932 [00:55<25:28,  9.43it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -5880,8 +5855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 517/14932 [00:56<26:09,  9.19it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   3%| | 517/14932 [00:56<26:09,  9.19it/s, v_num=o30c, train/loss=1.800"
+      "Epoch 0:   3%| | 520/14932 [00:55<25:27,  9.43it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   3%| | 520/14932 [00:55<25:27,  9.43it/s, v_num=ui8w, train/loss=2.140"
      ]
     },
     {
@@ -5889,8 +5864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 518/14932 [00:56<26:08,  9.19it/s, v_num=o30c, train/loss=1.800\r",
-      "Epoch 0:   3%| | 518/14932 [00:56<26:08,  9.19it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   3%| | 521/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=2.140\r",
+      "Epoch 0:   3%| | 521/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -5898,8 +5873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 519/14932 [00:56<26:06,  9.20it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   3%| | 519/14932 [00:56<26:06,  9.20it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   3%| | 522/14932 [00:55<25:27,  9.43it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   3%| | 522/14932 [00:55<25:27,  9.43it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -5907,8 +5882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 520/14932 [00:56<26:05,  9.20it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   3%| | 520/14932 [00:56<26:05,  9.20it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   4%| | 523/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   4%| | 523/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -5916,8 +5891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 521/14932 [00:56<26:04,  9.21it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   3%| | 521/14932 [00:56<26:04,  9.21it/s, v_num=o30c, train/loss=3.800"
+      "Epoch 0:   4%| | 524/14932 [00:55<25:25,  9.45it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   4%| | 524/14932 [00:55<25:25,  9.45it/s, v_num=ui8w, train/loss=2.360"
      ]
     },
     {
@@ -5925,8 +5900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   3%| | 522/14932 [00:56<26:03,  9.22it/s, v_num=o30c, train/loss=3.800\r",
-      "Epoch 0:   3%| | 522/14932 [00:56<26:03,  9.22it/s, v_num=o30c, train/loss=1.240"
+      "Epoch 0:   4%| | 525/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=2.360\r",
+      "Epoch 0:   4%| | 525/14932 [00:55<25:26,  9.44it/s, v_num=ui8w, train/loss=2.860"
      ]
     },
     {
@@ -5934,8 +5909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 523/14932 [00:56<26:02,  9.22it/s, v_num=o30c, train/loss=1.240\r",
-      "Epoch 0:   4%| | 523/14932 [00:56<26:02,  9.22it/s, v_num=o30c, train/loss=2.590"
+      "Epoch 0:   4%| | 526/14932 [00:55<25:25,  9.45it/s, v_num=ui8w, train/loss=2.860\r",
+      "Epoch 0:   4%| | 526/14932 [00:55<25:25,  9.45it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -5943,8 +5918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 524/14932 [00:56<26:01,  9.23it/s, v_num=o30c, train/loss=2.590\r",
-      "Epoch 0:   4%| | 524/14932 [00:56<26:01,  9.23it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   4%| | 527/14932 [00:55<25:24,  9.45it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   4%| | 527/14932 [00:55<25:24,  9.45it/s, v_num=ui8w, train/loss=4.780"
      ]
     },
     {
@@ -5952,8 +5927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 525/14932 [00:57<26:05,  9.20it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   4%| | 525/14932 [00:57<26:05,  9.20it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   4%| | 528/14932 [00:55<25:22,  9.46it/s, v_num=ui8w, train/loss=4.780\r",
+      "Epoch 0:   4%| | 528/14932 [00:55<25:23,  9.46it/s, v_num=ui8w, train/loss=1.520"
      ]
     },
     {
@@ -5961,8 +5936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 526/14932 [00:57<26:04,  9.21it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   4%| | 526/14932 [00:57<26:04,  9.21it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   4%| | 529/14932 [00:55<25:21,  9.46it/s, v_num=ui8w, train/loss=1.520\r",
+      "Epoch 0:   4%| | 529/14932 [00:55<25:21,  9.46it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -5970,8 +5945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 527/14932 [00:57<26:03,  9.22it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   4%| | 527/14932 [00:57<26:03,  9.22it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   4%| | 530/14932 [00:55<25:20,  9.47it/s, v_num=ui8w, train/loss=3.470\r",
+      "Epoch 0:   4%| | 530/14932 [00:55<25:20,  9.47it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -5979,8 +5954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 528/14932 [00:57<26:01,  9.22it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   4%| | 528/14932 [00:57<26:01,  9.22it/s, v_num=o30c, train/loss=2.970"
+      "Epoch 0:   4%| | 531/14932 [00:56<25:19,  9.48it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   4%| | 531/14932 [00:56<25:19,  9.48it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -5988,8 +5963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 529/14932 [00:57<26:00,  9.23it/s, v_num=o30c, train/loss=2.970\r",
-      "Epoch 0:   4%| | 529/14932 [00:57<26:00,  9.23it/s, v_num=o30c, train/loss=2.780"
+      "Epoch 0:   4%| | 532/14932 [00:56<25:18,  9.48it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   4%| | 532/14932 [00:56<25:18,  9.48it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -5997,8 +5972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 530/14932 [00:57<25:59,  9.24it/s, v_num=o30c, train/loss=2.780\r",
-      "Epoch 0:   4%| | 530/14932 [00:57<25:59,  9.24it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   4%| | 533/14932 [00:56<25:17,  9.49it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   4%| | 533/14932 [00:56<25:17,  9.49it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -6006,8 +5981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 531/14932 [00:57<25:58,  9.24it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   4%| | 531/14932 [00:57<25:58,  9.24it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   4%| | 534/14932 [00:56<25:16,  9.49it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   4%| | 534/14932 [00:56<25:16,  9.49it/s, v_num=ui8w, train/loss=2.580"
      ]
     },
     {
@@ -6015,8 +5990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 532/14932 [00:57<25:56,  9.25it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   4%| | 532/14932 [00:57<25:56,  9.25it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   4%| | 535/14932 [00:56<25:15,  9.50it/s, v_num=ui8w, train/loss=2.580\r",
+      "Epoch 0:   4%| | 535/14932 [00:56<25:15,  9.50it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -6024,8 +5999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 533/14932 [00:57<25:55,  9.25it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   4%| | 533/14932 [00:57<25:55,  9.25it/s, v_num=o30c, train/loss=2.890"
+      "Epoch 0:   4%| | 536/14932 [00:56<25:14,  9.51it/s, v_num=ui8w, train/loss=2.030\r",
+      "Epoch 0:   4%| | 536/14932 [00:56<25:14,  9.51it/s, v_num=ui8w, train/loss=2.620"
      ]
     },
     {
@@ -6033,8 +6008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 534/14932 [00:57<25:54,  9.26it/s, v_num=o30c, train/loss=2.890\r",
-      "Epoch 0:   4%| | 534/14932 [00:57<25:54,  9.26it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   4%| | 537/14932 [00:56<25:13,  9.51it/s, v_num=ui8w, train/loss=2.620\r",
+      "Epoch 0:   4%| | 537/14932 [00:56<25:13,  9.51it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -6042,8 +6017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 535/14932 [00:57<25:53,  9.27it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   4%| | 535/14932 [00:57<25:53,  9.27it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   4%| | 538/14932 [00:56<25:12,  9.52it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   4%| | 538/14932 [00:56<25:12,  9.52it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -6051,8 +6026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 536/14932 [00:57<25:52,  9.27it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   4%| | 536/14932 [00:57<25:52,  9.27it/s, v_num=o30c, train/loss=1.140"
+      "Epoch 0:   4%| | 539/14932 [00:56<25:11,  9.52it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   4%| | 539/14932 [00:56<25:11,  9.52it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -6060,8 +6035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 537/14932 [00:57<25:51,  9.28it/s, v_num=o30c, train/loss=1.140\r",
-      "Epoch 0:   4%| | 537/14932 [00:57<25:51,  9.28it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   4%| | 540/14932 [00:56<25:10,  9.53it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   4%| | 540/14932 [00:56<25:10,  9.53it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -6069,8 +6044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 538/14932 [00:57<25:50,  9.28it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   4%| | 538/14932 [00:57<25:50,  9.28it/s, v_num=o30c, train/loss=2.360"
+      "Epoch 0:   4%| | 541/14932 [00:56<25:09,  9.53it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   4%| | 541/14932 [00:56<25:09,  9.53it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -6078,8 +6053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 539/14932 [00:58<25:51,  9.28it/s, v_num=o30c, train/loss=2.360\r",
-      "Epoch 0:   4%| | 539/14932 [00:58<25:51,  9.28it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   4%| | 542/14932 [00:56<25:08,  9.54it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   4%| | 542/14932 [00:56<25:08,  9.54it/s, v_num=ui8w, train/loss=2.300"
      ]
     },
     {
@@ -6087,8 +6062,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 540/14932 [00:58<25:50,  9.28it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   4%| | 540/14932 [00:58<25:50,  9.28it/s, v_num=o30c, train/loss=2.660"
+      "Epoch 0:   4%| | 543/14932 [00:56<25:07,  9.55it/s, v_num=ui8w, train/loss=2.300"
      ]
     },
     {
@@ -6096,8 +6070,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 541/14932 [00:58<25:49,  9.29it/s, v_num=o30c, train/loss=2.660\r",
-      "Epoch 0:   4%| | 541/14932 [00:58<25:49,  9.29it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   4%| | 543/14932 [00:56<25:07,  9.55it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -6105,8 +6078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 542/14932 [00:58<25:48,  9.30it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   4%| | 542/14932 [00:58<25:48,  9.30it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   4%| | 544/14932 [00:57<25:09,  9.53it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   4%| | 544/14932 [00:57<25:09,  9.53it/s, v_num=ui8w, train/loss=2.640"
      ]
     },
     {
@@ -6114,8 +6087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 543/14932 [00:58<25:47,  9.30it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   4%| | 543/14932 [00:58<25:47,  9.30it/s, v_num=o30c, train/loss=2.470"
+      "Epoch 0:   4%| | 545/14932 [00:57<25:08,  9.54it/s, v_num=ui8w, train/loss=2.640\r",
+      "Epoch 0:   4%| | 545/14932 [00:57<25:08,  9.54it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -6123,8 +6096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 544/14932 [00:58<25:49,  9.29it/s, v_num=o30c, train/loss=2.470\r",
-      "Epoch 0:   4%| | 544/14932 [00:58<25:49,  9.29it/s, v_num=o30c, train/loss=3.500"
+      "Epoch 0:   4%| | 546/14932 [00:57<25:07,  9.55it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   4%| | 546/14932 [00:57<25:07,  9.55it/s, v_num=ui8w, train/loss=2.120"
      ]
     },
     {
@@ -6132,8 +6105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 545/14932 [00:58<25:48,  9.29it/s, v_num=o30c, train/loss=3.500\r",
-      "Epoch 0:   4%| | 545/14932 [00:58<25:48,  9.29it/s, v_num=o30c, train/loss=3.160"
+      "Epoch 0:   4%| | 547/14932 [00:57<25:06,  9.55it/s, v_num=ui8w, train/loss=2.120\r",
+      "Epoch 0:   4%| | 547/14932 [00:57<25:06,  9.55it/s, v_num=ui8w, train/loss=4.560"
      ]
     },
     {
@@ -6141,8 +6114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 546/14932 [00:58<25:47,  9.30it/s, v_num=o30c, train/loss=3.160\r",
-      "Epoch 0:   4%| | 546/14932 [00:58<25:47,  9.30it/s, v_num=o30c, train/loss=2.420"
+      "Epoch 0:   4%| | 548/14932 [00:57<25:05,  9.56it/s, v_num=ui8w, train/loss=4.560\r",
+      "Epoch 0:   4%| | 548/14932 [00:57<25:05,  9.56it/s, v_num=ui8w, train/loss=2.120"
      ]
     },
     {
@@ -6150,8 +6123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 547/14932 [00:58<25:46,  9.30it/s, v_num=o30c, train/loss=2.420\r",
-      "Epoch 0:   4%| | 547/14932 [00:58<25:46,  9.30it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   4%| | 549/14932 [00:57<25:05,  9.55it/s, v_num=ui8w, train/loss=2.120\r",
+      "Epoch 0:   4%| | 549/14932 [00:57<25:05,  9.55it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -6159,8 +6132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 548/14932 [00:58<25:45,  9.31it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   4%| | 548/14932 [00:58<25:45,  9.31it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   4%| | 550/14932 [00:57<25:04,  9.56it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   4%| | 550/14932 [00:57<25:04,  9.56it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -6168,8 +6141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 549/14932 [00:58<25:44,  9.31it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   4%| | 549/14932 [00:58<25:44,  9.31it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   4%| | 551/14932 [00:57<25:03,  9.56it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   4%| | 551/14932 [00:57<25:03,  9.56it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -6177,8 +6150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 550/14932 [00:59<25:43,  9.32it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   4%| | 550/14932 [00:59<25:43,  9.32it/s, v_num=o30c, train/loss=3.280"
+      "Epoch 0:   4%| | 552/14932 [00:57<25:02,  9.57it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   4%| | 552/14932 [00:57<25:02,  9.57it/s, v_num=ui8w, train/loss=2.580"
      ]
     },
     {
@@ -6186,8 +6159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 551/14932 [00:59<25:43,  9.31it/s, v_num=o30c, train/loss=3.280\r",
-      "Epoch 0:   4%| | 551/14932 [00:59<25:43,  9.31it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   4%| | 553/14932 [00:57<25:01,  9.58it/s, v_num=ui8w, train/loss=2.580\r",
+      "Epoch 0:   4%| | 553/14932 [00:57<25:01,  9.58it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -6195,8 +6168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 552/14932 [00:59<25:42,  9.32it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   4%| | 552/14932 [00:59<25:42,  9.32it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   4%| | 554/14932 [00:57<25:00,  9.58it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   4%| | 554/14932 [00:57<25:00,  9.58it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -6204,8 +6177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 553/14932 [00:59<25:41,  9.33it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   4%| | 553/14932 [00:59<25:41,  9.33it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   4%| | 555/14932 [00:57<24:59,  9.59it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   4%| | 555/14932 [00:57<24:59,  9.59it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -6213,8 +6186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 554/14932 [00:59<25:40,  9.33it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   4%| | 554/14932 [00:59<25:40,  9.33it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   4%| | 556/14932 [00:58<25:00,  9.58it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   4%| | 556/14932 [00:58<25:00,  9.58it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -6222,8 +6195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 555/14932 [00:59<25:39,  9.34it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   4%| | 555/14932 [00:59<25:39,  9.34it/s, v_num=o30c, train/loss=3.110"
+      "Epoch 0:   4%| | 557/14932 [00:58<24:59,  9.59it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   4%| | 557/14932 [00:58<24:59,  9.59it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -6231,8 +6204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 556/14932 [00:59<25:39,  9.34it/s, v_num=o30c, train/loss=3.110\r",
-      "Epoch 0:   4%| | 556/14932 [00:59<25:39,  9.34it/s, v_num=o30c, train/loss=4.590"
+      "Epoch 0:   4%| | 558/14932 [00:58<24:58,  9.59it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   4%| | 558/14932 [00:58<24:58,  9.59it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -6240,8 +6213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 557/14932 [00:59<25:38,  9.35it/s, v_num=o30c, train/loss=4.590\r",
-      "Epoch 0:   4%| | 557/14932 [00:59<25:38,  9.35it/s, v_num=o30c, train/loss=4.410"
+      "Epoch 0:   4%| | 559/14932 [00:58<24:57,  9.60it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   4%| | 559/14932 [00:58<24:57,  9.60it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -6249,8 +6222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 558/14932 [00:59<25:37,  9.35it/s, v_num=o30c, train/loss=4.410\r",
-      "Epoch 0:   4%| | 558/14932 [00:59<25:37,  9.35it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   4%| | 560/14932 [00:58<24:56,  9.60it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   4%| | 560/14932 [00:58<24:56,  9.60it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -6258,8 +6231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 559/14932 [00:59<25:36,  9.36it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   4%| | 559/14932 [00:59<25:36,  9.36it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   4%| | 561/14932 [00:58<25:02,  9.57it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   4%| | 561/14932 [00:58<25:02,  9.57it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -6267,8 +6240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 560/14932 [00:59<25:35,  9.36it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   4%| | 560/14932 [00:59<25:35,  9.36it/s, v_num=o30c, train/loss=1.360"
+      "Epoch 0:   4%| | 562/14932 [00:58<25:01,  9.57it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   4%| | 562/14932 [00:58<25:01,  9.57it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -6276,8 +6249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 561/14932 [00:59<25:33,  9.37it/s, v_num=o30c, train/loss=1.360\r",
-      "Epoch 0:   4%| | 561/14932 [00:59<25:33,  9.37it/s, v_num=o30c, train/loss=1.990"
+      "Epoch 0:   4%| | 563/14932 [00:58<25:00,  9.58it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   4%| | 563/14932 [00:58<25:00,  9.58it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -6285,8 +6258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 562/14932 [00:59<25:32,  9.37it/s, v_num=o30c, train/loss=1.990\r",
-      "Epoch 0:   4%| | 562/14932 [00:59<25:32,  9.37it/s, v_num=o30c, train/loss=2.310"
+      "Epoch 0:   4%| | 564/14932 [00:58<24:59,  9.58it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   4%| | 564/14932 [00:58<24:59,  9.58it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -6294,8 +6267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 563/14932 [01:00<25:31,  9.38it/s, v_num=o30c, train/loss=2.310\r",
-      "Epoch 0:   4%| | 563/14932 [01:00<25:31,  9.38it/s, v_num=o30c, train/loss=2.330"
+      "Epoch 0:   4%| | 565/14932 [00:58<24:58,  9.59it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   4%| | 565/14932 [00:58<24:58,  9.59it/s, v_num=ui8w, train/loss=2.120"
      ]
     },
     {
@@ -6303,8 +6276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 564/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=2.330\r",
-      "Epoch 0:   4%| | 564/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   4%| | 566/14932 [00:58<24:57,  9.60it/s, v_num=ui8w, train/loss=2.120\r",
+      "Epoch 0:   4%| | 566/14932 [00:58<24:57,  9.60it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -6312,8 +6285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 565/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   4%| | 565/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=2.620"
+      "Epoch 0:   4%| | 567/14932 [00:59<24:56,  9.60it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   4%| | 567/14932 [00:59<24:56,  9.60it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -6321,8 +6294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 566/14932 [01:00<25:29,  9.39it/s, v_num=o30c, train/loss=2.620\r",
-      "Epoch 0:   4%| | 566/14932 [01:00<25:29,  9.39it/s, v_num=o30c, train/loss=3.440"
+      "Epoch 0:   4%| | 568/14932 [00:59<24:54,  9.61it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   4%| | 568/14932 [00:59<24:54,  9.61it/s, v_num=ui8w, train/loss=4.280"
      ]
     },
     {
@@ -6330,8 +6303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 567/14932 [01:00<25:28,  9.40it/s, v_num=o30c, train/loss=3.440\r",
-      "Epoch 0:   4%| | 567/14932 [01:00<25:28,  9.40it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   4%| | 569/14932 [00:59<24:53,  9.61it/s, v_num=ui8w, train/loss=4.280\r",
+      "Epoch 0:   4%| | 569/14932 [00:59<24:53,  9.61it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -6339,8 +6312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 568/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   4%| | 568/14932 [01:00<25:30,  9.39it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   4%| | 570/14932 [00:59<24:52,  9.62it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   4%| | 570/14932 [00:59<24:52,  9.62it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -6348,8 +6321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 569/14932 [01:00<25:29,  9.39it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   4%| | 569/14932 [01:00<25:29,  9.39it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   4%| | 571/14932 [00:59<24:52,  9.63it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   4%| | 571/14932 [00:59<24:52,  9.63it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -6357,8 +6330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 570/14932 [01:00<25:28,  9.40it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   4%| | 570/14932 [01:00<25:28,  9.40it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   4%| | 572/14932 [00:59<24:51,  9.63it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   4%| | 572/14932 [00:59<24:51,  9.63it/s, v_num=ui8w, train/loss=3.080"
      ]
     },
     {
@@ -6366,8 +6339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 571/14932 [01:00<25:32,  9.37it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   4%| | 571/14932 [01:00<25:32,  9.37it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   4%| | 573/14932 [00:59<24:50,  9.64it/s, v_num=ui8w, train/loss=3.080\r",
+      "Epoch 0:   4%| | 573/14932 [00:59<24:50,  9.64it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -6375,8 +6348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 572/14932 [01:01<25:31,  9.37it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   4%| | 572/14932 [01:01<25:31,  9.37it/s, v_num=o30c, train/loss=1.440"
+      "Epoch 0:   4%| | 574/14932 [00:59<24:49,  9.64it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   4%| | 574/14932 [00:59<24:49,  9.64it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -6384,8 +6357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 573/14932 [01:01<25:30,  9.38it/s, v_num=o30c, train/loss=1.440\r",
-      "Epoch 0:   4%| | 573/14932 [01:01<25:30,  9.38it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   4%| | 575/14932 [00:59<24:48,  9.65it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   4%| | 575/14932 [00:59<24:48,  9.65it/s, v_num=ui8w, train/loss=2.020"
      ]
     },
     {
@@ -6393,8 +6366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 574/14932 [01:01<25:29,  9.38it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   4%| | 574/14932 [01:01<25:29,  9.38it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   4%| | 576/14932 [00:59<24:50,  9.63it/s, v_num=ui8w, train/loss=2.020\r",
+      "Epoch 0:   4%| | 576/14932 [00:59<24:50,  9.63it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -6402,8 +6375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 575/14932 [01:01<25:29,  9.39it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   4%| | 575/14932 [01:01<25:29,  9.39it/s, v_num=o30c, train/loss=4.720"
+      "Epoch 0:   4%| | 577/14932 [00:59<24:49,  9.64it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   4%| | 577/14932 [00:59<24:49,  9.64it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -6411,8 +6384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 576/14932 [01:01<25:30,  9.38it/s, v_num=o30c, train/loss=4.720\r",
-      "Epoch 0:   4%| | 576/14932 [01:01<25:30,  9.38it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   4%| | 578/14932 [00:59<24:48,  9.64it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   4%| | 578/14932 [00:59<24:48,  9.64it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -6420,8 +6393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 577/14932 [01:01<25:29,  9.38it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   4%| | 577/14932 [01:01<25:29,  9.38it/s, v_num=o30c, train/loss=3.980"
+      "Epoch 0:   4%| | 579/14932 [01:00<24:47,  9.65it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   4%| | 579/14932 [01:00<24:47,  9.65it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -6429,8 +6402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 578/14932 [01:01<25:28,  9.39it/s, v_num=o30c, train/loss=3.980\r",
-      "Epoch 0:   4%| | 578/14932 [01:01<25:28,  9.39it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   4%| | 580/14932 [01:00<24:46,  9.65it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   4%| | 580/14932 [01:00<24:46,  9.65it/s, v_num=ui8w, train/loss=3.120"
      ]
     },
     {
@@ -6438,8 +6411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 579/14932 [01:01<25:29,  9.39it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   4%| | 579/14932 [01:01<25:29,  9.39it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   4%| | 581/14932 [01:00<24:45,  9.66it/s, v_num=ui8w, train/loss=3.120\r",
+      "Epoch 0:   4%| | 581/14932 [01:00<24:45,  9.66it/s, v_num=ui8w, train/loss=4.940"
      ]
     },
     {
@@ -6447,8 +6420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 580/14932 [01:01<25:28,  9.39it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   4%| | 580/14932 [01:01<25:28,  9.39it/s, v_num=o30c, train/loss=5.000"
+      "Epoch 0:   4%| | 582/14932 [01:00<24:45,  9.66it/s, v_num=ui8w, train/loss=4.940\r",
+      "Epoch 0:   4%| | 582/14932 [01:00<24:45,  9.66it/s, v_num=ui8w, train/loss=1.610"
      ]
     },
     {
@@ -6456,8 +6429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 581/14932 [01:01<25:27,  9.40it/s, v_num=o30c, train/loss=5.000\r",
-      "Epoch 0:   4%| | 581/14932 [01:01<25:27,  9.40it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   4%| | 583/14932 [01:00<24:44,  9.67it/s, v_num=ui8w, train/loss=1.610\r",
+      "Epoch 0:   4%| | 583/14932 [01:00<24:44,  9.67it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -6465,8 +6438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 582/14932 [01:01<25:26,  9.40it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   4%| | 582/14932 [01:01<25:26,  9.40it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   4%| | 584/14932 [01:00<24:43,  9.67it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   4%| | 584/14932 [01:00<24:43,  9.67it/s, v_num=ui8w, train/loss=2.050"
      ]
     },
     {
@@ -6474,8 +6447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 583/14932 [01:02<25:27,  9.40it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   4%| | 583/14932 [01:02<25:27,  9.40it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   4%| | 585/14932 [01:00<24:42,  9.68it/s, v_num=ui8w, train/loss=2.050\r",
+      "Epoch 0:   4%| | 585/14932 [01:00<24:42,  9.68it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -6483,8 +6456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 584/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   4%| | 584/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=4.750"
+      "Epoch 0:   4%| | 586/14932 [01:00<24:41,  9.68it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   4%| | 586/14932 [01:00<24:41,  9.68it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -6492,8 +6465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 585/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=4.750\r",
-      "Epoch 0:   4%| | 585/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   4%| | 587/14932 [01:00<24:41,  9.69it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   4%| | 587/14932 [01:00<24:41,  9.69it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -6501,8 +6474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 586/14932 [01:02<25:27,  9.39it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   4%| | 586/14932 [01:02<25:27,  9.39it/s, v_num=o30c, train/loss=4.880"
+      "Epoch 0:   4%| | 588/14932 [01:00<24:40,  9.69it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   4%| | 588/14932 [01:00<24:40,  9.69it/s, v_num=ui8w, train/loss=3.800"
      ]
     },
     {
@@ -6510,8 +6483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 587/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=4.880\r",
-      "Epoch 0:   4%| | 587/14932 [01:02<25:26,  9.40it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   4%| | 589/14932 [01:00<24:39,  9.70it/s, v_num=ui8w, train/loss=3.800\r",
+      "Epoch 0:   4%| | 589/14932 [01:00<24:39,  9.70it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -6519,8 +6492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 588/14932 [01:02<25:25,  9.40it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   4%| | 588/14932 [01:02<25:25,  9.40it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   4%| | 590/14932 [01:00<24:38,  9.70it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   4%| | 590/14932 [01:00<24:38,  9.70it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -6528,8 +6501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 589/14932 [01:02<25:24,  9.41it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   4%| | 589/14932 [01:02<25:24,  9.41it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   4%| | 591/14932 [01:00<24:37,  9.71it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   4%| | 591/14932 [01:00<24:37,  9.71it/s, v_num=ui8w, train/loss=1.600"
      ]
     },
     {
@@ -6537,8 +6510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 590/14932 [01:02<25:23,  9.41it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   4%| | 590/14932 [01:02<25:23,  9.41it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   4%| | 592/14932 [01:00<24:36,  9.71it/s, v_num=ui8w, train/loss=1.600\r",
+      "Epoch 0:   4%| | 592/14932 [01:00<24:36,  9.71it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -6546,8 +6519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 591/14932 [01:02<25:22,  9.42it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   4%| | 591/14932 [01:02<25:22,  9.42it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   4%| | 593/14932 [01:01<24:35,  9.72it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   4%| | 593/14932 [01:01<24:35,  9.72it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -6555,8 +6528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 592/14932 [01:02<25:21,  9.42it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   4%| | 592/14932 [01:02<25:21,  9.42it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   4%| | 594/14932 [01:01<24:34,  9.72it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   4%| | 594/14932 [01:01<24:34,  9.72it/s, v_num=ui8w, train/loss=3.120"
      ]
     },
     {
@@ -6564,7 +6537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 593/14932 [01:02<25:20,  9.43it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   4%| | 595/14932 [01:01<24:33,  9.73it/s, v_num=ui8w, train/loss=3.120\r",
+      "Epoch 0:   4%| | 595/14932 [01:01<24:33,  9.73it/s, v_num=ui8w, train/loss=2.250"
      ]
     },
     {
@@ -6572,7 +6546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 593/14932 [01:02<25:20,  9.43it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   4%| | 596/14932 [01:01<24:33,  9.73it/s, v_num=ui8w, train/loss=2.250\r",
+      "Epoch 0:   4%| | 596/14932 [01:01<24:33,  9.73it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -6580,8 +6555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 594/14932 [01:02<25:19,  9.43it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   4%| | 594/14932 [01:02<25:19,  9.43it/s, v_num=o30c, train/loss=4.380"
+      "Epoch 0:   4%| | 597/14932 [01:01<24:32,  9.74it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   4%| | 597/14932 [01:01<24:32,  9.74it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -6589,8 +6564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 595/14932 [01:03<25:18,  9.44it/s, v_num=o30c, train/loss=4.380\r",
-      "Epoch 0:   4%| | 595/14932 [01:03<25:18,  9.44it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   4%| | 598/14932 [01:01<24:31,  9.74it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   4%| | 598/14932 [01:01<24:31,  9.74it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -6598,8 +6573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 596/14932 [01:03<25:17,  9.44it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   4%| | 596/14932 [01:03<25:17,  9.44it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   4%| | 599/14932 [01:01<24:30,  9.75it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   4%| | 599/14932 [01:01<24:30,  9.75it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -6607,8 +6582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 597/14932 [01:03<25:18,  9.44it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   4%| | 597/14932 [01:03<25:18,  9.44it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   4%| | 600/14932 [01:01<24:29,  9.75it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   4%| | 600/14932 [01:01<24:29,  9.75it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -6616,8 +6591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 598/14932 [01:03<25:17,  9.44it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   4%| | 598/14932 [01:03<25:17,  9.44it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   4%| | 601/14932 [01:01<24:29,  9.75it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   4%| | 601/14932 [01:01<24:29,  9.75it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -6625,8 +6600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 599/14932 [01:03<25:16,  9.45it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   4%| | 599/14932 [01:03<25:16,  9.45it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   4%| | 602/14932 [01:01<24:28,  9.76it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   4%| | 602/14932 [01:01<24:28,  9.76it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -6634,8 +6609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 600/14932 [01:03<25:16,  9.45it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   4%| | 600/14932 [01:03<25:16,  9.45it/s, v_num=o30c, train/loss=2.700"
+      "Epoch 0:   4%| | 603/14932 [01:01<24:27,  9.76it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   4%| | 603/14932 [01:01<24:27,  9.76it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -6643,8 +6618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 601/14932 [01:03<25:15,  9.46it/s, v_num=o30c, train/loss=2.700\r",
-      "Epoch 0:   4%| | 601/14932 [01:03<25:15,  9.46it/s, v_num=o30c, train/loss=1.810"
+      "Epoch 0:   4%| | 604/14932 [01:01<24:26,  9.77it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   4%| | 604/14932 [01:01<24:26,  9.77it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -6652,8 +6627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 602/14932 [01:03<25:14,  9.46it/s, v_num=o30c, train/loss=1.810\r",
-      "Epoch 0:   4%| | 602/14932 [01:03<25:14,  9.46it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   4%| | 605/14932 [01:01<24:25,  9.77it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   4%| | 605/14932 [01:01<24:25,  9.77it/s, v_num=ui8w, train/loss=4.910"
      ]
     },
     {
@@ -6661,8 +6636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 603/14932 [01:03<25:13,  9.47it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   4%| | 603/14932 [01:03<25:13,  9.47it/s, v_num=o30c, train/loss=3.940"
+      "Epoch 0:   4%| | 606/14932 [01:01<24:25,  9.78it/s, v_num=ui8w, train/loss=4.910\r",
+      "Epoch 0:   4%| | 606/14932 [01:01<24:25,  9.78it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -6670,8 +6645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 604/14932 [01:03<25:12,  9.47it/s, v_num=o30c, train/loss=3.940\r",
-      "Epoch 0:   4%| | 604/14932 [01:03<25:12,  9.47it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   4%| | 607/14932 [01:02<24:24,  9.78it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   4%| | 607/14932 [01:02<24:24,  9.78it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -6679,8 +6654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 605/14932 [01:03<25:11,  9.48it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   4%| | 605/14932 [01:03<25:11,  9.48it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   4%| | 608/14932 [01:02<24:26,  9.77it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   4%| | 608/14932 [01:02<24:26,  9.77it/s, v_num=ui8w, train/loss=1.870"
      ]
     },
     {
@@ -6688,8 +6663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 606/14932 [01:03<25:10,  9.48it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   4%| | 606/14932 [01:03<25:10,  9.48it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   4%| | 609/14932 [01:02<24:25,  9.77it/s, v_num=ui8w, train/loss=1.870\r",
+      "Epoch 0:   4%| | 609/14932 [01:02<24:25,  9.77it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -6697,8 +6672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 607/14932 [01:03<25:09,  9.49it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   4%| | 607/14932 [01:03<25:09,  9.49it/s, v_num=o30c, train/loss=3.520"
+      "Epoch 0:   4%| | 610/14932 [01:02<24:24,  9.78it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   4%| | 610/14932 [01:02<24:24,  9.78it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -6706,8 +6681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 608/14932 [01:04<25:11,  9.48it/s, v_num=o30c, train/loss=3.520\r",
-      "Epoch 0:   4%| | 608/14932 [01:04<25:11,  9.48it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   4%| | 611/14932 [01:02<24:23,  9.78it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   4%| | 611/14932 [01:02<24:23,  9.78it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -6715,8 +6690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 609/14932 [01:04<25:12,  9.47it/s, v_num=o30c, train/loss=4.160\r",
-      "Epoch 0:   4%| | 609/14932 [01:04<25:12,  9.47it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   4%| | 612/14932 [01:02<24:22,  9.79it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   4%| | 612/14932 [01:02<24:22,  9.79it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -6724,8 +6699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 610/14932 [01:04<25:11,  9.48it/s, v_num=o30c, train/loss=4.160\r",
-      "Epoch 0:   4%| | 610/14932 [01:04<25:11,  9.48it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   4%| | 613/14932 [01:02<24:22,  9.79it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   4%| | 613/14932 [01:02<24:22,  9.79it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -6733,8 +6708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 611/14932 [01:04<25:10,  9.48it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   4%| | 611/14932 [01:04<25:10,  9.48it/s, v_num=o30c, train/loss=4.530"
+      "Epoch 0:   4%| | 614/14932 [01:02<24:21,  9.80it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   4%| | 614/14932 [01:02<24:21,  9.80it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -6742,8 +6717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 612/14932 [01:04<25:09,  9.49it/s, v_num=o30c, train/loss=4.530\r",
-      "Epoch 0:   4%| | 612/14932 [01:04<25:09,  9.49it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   4%| | 615/14932 [01:02<24:20,  9.80it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   4%| | 615/14932 [01:02<24:20,  9.80it/s, v_num=ui8w, train/loss=4.750"
      ]
     },
     {
@@ -6751,8 +6726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 613/14932 [01:04<25:08,  9.49it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   4%| | 613/14932 [01:04<25:08,  9.49it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   4%| | 616/14932 [01:02<24:19,  9.81it/s, v_num=ui8w, train/loss=4.750\r",
+      "Epoch 0:   4%| | 616/14932 [01:02<24:19,  9.81it/s, v_num=ui8w, train/loss=2.890"
      ]
     },
     {
@@ -6760,8 +6735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 614/14932 [01:04<25:07,  9.50it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   4%| | 614/14932 [01:04<25:07,  9.50it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   4%| | 617/14932 [01:02<24:19,  9.81it/s, v_num=ui8w, train/loss=2.890\r",
+      "Epoch 0:   4%| | 617/14932 [01:02<24:19,  9.81it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -6769,8 +6744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 615/14932 [01:04<25:07,  9.50it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   4%| | 615/14932 [01:04<25:07,  9.50it/s, v_num=o30c, train/loss=3.030"
+      "Epoch 0:   4%| | 618/14932 [01:02<24:18,  9.82it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   4%| | 618/14932 [01:02<24:18,  9.82it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -6778,8 +6753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 616/14932 [01:04<25:06,  9.50it/s, v_num=o30c, train/loss=3.030\r",
-      "Epoch 0:   4%| | 616/14932 [01:04<25:06,  9.50it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   4%| | 619/14932 [01:03<24:17,  9.82it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   4%| | 619/14932 [01:03<24:17,  9.82it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -6787,8 +6762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 617/14932 [01:04<25:05,  9.51it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   4%| | 617/14932 [01:04<25:05,  9.51it/s, v_num=o30c, train/loss=4.840"
+      "Epoch 0:   4%| | 620/14932 [01:03<24:16,  9.83it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   4%| | 620/14932 [01:03<24:16,  9.83it/s, v_num=ui8w, train/loss=4.560"
      ]
     },
     {
@@ -6796,8 +6771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 618/14932 [01:04<25:04,  9.51it/s, v_num=o30c, train/loss=4.840\r",
-      "Epoch 0:   4%| | 618/14932 [01:04<25:04,  9.51it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   4%| | 621/14932 [01:03<24:15,  9.83it/s, v_num=ui8w, train/loss=4.560\r",
+      "Epoch 0:   4%| | 621/14932 [01:03<24:15,  9.83it/s, v_num=ui8w, train/loss=2.160"
      ]
     },
     {
@@ -6805,8 +6780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 619/14932 [01:05<25:03,  9.52it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   4%| | 619/14932 [01:05<25:03,  9.52it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   4%| | 622/14932 [01:03<24:14,  9.84it/s, v_num=ui8w, train/loss=2.160\r",
+      "Epoch 0:   4%| | 622/14932 [01:03<24:14,  9.84it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -6814,8 +6789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 620/14932 [01:05<25:03,  9.52it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   4%| | 620/14932 [01:05<25:03,  9.52it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   4%| | 623/14932 [01:03<24:13,  9.84it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   4%| | 623/14932 [01:03<24:13,  9.84it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -6823,8 +6798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 621/14932 [01:05<25:02,  9.53it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   4%| | 621/14932 [01:05<25:02,  9.53it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   4%| | 624/14932 [01:03<24:13,  9.85it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   4%| | 624/14932 [01:03<24:13,  9.85it/s, v_num=ui8w, train/loss=2.770"
      ]
     },
     {
@@ -6832,8 +6807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 622/14932 [01:05<25:01,  9.53it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   4%| | 622/14932 [01:05<25:01,  9.53it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   4%| | 625/14932 [01:03<24:12,  9.85it/s, v_num=ui8w, train/loss=2.770\r",
+      "Epoch 0:   4%| | 625/14932 [01:03<24:12,  9.85it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -6841,8 +6816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 623/14932 [01:05<25:00,  9.54it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   4%| | 623/14932 [01:05<25:00,  9.54it/s, v_num=o30c, train/loss=3.030"
+      "Epoch 0:   4%| | 626/14932 [01:03<24:11,  9.86it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   4%| | 626/14932 [01:03<24:11,  9.86it/s, v_num=ui8w, train/loss=2.360"
      ]
     },
     {
@@ -6850,8 +6825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 624/14932 [01:05<24:59,  9.54it/s, v_num=o30c, train/loss=3.030\r",
-      "Epoch 0:   4%| | 624/14932 [01:05<24:59,  9.54it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   4%| | 627/14932 [01:03<24:10,  9.86it/s, v_num=ui8w, train/loss=2.360\r",
+      "Epoch 0:   4%| | 627/14932 [01:03<24:10,  9.86it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -6859,8 +6834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 625/14932 [01:05<24:59,  9.54it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   4%| | 625/14932 [01:05<24:59,  9.54it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   4%| | 628/14932 [01:03<24:09,  9.87it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   4%| | 628/14932 [01:03<24:09,  9.87it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -6868,8 +6843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 626/14932 [01:05<24:58,  9.55it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   4%| | 626/14932 [01:05<24:58,  9.55it/s, v_num=o30c, train/loss=3.520"
+      "Epoch 0:   4%| | 629/14932 [01:03<24:08,  9.87it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   4%| | 629/14932 [01:03<24:08,  9.87it/s, v_num=ui8w, train/loss=2.340"
      ]
     },
     {
@@ -6877,8 +6852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 627/14932 [01:05<24:57,  9.55it/s, v_num=o30c, train/loss=3.520\r",
-      "Epoch 0:   4%| | 627/14932 [01:05<24:57,  9.55it/s, v_num=o30c, train/loss=1.770"
+      "Epoch 0:   4%| | 630/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=2.340\r",
+      "Epoch 0:   4%| | 630/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -6886,8 +6861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 628/14932 [01:05<24:56,  9.56it/s, v_num=o30c, train/loss=1.770\r",
-      "Epoch 0:   4%| | 628/14932 [01:05<24:56,  9.56it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   4%| | 631/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   4%| | 631/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=4.500"
      ]
     },
     {
@@ -6895,8 +6870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 629/14932 [01:05<24:55,  9.56it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   4%| | 629/14932 [01:05<24:55,  9.56it/s, v_num=o30c, train/loss=3.840"
+      "Epoch 0:   4%| | 632/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=4.500\r",
+      "Epoch 0:   4%| | 632/14932 [01:03<24:07,  9.88it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -6904,8 +6879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 630/14932 [01:05<24:54,  9.57it/s, v_num=o30c, train/loss=3.840\r",
-      "Epoch 0:   4%| | 630/14932 [01:05<24:54,  9.57it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   4%| | 633/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   4%| | 633/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=3.270"
      ]
     },
     {
@@ -6913,8 +6888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 631/14932 [01:05<24:54,  9.57it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   4%| | 631/14932 [01:05<24:54,  9.57it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   4%| | 634/14932 [01:04<24:07,  9.88it/s, v_num=ui8w, train/loss=3.270\r",
+      "Epoch 0:   4%| | 634/14932 [01:04<24:07,  9.88it/s, v_num=ui8w, train/loss=4.590"
      ]
     },
     {
@@ -6922,8 +6897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 632/14932 [01:06<24:53,  9.58it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   4%| | 632/14932 [01:06<24:53,  9.58it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   4%| | 635/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=4.590\r",
+      "Epoch 0:   4%| | 635/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -6931,8 +6906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 633/14932 [01:06<24:52,  9.58it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   4%| | 633/14932 [01:06<24:52,  9.58it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   4%| | 636/14932 [01:04<24:06,  9.89it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   4%| | 636/14932 [01:04<24:06,  9.89it/s, v_num=ui8w, train/loss=1.730"
      ]
     },
     {
@@ -6940,8 +6915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 634/14932 [01:06<24:51,  9.58it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   4%| | 634/14932 [01:06<24:51,  9.58it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   4%| | 637/14932 [01:04<24:05,  9.89it/s, v_num=ui8w, train/loss=1.730\r",
+      "Epoch 0:   4%| | 637/14932 [01:04<24:05,  9.89it/s, v_num=ui8w, train/loss=2.910"
      ]
     },
     {
@@ -6949,8 +6924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 635/14932 [01:06<24:51,  9.59it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   4%| | 635/14932 [01:06<24:51,  9.59it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   4%| | 638/14932 [01:04<24:04,  9.90it/s, v_num=ui8w, train/loss=2.910\r",
+      "Epoch 0:   4%| | 638/14932 [01:04<24:04,  9.90it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -6958,8 +6933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 636/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   4%| | 636/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=2.720"
+      "Epoch 0:   4%| | 639/14932 [01:04<24:03,  9.90it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   4%| | 639/14932 [01:04<24:03,  9.90it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -6967,8 +6942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 637/14932 [01:06<24:49,  9.60it/s, v_num=o30c, train/loss=2.720\r",
-      "Epoch 0:   4%| | 637/14932 [01:06<24:49,  9.60it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   4%| | 640/14932 [01:04<24:07,  9.88it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   4%| | 640/14932 [01:04<24:07,  9.88it/s, v_num=ui8w, train/loss=4.470"
      ]
     },
     {
@@ -6976,8 +6951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 638/14932 [01:06<24:48,  9.60it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   4%| | 638/14932 [01:06<24:48,  9.60it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   4%| | 641/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=4.470\r",
+      "Epoch 0:   4%| | 641/14932 [01:04<24:06,  9.88it/s, v_num=ui8w, train/loss=2.670"
      ]
     },
     {
@@ -6985,8 +6960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 639/14932 [01:06<24:48,  9.60it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   4%| | 639/14932 [01:06<24:48,  9.60it/s, v_num=o30c, train/loss=3.660"
+      "Epoch 0:   4%| | 642/14932 [01:04<24:05,  9.89it/s, v_num=ui8w, train/loss=2.670\r",
+      "Epoch 0:   4%| | 642/14932 [01:04<24:05,  9.89it/s, v_num=ui8w, train/loss=2.950"
      ]
     },
     {
@@ -6994,8 +6969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 640/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=3.660\r",
-      "Epoch 0:   4%| | 640/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   4%| | 643/14932 [01:05<24:04,  9.89it/s, v_num=ui8w, train/loss=2.950\r",
+      "Epoch 0:   4%| | 643/14932 [01:05<24:04,  9.89it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -7003,8 +6978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 641/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   4%| | 641/14932 [01:06<24:50,  9.59it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   4%| | 644/14932 [01:05<24:04,  9.89it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   4%| | 644/14932 [01:05<24:04,  9.89it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -7012,8 +6987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 642/14932 [01:06<24:49,  9.59it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   4%| | 642/14932 [01:06<24:49,  9.59it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   4%| | 645/14932 [01:05<24:03,  9.90it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   4%| | 645/14932 [01:05<24:03,  9.90it/s, v_num=ui8w, train/loss=2.500"
      ]
     },
     {
@@ -7021,8 +6996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 643/14932 [01:07<24:49,  9.60it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   4%| | 643/14932 [01:07<24:49,  9.60it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   4%| | 646/14932 [01:05<24:02,  9.90it/s, v_num=ui8w, train/loss=2.500\r",
+      "Epoch 0:   4%| | 646/14932 [01:05<24:02,  9.90it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -7030,8 +7005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 644/14932 [01:07<24:48,  9.60it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   4%| | 644/14932 [01:07<24:48,  9.60it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   4%| | 647/14932 [01:05<24:01,  9.91it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   4%| | 647/14932 [01:05<24:01,  9.91it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -7039,8 +7014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 645/14932 [01:07<24:47,  9.61it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   4%| | 645/14932 [01:07<24:47,  9.61it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   4%| | 648/14932 [01:05<24:01,  9.91it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   4%| | 648/14932 [01:05<24:01,  9.91it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -7048,8 +7023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 646/14932 [01:07<24:46,  9.61it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   4%| | 646/14932 [01:07<24:46,  9.61it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   4%| | 649/14932 [01:05<24:00,  9.92it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   4%| | 649/14932 [01:05<24:00,  9.92it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -7057,8 +7032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 647/14932 [01:07<24:45,  9.62it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   4%| | 647/14932 [01:07<24:45,  9.61it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   4%| | 650/14932 [01:05<23:59,  9.92it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   4%| | 650/14932 [01:05<23:59,  9.92it/s, v_num=ui8w, train/loss=4.750"
      ]
     },
     {
@@ -7066,8 +7041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 648/14932 [01:07<24:44,  9.62it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   4%| | 648/14932 [01:07<24:44,  9.62it/s, v_num=o30c, train/loss=2.700"
+      "Epoch 0:   4%| | 651/14932 [01:05<23:59,  9.92it/s, v_num=ui8w, train/loss=4.750\r",
+      "Epoch 0:   4%| | 651/14932 [01:05<23:59,  9.92it/s, v_num=ui8w, train/loss=3.270"
      ]
     },
     {
@@ -7075,8 +7050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 649/14932 [01:07<24:43,  9.63it/s, v_num=o30c, train/loss=2.700\r",
-      "Epoch 0:   4%| | 649/14932 [01:07<24:43,  9.63it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   4%| | 652/14932 [01:05<23:58,  9.93it/s, v_num=ui8w, train/loss=3.270\r",
+      "Epoch 0:   4%| | 652/14932 [01:05<23:58,  9.93it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -7084,8 +7059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 650/14932 [01:07<24:43,  9.63it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   4%| | 650/14932 [01:07<24:43,  9.63it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   4%| | 653/14932 [01:05<23:57,  9.93it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   4%| | 653/14932 [01:05<23:57,  9.93it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -7093,8 +7068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 651/14932 [01:07<24:42,  9.63it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   4%| | 651/14932 [01:07<24:42,  9.63it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   4%| | 654/14932 [01:05<23:57,  9.94it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   4%| | 654/14932 [01:05<23:57,  9.94it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -7102,8 +7077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 652/14932 [01:07<24:41,  9.64it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   4%| | 652/14932 [01:07<24:41,  9.64it/s, v_num=o30c, train/loss=2.550"
+      "Epoch 0:   4%| | 655/14932 [01:05<23:56,  9.94it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   4%| | 655/14932 [01:05<23:56,  9.94it/s, v_num=ui8w, train/loss=2.330"
      ]
     },
     {
@@ -7111,8 +7086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 653/14932 [01:07<24:40,  9.64it/s, v_num=o30c, train/loss=2.550\r",
-      "Epoch 0:   4%| | 653/14932 [01:07<24:40,  9.64it/s, v_num=o30c, train/loss=2.700"
+      "Epoch 0:   4%| | 656/14932 [01:05<23:55,  9.94it/s, v_num=ui8w, train/loss=2.330\r",
+      "Epoch 0:   4%| | 656/14932 [01:05<23:55,  9.94it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -7120,8 +7095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 654/14932 [01:07<24:40,  9.65it/s, v_num=o30c, train/loss=2.700\r",
-      "Epoch 0:   4%| | 654/14932 [01:07<24:40,  9.65it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   4%| | 657/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   4%| | 657/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -7129,8 +7104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 655/14932 [01:07<24:39,  9.65it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   4%| | 655/14932 [01:07<24:39,  9.65it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   4%| | 658/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   4%| | 658/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=3.230"
      ]
     },
     {
@@ -7138,8 +7113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 656/14932 [01:07<24:38,  9.65it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   4%| | 656/14932 [01:07<24:38,  9.65it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   4%| | 659/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=3.230\r",
+      "Epoch 0:   4%| | 659/14932 [01:06<23:54,  9.95it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -7147,8 +7122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 657/14932 [01:08<24:37,  9.66it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   4%| | 657/14932 [01:08<24:37,  9.66it/s, v_num=o30c, train/loss=3.720"
+      "Epoch 0:   4%| | 660/14932 [01:06<23:53,  9.95it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   4%| | 660/14932 [01:06<23:53,  9.95it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -7156,8 +7131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 658/14932 [01:08<24:37,  9.66it/s, v_num=o30c, train/loss=3.720\r",
-      "Epoch 0:   4%| | 658/14932 [01:08<24:37,  9.66it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   4%| | 661/14932 [01:06<23:53,  9.96it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   4%| | 661/14932 [01:06<23:53,  9.96it/s, v_num=ui8w, train/loss=4.620"
      ]
     },
     {
@@ -7165,8 +7140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 659/14932 [01:08<24:36,  9.67it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   4%| | 659/14932 [01:08<24:36,  9.67it/s, v_num=o30c, train/loss=3.940"
+      "Epoch 0:   4%| | 662/14932 [01:06<23:52,  9.96it/s, v_num=ui8w, train/loss=4.620\r",
+      "Epoch 0:   4%| | 662/14932 [01:06<23:52,  9.96it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -7174,8 +7149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 660/14932 [01:08<24:35,  9.67it/s, v_num=o30c, train/loss=3.940\r",
-      "Epoch 0:   4%| | 660/14932 [01:08<24:35,  9.67it/s, v_num=o30c, train/loss=2.270"
+      "Epoch 0:   4%| | 663/14932 [01:06<23:51,  9.96it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   4%| | 663/14932 [01:06<23:51,  9.96it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -7183,8 +7158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 661/14932 [01:08<24:34,  9.68it/s, v_num=o30c, train/loss=2.270\r",
-      "Epoch 0:   4%| | 661/14932 [01:08<24:34,  9.68it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   4%| | 664/14932 [01:06<23:51,  9.97it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   4%| | 664/14932 [01:06<23:51,  9.97it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -7192,8 +7167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 662/14932 [01:08<24:33,  9.68it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   4%| | 662/14932 [01:08<24:33,  9.68it/s, v_num=o30c, train/loss=2.110"
+      "Epoch 0:   4%| | 665/14932 [01:06<23:51,  9.96it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   4%| | 665/14932 [01:06<23:51,  9.96it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -7201,8 +7176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 663/14932 [01:08<24:33,  9.69it/s, v_num=o30c, train/loss=2.110\r",
-      "Epoch 0:   4%| | 663/14932 [01:08<24:33,  9.69it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   4%| | 666/14932 [01:06<23:51,  9.97it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   4%| | 666/14932 [01:06<23:51,  9.97it/s, v_num=ui8w, train/loss=2.750"
      ]
     },
     {
@@ -7210,8 +7185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 664/14932 [01:08<24:32,  9.69it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   4%| | 664/14932 [01:08<24:32,  9.69it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   4%| | 667/14932 [01:06<23:50,  9.97it/s, v_num=ui8w, train/loss=2.750\r",
+      "Epoch 0:   4%| | 667/14932 [01:06<23:50,  9.97it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -7219,8 +7194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 665/14932 [01:08<24:31,  9.69it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   4%| | 665/14932 [01:08<24:31,  9.69it/s, v_num=o30c, train/loss=2.330"
+      "Epoch 0:   4%| | 668/14932 [01:06<23:49,  9.97it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   4%| | 668/14932 [01:06<23:49,  9.97it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -7228,8 +7203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 666/14932 [01:08<24:30,  9.70it/s, v_num=o30c, train/loss=2.330\r",
-      "Epoch 0:   4%| | 666/14932 [01:08<24:30,  9.70it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   4%| | 669/14932 [01:07<23:49,  9.98it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   4%| | 669/14932 [01:07<23:49,  9.98it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -7237,8 +7212,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 667/14932 [01:08<24:30,  9.70it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   4%| | 667/14932 [01:08<24:30,  9.70it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   4%| | 670/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -7246,8 +7220,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 668/14932 [01:08<24:29,  9.71it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   4%| | 668/14932 [01:08<24:29,  9.71it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   4%| | 670/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=2.090"
      ]
     },
     {
@@ -7255,8 +7228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 669/14932 [01:08<24:28,  9.71it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   4%| | 669/14932 [01:08<24:28,  9.71it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   4%| | 671/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=2.090\r",
+      "Epoch 0:   4%| | 671/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -7264,8 +7237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 670/14932 [01:08<24:27,  9.72it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   4%| | 670/14932 [01:08<24:27,  9.72it/s, v_num=o30c, train/loss=1.530"
+      "Epoch 0:   5%| | 672/14932 [01:07<23:49,  9.98it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   5%| | 672/14932 [01:07<23:49,  9.98it/s, v_num=ui8w, train/loss=2.470"
      ]
     },
     {
@@ -7273,8 +7246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   4%| | 671/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=1.530\r",
-      "Epoch 0:   4%| | 671/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   5%| | 673/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=2.470\r",
+      "Epoch 0:   5%| | 673/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -7282,8 +7255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 672/14932 [01:09<24:28,  9.71it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   5%| | 672/14932 [01:09<24:28,  9.71it/s, v_num=o30c, train/loss=3.110"
+      "Epoch 0:   5%| | 674/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   5%| | 674/14932 [01:07<23:48,  9.98it/s, v_num=ui8w, train/loss=4.310"
      ]
     },
     {
@@ -7291,8 +7264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 673/14932 [01:09<24:27,  9.71it/s, v_num=o30c, train/loss=3.110\r",
-      "Epoch 0:   5%| | 673/14932 [01:09<24:27,  9.71it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   5%| | 675/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=4.310\r",
+      "Epoch 0:   5%| | 675/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=3.890"
      ]
     },
     {
@@ -7300,8 +7273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 674/14932 [01:09<24:27,  9.72it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   5%| | 674/14932 [01:09<24:27,  9.72it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   5%| | 676/14932 [01:07<23:46,  9.99it/s, v_num=ui8w, train/loss=3.890\r",
+      "Epoch 0:   5%| | 676/14932 [01:07<23:46,  9.99it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -7309,8 +7282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 675/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   5%| | 675/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   5%| | 677/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   5%| | 677/14932 [01:07<23:47,  9.99it/s, v_num=ui8w, train/loss=2.840"
      ]
     },
     {
@@ -7318,8 +7291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 676/14932 [01:09<24:27,  9.72it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   5%| | 676/14932 [01:09<24:27,  9.72it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   5%| | 678/14932 [01:07<23:46,  9.99it/s, v_num=ui8w, train/loss=2.840\r",
+      "Epoch 0:   5%| | 678/14932 [01:07<23:46,  9.99it/s, v_num=ui8w, train/loss=4.470"
      ]
     },
     {
@@ -7327,8 +7300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 677/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   5%| | 677/14932 [01:09<24:26,  9.72it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   5%| | 679/14932 [01:07<23:45, 10.00it/s, v_num=ui8w, train/loss=4.470\r",
+      "Epoch 0:   5%| | 679/14932 [01:07<23:45, 10.00it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -7336,8 +7309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 678/14932 [01:09<24:25,  9.73it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   5%| | 678/14932 [01:09<24:25,  9.72it/s, v_num=o30c, train/loss=2.390"
+      "Epoch 0:   5%| | 680/14932 [01:07<23:45, 10.00it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   5%| | 680/14932 [01:07<23:45, 10.00it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -7345,8 +7318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 679/14932 [01:09<24:25,  9.73it/s, v_num=o30c, train/loss=2.390\r",
-      "Epoch 0:   5%| | 679/14932 [01:09<24:25,  9.73it/s, v_num=o30c, train/loss=4.590"
+      "Epoch 0:   5%| | 681/14932 [01:08<23:44, 10.01it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   5%| | 681/14932 [01:08<23:44, 10.01it/s, v_num=ui8w, train/loss=3.270"
      ]
     },
     {
@@ -7354,8 +7327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 680/14932 [01:09<24:24,  9.73it/s, v_num=o30c, train/loss=4.590\r",
-      "Epoch 0:   5%| | 680/14932 [01:09<24:24,  9.73it/s, v_num=o30c, train/loss=2.910"
+      "Epoch 0:   5%| | 682/14932 [01:08<23:43, 10.01it/s, v_num=ui8w, train/loss=3.270\r",
+      "Epoch 0:   5%| | 682/14932 [01:08<23:43, 10.01it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -7363,8 +7336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 681/14932 [01:09<24:23,  9.74it/s, v_num=o30c, train/loss=2.910\r",
-      "Epoch 0:   5%| | 681/14932 [01:09<24:23,  9.73it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   5%| | 683/14932 [01:08<23:43, 10.01it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   5%| | 683/14932 [01:08<23:43, 10.01it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -7372,8 +7345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 682/14932 [01:10<24:23,  9.74it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   5%| | 682/14932 [01:10<24:23,  9.74it/s, v_num=o30c, train/loss=4.720"
+      "Epoch 0:   5%| | 684/14932 [01:08<23:42, 10.02it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   5%| | 684/14932 [01:08<23:42, 10.02it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -7381,8 +7354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 683/14932 [01:10<24:22,  9.74it/s, v_num=o30c, train/loss=4.720\r",
-      "Epoch 0:   5%| | 683/14932 [01:10<24:22,  9.74it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   5%| | 685/14932 [01:08<23:41, 10.02it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   5%| | 685/14932 [01:08<23:41, 10.02it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -7390,8 +7363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 684/14932 [01:10<24:21,  9.75it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   5%| | 684/14932 [01:10<24:21,  9.75it/s, v_num=o30c, train/loss=2.410"
+      "Epoch 0:   5%| | 686/14932 [01:08<23:41, 10.03it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   5%| | 686/14932 [01:08<23:41, 10.03it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -7399,8 +7372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 685/14932 [01:10<24:21,  9.75it/s, v_num=o30c, train/loss=2.410\r",
-      "Epoch 0:   5%| | 685/14932 [01:10<24:21,  9.75it/s, v_num=o30c, train/loss=3.380"
+      "Epoch 0:   5%| | 687/14932 [01:08<23:40, 10.03it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   5%| | 687/14932 [01:08<23:40, 10.03it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -7408,8 +7381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 686/14932 [01:10<24:20,  9.76it/s, v_num=o30c, train/loss=3.380\r",
-      "Epoch 0:   5%| | 686/14932 [01:10<24:20,  9.76it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   5%| | 688/14932 [01:08<23:40, 10.02it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   5%| | 688/14932 [01:08<23:40, 10.02it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -7417,8 +7390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 687/14932 [01:10<24:19,  9.76it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   5%| | 687/14932 [01:10<24:19,  9.76it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   5%| | 689/14932 [01:08<23:40, 10.03it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   5%| | 689/14932 [01:08<23:40, 10.03it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -7426,8 +7399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 688/14932 [01:10<24:18,  9.76it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   5%| | 688/14932 [01:10<24:18,  9.76it/s, v_num=o30c, train/loss=3.720"
+      "Epoch 0:   5%| | 690/14932 [01:08<23:39, 10.03it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   5%| | 690/14932 [01:08<23:39, 10.03it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -7435,8 +7408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 689/14932 [01:10<24:18,  9.77it/s, v_num=o30c, train/loss=3.720\r",
-      "Epoch 0:   5%| | 689/14932 [01:10<24:18,  9.77it/s, v_num=o30c, train/loss=1.170"
+      "Epoch 0:   5%| | 691/14932 [01:08<23:38, 10.04it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   5%| | 691/14932 [01:08<23:38, 10.04it/s, v_num=ui8w, train/loss=3.120"
      ]
     },
     {
@@ -7444,8 +7417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 690/14932 [01:10<24:17,  9.77it/s, v_num=o30c, train/loss=1.170\r",
-      "Epoch 0:   5%| | 690/14932 [01:10<24:17,  9.77it/s, v_num=o30c, train/loss=2.910"
+      "Epoch 0:   5%| | 692/14932 [01:08<23:38, 10.04it/s, v_num=ui8w, train/loss=3.120\r",
+      "Epoch 0:   5%| | 692/14932 [01:08<23:38, 10.04it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -7453,8 +7426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 691/14932 [01:10<24:16,  9.78it/s, v_num=o30c, train/loss=2.910\r",
-      "Epoch 0:   5%| | 691/14932 [01:10<24:16,  9.78it/s, v_num=o30c, train/loss=4.750"
+      "Epoch 0:   5%| | 693/14932 [01:08<23:37, 10.04it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   5%| | 693/14932 [01:08<23:37, 10.04it/s, v_num=ui8w, train/loss=3.780"
      ]
     },
     {
@@ -7462,8 +7435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 692/14932 [01:10<24:15,  9.78it/s, v_num=o30c, train/loss=4.750\r",
-      "Epoch 0:   5%| | 692/14932 [01:10<24:15,  9.78it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   5%| | 694/14932 [01:09<23:36, 10.05it/s, v_num=ui8w, train/loss=3.780\r",
+      "Epoch 0:   5%| | 694/14932 [01:09<23:36, 10.05it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -7471,8 +7444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 693/14932 [01:10<24:15,  9.78it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   5%| | 693/14932 [01:10<24:15,  9.78it/s, v_num=o30c, train/loss=1.660"
+      "Epoch 0:   5%| | 695/14932 [01:09<23:36, 10.05it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   5%| | 695/14932 [01:09<23:36, 10.05it/s, v_num=ui8w, train/loss=4.750"
      ]
     },
     {
@@ -7480,8 +7453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 694/14932 [01:10<24:14,  9.79it/s, v_num=o30c, train/loss=1.660\r",
-      "Epoch 0:   5%| | 694/14932 [01:10<24:14,  9.79it/s, v_num=o30c, train/loss=3.660"
+      "Epoch 0:   5%| | 696/14932 [01:09<23:35, 10.06it/s, v_num=ui8w, train/loss=4.750\r",
+      "Epoch 0:   5%| | 696/14932 [01:09<23:35, 10.06it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -7489,8 +7462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 695/14932 [01:10<24:13,  9.79it/s, v_num=o30c, train/loss=3.660\r",
-      "Epoch 0:   5%| | 695/14932 [01:10<24:13,  9.79it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   5%| | 697/14932 [01:09<23:34, 10.06it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   5%| | 697/14932 [01:09<23:34, 10.06it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -7498,8 +7471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 696/14932 [01:11<24:14,  9.79it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   5%| | 696/14932 [01:11<24:14,  9.79it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   5%| | 698/14932 [01:09<23:33, 10.07it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   5%| | 698/14932 [01:09<23:33, 10.07it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -7507,8 +7480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 697/14932 [01:11<24:13,  9.79it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   5%| | 697/14932 [01:11<24:13,  9.79it/s, v_num=o30c, train/loss=3.380"
+      "Epoch 0:   5%| | 699/14932 [01:09<23:33, 10.07it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   5%| | 699/14932 [01:09<23:33, 10.07it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -7516,8 +7489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 698/14932 [01:11<24:13,  9.80it/s, v_num=o30c, train/loss=3.380\r",
-      "Epoch 0:   5%| | 698/14932 [01:11<24:13,  9.80it/s, v_num=o30c, train/loss=4.380"
+      "Epoch 0:   5%| | 700/14932 [01:09<23:32, 10.07it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   5%| | 700/14932 [01:09<23:32, 10.07it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -7525,8 +7498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 699/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=4.380\r",
-      "Epoch 0:   5%| | 699/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   5%| | 701/14932 [01:09<23:31, 10.08it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   5%| | 701/14932 [01:09<23:32, 10.08it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -7534,8 +7507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 700/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   5%| | 700/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   5%| | 702/14932 [01:09<23:31, 10.08it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   5%| | 702/14932 [01:09<23:31, 10.08it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -7543,8 +7516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 701/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   5%| | 701/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   5%| | 703/14932 [01:09<23:30, 10.09it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   5%| | 703/14932 [01:09<23:30, 10.09it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -7552,8 +7525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 702/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   5%| | 702/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   5%| | 704/14932 [01:09<23:32, 10.07it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   5%| | 704/14932 [01:09<23:32, 10.07it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -7561,8 +7534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 703/14932 [01:11<24:10,  9.81it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   5%| | 703/14932 [01:11<24:10,  9.81it/s, v_num=o30c, train/loss=2.300"
+      "Epoch 0:   5%| | 705/14932 [01:09<23:31, 10.08it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   5%| | 705/14932 [01:09<23:31, 10.08it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -7570,8 +7543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 704/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=2.300\r",
-      "Epoch 0:   5%| | 704/14932 [01:11<24:12,  9.80it/s, v_num=o30c, train/loss=3.060"
+      "Epoch 0:   5%| | 706/14932 [01:10<23:31, 10.08it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   5%| | 706/14932 [01:10<23:31, 10.08it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -7579,8 +7552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 705/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=3.060\r",
-      "Epoch 0:   5%| | 705/14932 [01:11<24:11,  9.80it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   5%| | 707/14932 [01:10<23:30, 10.09it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   5%| | 707/14932 [01:10<23:30, 10.09it/s, v_num=ui8w, train/loss=2.200"
      ]
     },
     {
@@ -7588,8 +7561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 706/14932 [01:12<24:11,  9.80it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   5%| | 706/14932 [01:12<24:11,  9.80it/s, v_num=o30c, train/loss=4.120"
+      "Epoch 0:   5%| | 708/14932 [01:10<23:29, 10.09it/s, v_num=ui8w, train/loss=2.200\r",
+      "Epoch 0:   5%| | 708/14932 [01:10<23:29, 10.09it/s, v_num=ui8w, train/loss=2.860"
      ]
     },
     {
@@ -7597,8 +7570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 707/14932 [01:12<24:12,  9.79it/s, v_num=o30c, train/loss=4.120\r",
-      "Epoch 0:   5%| | 707/14932 [01:12<24:12,  9.79it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   5%| | 709/14932 [01:10<23:28, 10.10it/s, v_num=ui8w, train/loss=2.860\r",
+      "Epoch 0:   5%| | 709/14932 [01:10<23:28, 10.10it/s, v_num=ui8w, train/loss=2.300"
      ]
     },
     {
@@ -7606,8 +7579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 708/14932 [01:12<24:12,  9.80it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   5%| | 708/14932 [01:12<24:12,  9.80it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   5%| | 710/14932 [01:10<23:28, 10.10it/s, v_num=ui8w, train/loss=2.300\r",
+      "Epoch 0:   5%| | 710/14932 [01:10<23:28, 10.10it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -7615,8 +7588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 709/14932 [01:12<24:11,  9.80it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   5%| | 709/14932 [01:12<24:11,  9.80it/s, v_num=o30c, train/loss=4.590"
+      "Epoch 0:   5%| | 711/14932 [01:10<23:27, 10.10it/s, v_num=ui8w, train/loss=2.030\r",
+      "Epoch 0:   5%| | 711/14932 [01:10<23:27, 10.10it/s, v_num=ui8w, train/loss=1.410"
      ]
     },
     {
@@ -7624,8 +7597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 710/14932 [01:12<24:10,  9.80it/s, v_num=o30c, train/loss=4.590\r",
-      "Epoch 0:   5%| | 710/14932 [01:12<24:11,  9.80it/s, v_num=o30c, train/loss=2.880"
+      "Epoch 0:   5%| | 712/14932 [01:10<23:26, 10.11it/s, v_num=ui8w, train/loss=1.410\r",
+      "Epoch 0:   5%| | 712/14932 [01:10<23:26, 10.11it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -7633,8 +7606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 711/14932 [01:12<24:10,  9.81it/s, v_num=o30c, train/loss=2.880\r",
-      "Epoch 0:   5%| | 711/14932 [01:12<24:10,  9.81it/s, v_num=o30c, train/loss=3.270"
+      "Epoch 0:   5%| | 713/14932 [01:10<23:26, 10.11it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   5%| | 713/14932 [01:10<23:26, 10.11it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -7642,8 +7615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 712/14932 [01:12<24:09,  9.81it/s, v_num=o30c, train/loss=3.270\r",
-      "Epoch 0:   5%| | 712/14932 [01:12<24:09,  9.81it/s, v_num=o30c, train/loss=3.440"
+      "Epoch 0:   5%| | 714/14932 [01:10<23:25, 10.12it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   5%| | 714/14932 [01:10<23:25, 10.12it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -7651,8 +7624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 713/14932 [01:12<24:08,  9.81it/s, v_num=o30c, train/loss=3.440\r",
-      "Epoch 0:   5%| | 713/14932 [01:12<24:08,  9.81it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   5%| | 715/14932 [01:10<23:24, 10.12it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   5%| | 715/14932 [01:10<23:25, 10.12it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -7660,8 +7633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 714/14932 [01:12<24:08,  9.82it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   5%| | 714/14932 [01:12<24:08,  9.82it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   5%| | 716/14932 [01:10<23:24, 10.12it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   5%| | 716/14932 [01:10<23:24, 10.12it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -7669,8 +7642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 715/14932 [01:12<24:07,  9.82it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   5%| | 715/14932 [01:12<24:07,  9.82it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   5%| | 717/14932 [01:10<23:23, 10.13it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   5%| | 717/14932 [01:10<23:23, 10.13it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -7678,8 +7651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 716/14932 [01:12<24:06,  9.83it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   5%| | 716/14932 [01:12<24:06,  9.83it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   5%| | 718/14932 [01:10<23:23, 10.13it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   5%| | 718/14932 [01:10<23:23, 10.13it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -7687,8 +7660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 717/14932 [01:12<24:06,  9.83it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   5%| | 717/14932 [01:12<24:06,  9.83it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   5%| | 719/14932 [01:10<23:22, 10.13it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   5%| | 719/14932 [01:10<23:22, 10.13it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -7696,8 +7669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 718/14932 [01:13<24:05,  9.83it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   5%| | 718/14932 [01:13<24:05,  9.83it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   5%| | 720/14932 [01:11<23:22, 10.14it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   5%| | 720/14932 [01:11<23:22, 10.14it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -7705,8 +7678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 719/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   5%| | 719/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.800"
+      "Epoch 0:   5%| | 721/14932 [01:11<23:21, 10.14it/s, v_num=ui8w, train/loss=3.470\r",
+      "Epoch 0:   5%| | 721/14932 [01:11<23:21, 10.14it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -7714,8 +7687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 720/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.800\r",
-      "Epoch 0:   5%| | 720/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.030"
+      "Epoch 0:   5%| | 722/14932 [01:11<23:21, 10.14it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   5%| | 722/14932 [01:11<23:21, 10.14it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -7723,8 +7696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 721/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.030\r",
-      "Epoch 0:   5%| | 721/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=4.910"
+      "Epoch 0:   5%| | 723/14932 [01:11<23:20, 10.15it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   5%| | 723/14932 [01:11<23:20, 10.15it/s, v_num=ui8w, train/loss=2.750"
      ]
     },
     {
@@ -7732,8 +7705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 722/14932 [01:13<24:05,  9.83it/s, v_num=o30c, train/loss=4.910\r",
-      "Epoch 0:   5%| | 722/14932 [01:13<24:05,  9.83it/s, v_num=o30c, train/loss=3.800"
+      "Epoch 0:   5%| | 724/14932 [01:11<23:23, 10.12it/s, v_num=ui8w, train/loss=2.750\r",
+      "Epoch 0:   5%| | 724/14932 [01:11<23:23, 10.12it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -7741,8 +7714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 723/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=3.800\r",
-      "Epoch 0:   5%| | 723/14932 [01:13<24:04,  9.84it/s, v_num=o30c, train/loss=2.780"
+      "Epoch 0:   5%| | 725/14932 [01:11<23:22, 10.13it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   5%| | 725/14932 [01:11<23:22, 10.13it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -7750,8 +7723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 724/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=2.780\r",
-      "Epoch 0:   5%| | 724/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=1.560"
+      "Epoch 0:   5%| | 726/14932 [01:11<23:22, 10.13it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   5%| | 726/14932 [01:11<23:22, 10.13it/s, v_num=ui8w, train/loss=3.700"
      ]
     },
     {
@@ -7759,8 +7732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 725/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=1.560\r",
-      "Epoch 0:   5%| | 725/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   5%| | 727/14932 [01:11<23:21, 10.13it/s, v_num=ui8w, train/loss=3.700\r",
+      "Epoch 0:   5%| | 727/14932 [01:11<23:21, 10.13it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -7768,8 +7741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 726/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   5%| | 726/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   5%| | 728/14932 [01:11<23:20, 10.14it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   5%| | 728/14932 [01:11<23:20, 10.14it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -7777,8 +7750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 727/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   5%| | 727/14932 [01:13<24:03,  9.84it/s, v_num=o30c, train/loss=4.000"
+      "Epoch 0:   5%| | 729/14932 [01:11<23:20, 10.14it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   5%| | 729/14932 [01:11<23:20, 10.14it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -7786,8 +7759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 728/14932 [01:13<24:02,  9.85it/s, v_num=o30c, train/loss=4.000\r",
-      "Epoch 0:   5%| | 728/14932 [01:13<24:02,  9.85it/s, v_num=o30c, train/loss=3.640"
+      "Epoch 0:   5%| | 730/14932 [01:11<23:19, 10.15it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   5%| | 730/14932 [01:11<23:19, 10.14it/s, v_num=ui8w, train/loss=1.600"
      ]
     },
     {
@@ -7795,8 +7768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 729/14932 [01:13<24:01,  9.85it/s, v_num=o30c, train/loss=3.640\r",
-      "Epoch 0:   5%| | 729/14932 [01:13<24:01,  9.85it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   5%| | 731/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=1.600\r",
+      "Epoch 0:   5%| | 731/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -7804,8 +7777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 730/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=4.160\r",
-      "Epoch 0:   5%| | 730/14932 [01:14<24:01,  9.86it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   5%| | 732/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   5%| | 732/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=2.660"
      ]
     },
     {
@@ -7813,8 +7786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 731/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   5%| | 731/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=2.080"
+      "Epoch 0:   5%| | 733/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=2.660\r",
+      "Epoch 0:   5%| | 733/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -7822,8 +7795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 732/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=2.080\r",
-      "Epoch 0:   5%| | 732/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=2.310"
+      "Epoch 0:   5%| | 734/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   5%| | 734/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -7831,8 +7804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 733/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=2.310\r",
-      "Epoch 0:   5%| | 733/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=3.280"
+      "Epoch 0:   5%| | 735/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   5%| | 735/14932 [01:12<23:19, 10.15it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -7840,8 +7813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 734/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=3.280\r",
-      "Epoch 0:   5%| | 734/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   5%| | 736/14932 [01:12<23:20, 10.13it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   5%| | 736/14932 [01:12<23:20, 10.13it/s, v_num=ui8w, train/loss=1.820"
      ]
     },
     {
@@ -7849,8 +7822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 735/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   5%| | 735/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=2.880"
+      "Epoch 0:   5%| | 737/14932 [01:12<23:20, 10.14it/s, v_num=ui8w, train/loss=1.820\r",
+      "Epoch 0:   5%| | 737/14932 [01:12<23:20, 10.14it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -7858,8 +7831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 736/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=2.880\r",
-      "Epoch 0:   5%| | 736/14932 [01:14<24:00,  9.86it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   5%| | 738/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   5%| | 738/14932 [01:12<23:19, 10.14it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -7867,8 +7840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 737/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   5%| | 737/14932 [01:14<23:59,  9.86it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   5%| | 739/14932 [01:12<23:18, 10.15it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   5%| | 739/14932 [01:12<23:18, 10.15it/s, v_num=ui8w, train/loss=2.700"
      ]
     },
     {
@@ -7876,8 +7849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 738/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   5%| | 738/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   5%| | 740/14932 [01:12<23:18, 10.15it/s, v_num=ui8w, train/loss=2.700\r",
+      "Epoch 0:   5%| | 740/14932 [01:12<23:18, 10.15it/s, v_num=ui8w, train/loss=2.530"
      ]
     },
     {
@@ -7885,8 +7858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 739/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   5%| | 739/14932 [01:14<23:58,  9.87it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   5%| | 741/14932 [01:12<23:17, 10.15it/s, v_num=ui8w, train/loss=2.530\r",
+      "Epoch 0:   5%| | 741/14932 [01:12<23:17, 10.15it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -7894,8 +7867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 740/14932 [01:14<23:57,  9.87it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   5%| | 740/14932 [01:14<23:57,  9.87it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   5%| | 742/14932 [01:13<23:17, 10.16it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   5%| | 742/14932 [01:13<23:17, 10.16it/s, v_num=ui8w, train/loss=3.340"
      ]
     },
     {
@@ -7903,8 +7876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 741/14932 [01:15<23:56,  9.88it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   5%| | 741/14932 [01:15<23:56,  9.88it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   5%| | 743/14932 [01:13<23:16, 10.16it/s, v_num=ui8w, train/loss=3.340\r",
+      "Epoch 0:   5%| | 743/14932 [01:13<23:16, 10.16it/s, v_num=ui8w, train/loss=3.800"
      ]
     },
     {
@@ -7912,8 +7885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 742/14932 [01:15<23:56,  9.88it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   5%| | 742/14932 [01:15<23:56,  9.88it/s, v_num=o30c, train/loss=2.840"
+      "Epoch 0:   5%| | 744/14932 [01:13<23:15, 10.17it/s, v_num=ui8w, train/loss=3.800\r",
+      "Epoch 0:   5%| | 744/14932 [01:13<23:15, 10.17it/s, v_num=ui8w, train/loss=3.390"
      ]
     },
     {
@@ -7921,8 +7894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 743/14932 [01:15<23:55,  9.88it/s, v_num=o30c, train/loss=2.840\r",
-      "Epoch 0:   5%| | 743/14932 [01:15<23:55,  9.88it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   5%| | 745/14932 [01:13<23:15, 10.17it/s, v_num=ui8w, train/loss=3.390\r",
+      "Epoch 0:   5%| | 745/14932 [01:13<23:15, 10.17it/s, v_num=ui8w, train/loss=2.750"
      ]
     },
     {
@@ -7930,8 +7903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 744/14932 [01:15<23:55,  9.89it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   5%| | 744/14932 [01:15<23:55,  9.89it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   5%| | 746/14932 [01:13<23:14, 10.17it/s, v_num=ui8w, train/loss=2.750\r",
+      "Epoch 0:   5%| | 746/14932 [01:13<23:14, 10.17it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -7939,8 +7912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 745/14932 [01:15<23:54,  9.89it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   5%| | 745/14932 [01:15<23:54,  9.89it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   5%| | 747/14932 [01:13<23:14, 10.18it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   5%| | 747/14932 [01:13<23:14, 10.18it/s, v_num=ui8w, train/loss=2.380"
      ]
     },
     {
@@ -7948,8 +7921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 746/14932 [01:15<23:53,  9.89it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   5%| | 746/14932 [01:15<23:53,  9.89it/s, v_num=o30c, train/loss=1.930"
+      "Epoch 0:   5%| | 748/14932 [01:13<23:13, 10.18it/s, v_num=ui8w, train/loss=2.380\r",
+      "Epoch 0:   5%| | 748/14932 [01:13<23:13, 10.18it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -7957,8 +7930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 747/14932 [01:15<23:54,  9.89it/s, v_num=o30c, train/loss=1.930\r",
-      "Epoch 0:   5%| | 747/14932 [01:15<23:54,  9.89it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   5%| | 749/14932 [01:13<23:12, 10.18it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   5%| | 749/14932 [01:13<23:12, 10.18it/s, v_num=ui8w, train/loss=3.090"
      ]
     },
     {
@@ -7966,8 +7939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 748/14932 [01:15<23:53,  9.89it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   5%| | 748/14932 [01:15<23:53,  9.89it/s, v_num=o30c, train/loss=3.030"
+      "Epoch 0:   5%| | 750/14932 [01:13<23:12, 10.19it/s, v_num=ui8w, train/loss=3.090\r",
+      "Epoch 0:   5%| | 750/14932 [01:13<23:12, 10.19it/s, v_num=ui8w, train/loss=2.300"
      ]
     },
     {
@@ -7975,8 +7948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 749/14932 [01:15<23:53,  9.90it/s, v_num=o30c, train/loss=3.030\r",
-      "Epoch 0:   5%| | 749/14932 [01:15<23:53,  9.90it/s, v_num=o30c, train/loss=1.470"
+      "Epoch 0:   5%| | 751/14932 [01:13<23:11, 10.19it/s, v_num=ui8w, train/loss=2.300\r",
+      "Epoch 0:   5%| | 751/14932 [01:13<23:11, 10.19it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -7984,8 +7957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 750/14932 [01:15<23:52,  9.90it/s, v_num=o30c, train/loss=1.470\r",
-      "Epoch 0:   5%| | 750/14932 [01:15<23:52,  9.90it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   5%| | 752/14932 [01:13<23:11, 10.19it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   5%| | 752/14932 [01:13<23:11, 10.19it/s, v_num=ui8w, train/loss=3.250"
      ]
     },
     {
@@ -7993,8 +7966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 751/14932 [01:15<23:51,  9.90it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   5%| | 751/14932 [01:15<23:51,  9.90it/s, v_num=o30c, train/loss=2.380"
+      "Epoch 0:   5%| | 753/14932 [01:13<23:10, 10.20it/s, v_num=ui8w, train/loss=3.250\r",
+      "Epoch 0:   5%| | 753/14932 [01:13<23:10, 10.20it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -8002,8 +7975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 752/14932 [01:15<23:51,  9.91it/s, v_num=o30c, train/loss=2.380\r",
-      "Epoch 0:   5%| | 752/14932 [01:15<23:51,  9.91it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   5%| | 754/14932 [01:14<23:11, 10.19it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   5%| | 754/14932 [01:14<23:11, 10.19it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8011,8 +7984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 753/14932 [01:15<23:50,  9.91it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   5%| | 753/14932 [01:15<23:50,  9.91it/s, v_num=o30c, train/loss=2.120"
+      "Epoch 0:   5%| | 755/14932 [01:14<23:10, 10.19it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   5%| | 755/14932 [01:14<23:11, 10.19it/s, v_num=ui8w, train/loss=1.200"
      ]
     },
     {
@@ -8020,8 +7993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 754/14932 [01:16<23:50,  9.91it/s, v_num=o30c, train/loss=2.120\r",
-      "Epoch 0:   5%| | 754/14932 [01:16<23:50,  9.91it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   5%| | 756/14932 [01:14<23:10, 10.20it/s, v_num=ui8w, train/loss=1.200\r",
+      "Epoch 0:   5%| | 756/14932 [01:14<23:10, 10.20it/s, v_num=ui8w, train/loss=3.120"
      ]
     },
     {
@@ -8029,8 +8002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 755/14932 [01:16<23:49,  9.92it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   5%| | 755/14932 [01:16<23:49,  9.92it/s, v_num=o30c, train/loss=3.110"
+      "Epoch 0:   5%| | 757/14932 [01:14<23:14, 10.17it/s, v_num=ui8w, train/loss=3.120\r",
+      "Epoch 0:   5%| | 757/14932 [01:14<23:14, 10.17it/s, v_num=ui8w, train/loss=5.090"
      ]
     },
     {
@@ -8038,8 +8011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 756/14932 [01:16<23:48,  9.92it/s, v_num=o30c, train/loss=3.110\r",
-      "Epoch 0:   5%| | 756/14932 [01:16<23:48,  9.92it/s, v_num=o30c, train/loss=3.530"
+      "Epoch 0:   5%| | 758/14932 [01:14<23:13, 10.17it/s, v_num=ui8w, train/loss=5.090\r",
+      "Epoch 0:   5%| | 758/14932 [01:14<23:13, 10.17it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -8047,8 +8020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 757/14932 [01:16<23:48,  9.93it/s, v_num=o30c, train/loss=3.530\r",
-      "Epoch 0:   5%| | 757/14932 [01:16<23:48,  9.93it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   5%| | 759/14932 [01:14<23:13, 10.17it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   5%| | 759/14932 [01:14<23:13, 10.17it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -8056,8 +8029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 758/14932 [01:16<23:47,  9.93it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   5%| | 758/14932 [01:16<23:47,  9.93it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   5%| | 760/14932 [01:14<23:12, 10.18it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   5%| | 760/14932 [01:14<23:12, 10.18it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -8065,8 +8038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 759/14932 [01:16<23:46,  9.93it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   5%| | 759/14932 [01:16<23:46,  9.93it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   5%| | 761/14932 [01:14<23:11, 10.18it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   5%| | 761/14932 [01:14<23:11, 10.18it/s, v_num=ui8w, train/loss=2.840"
      ]
     },
     {
@@ -8074,8 +8047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 760/14932 [01:16<23:46,  9.94it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   5%| | 760/14932 [01:16<23:46,  9.94it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   5%| | 762/14932 [01:14<23:11, 10.18it/s, v_num=ui8w, train/loss=2.840\r",
+      "Epoch 0:   5%| | 762/14932 [01:14<23:11, 10.18it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -8083,8 +8056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 761/14932 [01:16<23:45,  9.94it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   5%| | 761/14932 [01:16<23:45,  9.94it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   5%| | 763/14932 [01:14<23:10, 10.19it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   5%| | 763/14932 [01:14<23:10, 10.19it/s, v_num=ui8w, train/loss=4.160"
      ]
     },
     {
@@ -8092,8 +8065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 762/14932 [01:16<23:44,  9.94it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   5%| | 762/14932 [01:16<23:44,  9.94it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   5%| | 764/14932 [01:14<23:10, 10.19it/s, v_num=ui8w, train/loss=4.160\r",
+      "Epoch 0:   5%| | 764/14932 [01:14<23:10, 10.19it/s, v_num=ui8w, train/loss=1.950"
      ]
     },
     {
@@ -8101,8 +8074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 763/14932 [01:16<23:44,  9.95it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   5%| | 763/14932 [01:16<23:44,  9.95it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   5%| | 765/14932 [01:15<23:09, 10.19it/s, v_num=ui8w, train/loss=1.950\r",
+      "Epoch 0:   5%| | 765/14932 [01:15<23:09, 10.19it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -8110,8 +8083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 764/14932 [01:16<23:43,  9.95it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   5%| | 764/14932 [01:16<23:43,  9.95it/s, v_num=o30c, train/loss=2.690"
+      "Epoch 0:   5%| | 766/14932 [01:15<23:09, 10.20it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   5%| | 766/14932 [01:15<23:09, 10.20it/s, v_num=ui8w, train/loss=2.220"
      ]
     },
     {
@@ -8119,8 +8092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 765/14932 [01:16<23:42,  9.96it/s, v_num=o30c, train/loss=2.690\r",
-      "Epoch 0:   5%| | 765/14932 [01:16<23:42,  9.96it/s, v_num=o30c, train/loss=2.340"
+      "Epoch 0:   5%| | 767/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=2.220\r",
+      "Epoch 0:   5%| | 767/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -8128,8 +8101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 766/14932 [01:16<23:42,  9.96it/s, v_num=o30c, train/loss=2.340\r",
-      "Epoch 0:   5%| | 766/14932 [01:16<23:42,  9.96it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   5%| | 768/14932 [01:15<23:10, 10.19it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   5%| | 768/14932 [01:15<23:10, 10.19it/s, v_num=ui8w, train/loss=2.800"
      ]
     },
     {
@@ -8137,8 +8110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 767/14932 [01:16<23:41,  9.96it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   5%| | 767/14932 [01:16<23:41,  9.96it/s, v_num=o30c, train/loss=1.960"
+      "Epoch 0:   5%| | 769/14932 [01:15<23:09, 10.19it/s, v_num=ui8w, train/loss=2.800\r",
+      "Epoch 0:   5%| | 769/14932 [01:15<23:09, 10.19it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -8146,8 +8119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 768/14932 [01:17<23:43,  9.95it/s, v_num=o30c, train/loss=1.960\r",
-      "Epoch 0:   5%| | 768/14932 [01:17<23:43,  9.95it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   5%| | 770/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   5%| | 770/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=2.660"
      ]
     },
     {
@@ -8155,8 +8128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 769/14932 [01:17<23:42,  9.96it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   5%| | 769/14932 [01:17<23:42,  9.96it/s, v_num=o30c, train/loss=3.910"
+      "Epoch 0:   5%| | 771/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=2.660\r",
+      "Epoch 0:   5%| | 771/14932 [01:15<23:08, 10.20it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -8164,8 +8137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 770/14932 [01:17<23:41,  9.96it/s, v_num=o30c, train/loss=3.910\r",
-      "Epoch 0:   5%| | 770/14932 [01:17<23:41,  9.96it/s, v_num=o30c, train/loss=2.770"
+      "Epoch 0:   5%| | 772/14932 [01:15<23:07, 10.20it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   5%| | 772/14932 [01:15<23:07, 10.20it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -8173,8 +8146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 771/14932 [01:17<23:41,  9.96it/s, v_num=o30c, train/loss=2.770\r",
-      "Epoch 0:   5%| | 771/14932 [01:17<23:41,  9.96it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   5%| | 773/14932 [01:15<23:06, 10.21it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   5%| | 773/14932 [01:15<23:06, 10.21it/s, v_num=ui8w, train/loss=1.510"
      ]
     },
     {
@@ -8182,8 +8155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 772/14932 [01:17<23:40,  9.97it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   5%| | 772/14932 [01:17<23:40,  9.97it/s, v_num=o30c, train/loss=2.270"
+      "Epoch 0:   5%| | 774/14932 [01:15<23:06, 10.21it/s, v_num=ui8w, train/loss=1.510\r",
+      "Epoch 0:   5%| | 774/14932 [01:15<23:06, 10.21it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -8191,8 +8164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 773/14932 [01:17<23:40,  9.97it/s, v_num=o30c, train/loss=2.270\r",
-      "Epoch 0:   5%| | 773/14932 [01:17<23:40,  9.97it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   5%| | 775/14932 [01:15<23:05, 10.22it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   5%| | 775/14932 [01:15<23:05, 10.22it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -8200,8 +8173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 774/14932 [01:17<23:39,  9.97it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   5%| | 774/14932 [01:17<23:39,  9.97it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   5%| | 776/14932 [01:15<23:05, 10.22it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   5%| | 776/14932 [01:15<23:05, 10.22it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -8209,8 +8182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 775/14932 [01:17<23:39,  9.98it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   5%| | 775/14932 [01:17<23:39,  9.98it/s, v_num=o30c, train/loss=2.280"
+      "Epoch 0:   5%| | 777/14932 [01:16<23:04, 10.22it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   5%| | 777/14932 [01:16<23:04, 10.22it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -8218,8 +8191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 776/14932 [01:17<23:38,  9.98it/s, v_num=o30c, train/loss=2.280\r",
-      "Epoch 0:   5%| | 776/14932 [01:17<23:38,  9.98it/s, v_num=o30c, train/loss=3.390"
+      "Epoch 0:   5%| | 778/14932 [01:16<23:04, 10.22it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   5%| | 778/14932 [01:16<23:04, 10.22it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -8227,8 +8200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 777/14932 [01:17<23:37,  9.98it/s, v_num=o30c, train/loss=3.390\r",
-      "Epoch 0:   5%| | 777/14932 [01:17<23:37,  9.98it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   5%| | 779/14932 [01:16<23:03, 10.23it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   5%| | 779/14932 [01:16<23:03, 10.23it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -8236,8 +8209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 778/14932 [01:17<23:37,  9.98it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   5%| | 778/14932 [01:17<23:37,  9.98it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   5%| | 780/14932 [01:16<23:03, 10.23it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   5%| | 780/14932 [01:16<23:03, 10.23it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -8245,8 +8218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 779/14932 [01:17<23:37,  9.99it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   5%| | 779/14932 [01:17<23:37,  9.99it/s, v_num=o30c, train/loss=2.860"
+      "Epoch 0:   5%| | 781/14932 [01:16<23:02, 10.23it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   5%| | 781/14932 [01:16<23:02, 10.23it/s, v_num=ui8w, train/loss=2.330"
      ]
     },
     {
@@ -8254,8 +8227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 780/14932 [01:18<23:36,  9.99it/s, v_num=o30c, train/loss=2.860\r",
-      "Epoch 0:   5%| | 780/14932 [01:18<23:36,  9.99it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   5%| | 782/14932 [01:16<23:02, 10.24it/s, v_num=ui8w, train/loss=2.330\r",
+      "Epoch 0:   5%| | 782/14932 [01:16<23:02, 10.24it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -8263,8 +8236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 781/14932 [01:18<23:35,  9.99it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   5%| | 781/14932 [01:18<23:35,  9.99it/s, v_num=o30c, train/loss=1.730"
+      "Epoch 0:   5%| | 783/14932 [01:16<23:01, 10.24it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   5%| | 783/14932 [01:16<23:01, 10.24it/s, v_num=ui8w, train/loss=2.230"
      ]
     },
     {
@@ -8272,8 +8245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 782/14932 [01:18<23:35, 10.00it/s, v_num=o30c, train/loss=1.730\r",
-      "Epoch 0:   5%| | 782/14932 [01:18<23:35, 10.00it/s, v_num=o30c, train/loss=2.340"
+      "Epoch 0:   5%| | 784/14932 [01:16<23:01, 10.24it/s, v_num=ui8w, train/loss=2.230\r",
+      "Epoch 0:   5%| | 784/14932 [01:16<23:01, 10.24it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -8281,8 +8254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 783/14932 [01:18<23:34, 10.00it/s, v_num=o30c, train/loss=2.340\r",
-      "Epoch 0:   5%| | 783/14932 [01:18<23:34, 10.00it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   5%| | 785/14932 [01:16<23:00, 10.25it/s, v_num=ui8w, train/loss=3.470\r",
+      "Epoch 0:   5%| | 785/14932 [01:16<23:00, 10.25it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -8290,8 +8263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 784/14932 [01:18<23:33, 10.01it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   5%| | 784/14932 [01:18<23:33, 10.01it/s, v_num=o30c, train/loss=4.380"
+      "Epoch 0:   5%| | 786/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   5%| | 786/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -8299,8 +8272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 785/14932 [01:18<23:33, 10.01it/s, v_num=o30c, train/loss=4.380\r",
-      "Epoch 0:   5%| | 785/14932 [01:18<23:33, 10.01it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   5%| | 787/14932 [01:16<23:00, 10.25it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   5%| | 787/14932 [01:16<23:00, 10.25it/s, v_num=ui8w, train/loss=3.910"
      ]
     },
     {
@@ -8308,8 +8281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 786/14932 [01:18<23:32, 10.01it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   5%| | 786/14932 [01:18<23:32, 10.01it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   5%| | 788/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.910\r",
+      "Epoch 0:   5%| | 788/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -8317,8 +8290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 787/14932 [01:18<23:32, 10.02it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   5%| | 787/14932 [01:18<23:32, 10.02it/s, v_num=o30c, train/loss=3.300"
+      "Epoch 0:   5%| | 789/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   5%| | 789/14932 [01:16<22:59, 10.25it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -8326,8 +8299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 788/14932 [01:18<23:31, 10.02it/s, v_num=o30c, train/loss=3.300\r",
-      "Epoch 0:   5%| | 788/14932 [01:18<23:31, 10.02it/s, v_num=o30c, train/loss=4.120"
+      "Epoch 0:   5%| | 790/14932 [01:17<22:58, 10.26it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   5%| | 790/14932 [01:17<22:58, 10.26it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -8335,8 +8308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 789/14932 [01:18<23:31, 10.02it/s, v_num=o30c, train/loss=4.120\r",
-      "Epoch 0:   5%| | 789/14932 [01:18<23:31, 10.02it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   5%| | 791/14932 [01:17<22:58, 10.26it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   5%| | 791/14932 [01:17<22:58, 10.26it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8344,8 +8317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 790/14932 [01:18<23:30, 10.03it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   5%| | 790/14932 [01:18<23:30, 10.03it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   5%| | 792/14932 [01:17<22:57, 10.26it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   5%| | 792/14932 [01:17<22:57, 10.26it/s, v_num=ui8w, train/loss=3.840"
      ]
     },
     {
@@ -8353,8 +8326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 791/14932 [01:18<23:29, 10.03it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   5%| | 791/14932 [01:18<23:29, 10.03it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   5%| | 793/14932 [01:17<22:57, 10.26it/s, v_num=ui8w, train/loss=3.840\r",
+      "Epoch 0:   5%| | 793/14932 [01:17<22:57, 10.26it/s, v_num=ui8w, train/loss=4.590"
      ]
     },
     {
@@ -8362,8 +8335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 792/14932 [01:18<23:30, 10.03it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   5%| | 792/14932 [01:18<23:30, 10.03it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   5%| | 794/14932 [01:17<22:57, 10.27it/s, v_num=ui8w, train/loss=4.590\r",
+      "Epoch 0:   5%| | 794/14932 [01:17<22:57, 10.27it/s, v_num=ui8w, train/loss=4.590"
      ]
     },
     {
@@ -8371,8 +8344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 793/14932 [01:19<23:29, 10.03it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   5%| | 793/14932 [01:19<23:29, 10.03it/s, v_num=o30c, train/loss=2.200"
+      "Epoch 0:   5%| | 795/14932 [01:17<22:56, 10.27it/s, v_num=ui8w, train/loss=4.590\r",
+      "Epoch 0:   5%| | 795/14932 [01:17<22:56, 10.27it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8380,8 +8353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 794/14932 [01:19<23:29, 10.03it/s, v_num=o30c, train/loss=2.200\r",
-      "Epoch 0:   5%| | 794/14932 [01:19<23:29, 10.03it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   5%| | 796/14932 [01:17<22:55, 10.27it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   5%| | 796/14932 [01:17<22:55, 10.27it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -8389,8 +8362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 795/14932 [01:19<23:35,  9.98it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   5%| | 795/14932 [01:19<23:35,  9.98it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   5%| | 797/14932 [01:17<22:55, 10.28it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   5%| | 797/14932 [01:17<22:55, 10.28it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -8398,8 +8371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 796/14932 [01:19<23:35,  9.99it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   5%| | 796/14932 [01:19<23:35,  9.99it/s, v_num=o30c, train/loss=2.660"
+      "Epoch 0:   5%| | 798/14932 [01:17<22:54, 10.28it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   5%| | 798/14932 [01:17<22:54, 10.28it/s, v_num=ui8w, train/loss=3.890"
      ]
     },
     {
@@ -8407,8 +8380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 797/14932 [01:19<23:34,  9.99it/s, v_num=o30c, train/loss=2.660\r",
-      "Epoch 0:   5%| | 797/14932 [01:19<23:34,  9.99it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   5%| | 799/14932 [01:17<22:54, 10.28it/s, v_num=ui8w, train/loss=3.890\r",
+      "Epoch 0:   5%| | 799/14932 [01:17<22:54, 10.28it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -8416,8 +8389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 798/14932 [01:19<23:34, 10.00it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   5%| | 798/14932 [01:19<23:34, 10.00it/s, v_num=o30c, train/loss=3.090"
+      "Epoch 0:   5%| | 800/14932 [01:17<22:56, 10.27it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   5%| | 800/14932 [01:17<22:56, 10.27it/s, v_num=ui8w, train/loss=3.060"
      ]
     },
     {
@@ -8425,8 +8398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 799/14932 [01:19<23:33, 10.00it/s, v_num=o30c, train/loss=3.090\r",
-      "Epoch 0:   5%| | 799/14932 [01:19<23:33, 10.00it/s, v_num=o30c, train/loss=4.910"
+      "Epoch 0:   5%| | 801/14932 [01:17<22:55, 10.27it/s, v_num=ui8w, train/loss=3.060\r",
+      "Epoch 0:   5%| | 801/14932 [01:17<22:55, 10.27it/s, v_num=ui8w, train/loss=1.260"
      ]
     },
     {
@@ -8434,8 +8407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 800/14932 [01:20<23:35,  9.99it/s, v_num=o30c, train/loss=4.910\r",
-      "Epoch 0:   5%| | 800/14932 [01:20<23:35,  9.99it/s, v_num=o30c, train/loss=3.050"
+      "Epoch 0:   5%| | 802/14932 [01:18<22:55, 10.28it/s, v_num=ui8w, train/loss=1.260\r",
+      "Epoch 0:   5%| | 802/14932 [01:18<22:55, 10.28it/s, v_num=ui8w, train/loss=4.560"
      ]
     },
     {
@@ -8443,8 +8416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 801/14932 [01:20<23:34,  9.99it/s, v_num=o30c, train/loss=3.050\r",
-      "Epoch 0:   5%| | 801/14932 [01:20<23:34,  9.99it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   5%| | 803/14932 [01:18<22:56, 10.26it/s, v_num=ui8w, train/loss=4.560\r",
+      "Epoch 0:   5%| | 803/14932 [01:18<22:56, 10.26it/s, v_num=ui8w, train/loss=3.530"
      ]
     },
     {
@@ -8452,8 +8425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 802/14932 [01:20<23:33,  9.99it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   5%| | 802/14932 [01:20<23:33,  9.99it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   5%| | 804/14932 [01:18<22:56, 10.27it/s, v_num=ui8w, train/loss=3.530\r",
+      "Epoch 0:   5%| | 804/14932 [01:18<22:56, 10.27it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8461,8 +8434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 803/14932 [01:20<23:33, 10.00it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   5%| | 803/14932 [01:20<23:33, 10.00it/s, v_num=o30c, train/loss=2.470"
+      "Epoch 0:   5%| | 805/14932 [01:18<22:55, 10.27it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   5%| | 805/14932 [01:18<22:55, 10.27it/s, v_num=ui8w, train/loss=4.440"
      ]
     },
     {
@@ -8470,8 +8443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 804/14932 [01:20<23:32, 10.00it/s, v_num=o30c, train/loss=2.470\r",
-      "Epoch 0:   5%| | 804/14932 [01:20<23:32, 10.00it/s, v_num=o30c, train/loss=3.660"
+      "Epoch 0:   5%| | 806/14932 [01:18<22:55, 10.27it/s, v_num=ui8w, train/loss=4.440\r",
+      "Epoch 0:   5%| | 806/14932 [01:18<22:55, 10.27it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -8479,8 +8452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 805/14932 [01:20<23:31, 10.01it/s, v_num=o30c, train/loss=3.660\r",
-      "Epoch 0:   5%| | 805/14932 [01:20<23:31, 10.01it/s, v_num=o30c, train/loss=2.780"
+      "Epoch 0:   5%| | 807/14932 [01:18<22:54, 10.27it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   5%| | 807/14932 [01:18<22:54, 10.27it/s, v_num=ui8w, train/loss=4.380"
      ]
     },
     {
@@ -8488,8 +8461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 806/14932 [01:20<23:31, 10.01it/s, v_num=o30c, train/loss=2.780\r",
-      "Epoch 0:   5%| | 806/14932 [01:20<23:31, 10.01it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   5%| | 808/14932 [01:18<22:54, 10.28it/s, v_num=ui8w, train/loss=4.380\r",
+      "Epoch 0:   5%| | 808/14932 [01:18<22:54, 10.28it/s, v_num=ui8w, train/loss=2.980"
      ]
     },
     {
@@ -8497,8 +8470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 807/14932 [01:20<23:30, 10.01it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   5%| | 807/14932 [01:20<23:30, 10.01it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   5%| | 809/14932 [01:18<22:53, 10.28it/s, v_num=ui8w, train/loss=2.980\r",
+      "Epoch 0:   5%| | 809/14932 [01:18<22:53, 10.28it/s, v_num=ui8w, train/loss=2.030"
      ]
     },
     {
@@ -8506,8 +8479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 808/14932 [01:20<23:30, 10.02it/s, v_num=o30c, train/loss=4.160\r",
-      "Epoch 0:   5%| | 808/14932 [01:20<23:30, 10.02it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   5%| | 810/14932 [01:18<22:53, 10.28it/s, v_num=ui8w, train/loss=2.030\r",
+      "Epoch 0:   5%| | 810/14932 [01:18<22:53, 10.28it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8515,8 +8488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 809/14932 [01:20<23:29, 10.02it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   5%| | 809/14932 [01:20<23:29, 10.02it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   5%| | 811/14932 [01:18<22:52, 10.29it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   5%| | 811/14932 [01:18<22:52, 10.29it/s, v_num=ui8w, train/loss=4.280"
      ]
     },
     {
@@ -8524,8 +8497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 810/14932 [01:20<23:28, 10.02it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   5%| | 810/14932 [01:20<23:28, 10.02it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   5%| | 812/14932 [01:18<22:52, 10.29it/s, v_num=ui8w, train/loss=4.280\r",
+      "Epoch 0:   5%| | 812/14932 [01:18<22:52, 10.29it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -8533,8 +8506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 811/14932 [01:20<23:28, 10.03it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   5%| | 811/14932 [01:20<23:28, 10.03it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   5%| | 813/14932 [01:18<22:51, 10.29it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   5%| | 813/14932 [01:18<22:51, 10.29it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -8542,8 +8515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 812/14932 [01:20<23:27, 10.03it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   5%| | 812/14932 [01:20<23:27, 10.03it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   5%| | 814/14932 [01:19<22:51, 10.30it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   5%| | 814/14932 [01:19<22:51, 10.30it/s, v_num=ui8w, train/loss=3.810"
      ]
     },
     {
@@ -8551,8 +8524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 813/14932 [01:21<23:26, 10.04it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   5%| | 813/14932 [01:21<23:26, 10.04it/s, v_num=o30c, train/loss=3.730"
+      "Epoch 0:   5%| | 815/14932 [01:19<22:51, 10.29it/s, v_num=ui8w, train/loss=3.810\r",
+      "Epoch 0:   5%| | 815/14932 [01:19<22:51, 10.29it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -8560,8 +8533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 814/14932 [01:21<23:26, 10.04it/s, v_num=o30c, train/loss=3.730\r",
-      "Epoch 0:   5%| | 814/14932 [01:21<23:26, 10.04it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   5%| | 816/14932 [01:19<22:51, 10.30it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   5%| | 816/14932 [01:19<22:51, 10.30it/s, v_num=ui8w, train/loss=3.440"
      ]
     },
     {
@@ -8569,8 +8542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 815/14932 [01:21<23:25, 10.04it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   5%| | 815/14932 [01:21<23:25, 10.04it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   5%| | 817/14932 [01:19<22:50, 10.30it/s, v_num=ui8w, train/loss=3.440\r",
+      "Epoch 0:   5%| | 817/14932 [01:19<22:50, 10.30it/s, v_num=ui8w, train/loss=1.160"
      ]
     },
     {
@@ -8578,8 +8551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 816/14932 [01:21<23:25, 10.04it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   5%| | 816/14932 [01:21<23:25, 10.04it/s, v_num=o30c, train/loss=2.090"
+      "Epoch 0:   5%| | 818/14932 [01:19<22:50, 10.30it/s, v_num=ui8w, train/loss=1.160\r",
+      "Epoch 0:   5%| | 818/14932 [01:19<22:50, 10.30it/s, v_num=ui8w, train/loss=2.640"
      ]
     },
     {
@@ -8587,8 +8560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 817/14932 [01:21<23:24, 10.05it/s, v_num=o30c, train/loss=2.090\r",
-      "Epoch 0:   5%| | 817/14932 [01:21<23:24, 10.05it/s, v_num=o30c, train/loss=3.220"
+      "Epoch 0:   5%| | 819/14932 [01:19<22:49, 10.30it/s, v_num=ui8w, train/loss=2.640\r",
+      "Epoch 0:   5%| | 819/14932 [01:19<22:49, 10.30it/s, v_num=ui8w, train/loss=2.690"
      ]
     },
     {
@@ -8596,8 +8569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 818/14932 [01:21<23:24, 10.05it/s, v_num=o30c, train/loss=3.220\r",
-      "Epoch 0:   5%| | 818/14932 [01:21<23:24, 10.05it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   5%| | 820/14932 [01:19<22:49, 10.31it/s, v_num=ui8w, train/loss=2.690\r",
+      "Epoch 0:   5%| | 820/14932 [01:19<22:49, 10.31it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -8605,8 +8578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 819/14932 [01:21<23:23, 10.05it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   5%| | 819/14932 [01:21<23:23, 10.05it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   5%| | 821/14932 [01:19<22:48, 10.31it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   5%| | 821/14932 [01:19<22:48, 10.31it/s, v_num=ui8w, train/loss=3.580"
      ]
     },
     {
@@ -8614,8 +8587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 820/14932 [01:21<23:23, 10.06it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   5%| | 820/14932 [01:21<23:23, 10.06it/s, v_num=o30c, train/loss=2.640"
+      "Epoch 0:   6%| | 822/14932 [01:19<22:48, 10.31it/s, v_num=ui8w, train/loss=3.580\r",
+      "Epoch 0:   6%| | 822/14932 [01:19<22:48, 10.31it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -8623,8 +8596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   5%| | 821/14932 [01:21<23:23, 10.05it/s, v_num=o30c, train/loss=2.640\r",
-      "Epoch 0:   5%| | 821/14932 [01:21<23:23, 10.05it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   6%| | 823/14932 [01:19<22:47, 10.32it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   6%| | 823/14932 [01:19<22:47, 10.32it/s, v_num=ui8w, train/loss=1.950"
      ]
     },
     {
@@ -8632,8 +8605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 822/14932 [01:21<23:22, 10.06it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   6%| | 822/14932 [01:21<23:23, 10.06it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   6%| | 824/14932 [01:19<22:46, 10.32it/s, v_num=ui8w, train/loss=1.950\r",
+      "Epoch 0:   6%| | 824/14932 [01:19<22:46, 10.32it/s, v_num=ui8w, train/loss=3.920"
      ]
     },
     {
@@ -8641,8 +8614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 823/14932 [01:21<23:22, 10.06it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   6%| | 823/14932 [01:21<23:22, 10.06it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   6%| | 825/14932 [01:19<22:46, 10.33it/s, v_num=ui8w, train/loss=3.920\r",
+      "Epoch 0:   6%| | 825/14932 [01:19<22:46, 10.33it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -8650,8 +8623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 824/14932 [01:21<23:22, 10.06it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   6%| | 824/14932 [01:21<23:22, 10.06it/s, v_num=o30c, train/loss=2.840"
+      "Epoch 0:   6%| | 826/14932 [01:19<22:45, 10.33it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   6%| | 826/14932 [01:19<22:45, 10.33it/s, v_num=ui8w, train/loss=1.190"
      ]
     },
     {
@@ -8659,8 +8632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 825/14932 [01:21<23:21, 10.07it/s, v_num=o30c, train/loss=2.840\r",
-      "Epoch 0:   6%| | 825/14932 [01:21<23:21, 10.07it/s, v_num=o30c, train/loss=1.330"
+      "Epoch 0:   6%| | 827/14932 [01:20<22:45, 10.33it/s, v_num=ui8w, train/loss=1.190\r",
+      "Epoch 0:   6%| | 827/14932 [01:20<22:45, 10.33it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -8668,8 +8641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 826/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=1.330\r",
-      "Epoch 0:   6%| | 826/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=1.800"
+      "Epoch 0:   6%| | 828/14932 [01:20<22:44, 10.33it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   6%| | 828/14932 [01:20<22:44, 10.33it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -8677,8 +8650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 827/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=1.800\r",
-      "Epoch 0:   6%| | 827/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   6%| | 829/14932 [01:20<22:44, 10.34it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   6%| | 829/14932 [01:20<22:44, 10.34it/s, v_num=ui8w, train/loss=2.060"
      ]
     },
     {
@@ -8686,8 +8659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 828/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   6%| | 828/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   6%| | 830/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=2.060\r",
+      "Epoch 0:   6%| | 830/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=2.560"
      ]
     },
     {
@@ -8695,8 +8668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 829/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   6%| | 829/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=2.050"
+      "Epoch 0:   6%| | 831/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=2.560\r",
+      "Epoch 0:   6%| | 831/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -8704,8 +8677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 830/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=2.050\r",
-      "Epoch 0:   6%| | 830/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   6%| | 832/14932 [01:20<22:44, 10.33it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   6%| | 832/14932 [01:20<22:44, 10.33it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -8713,8 +8686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 831/14932 [01:22<23:19, 10.08it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   6%| | 831/14932 [01:22<23:19, 10.08it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   6%| | 833/14932 [01:20<22:44, 10.34it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   6%| | 833/14932 [01:20<22:44, 10.34it/s, v_num=ui8w, train/loss=2.230"
      ]
     },
     {
@@ -8722,8 +8695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 832/14932 [01:22<23:20, 10.06it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   6%| | 832/14932 [01:22<23:20, 10.06it/s, v_num=o30c, train/loss=2.170"
+      "Epoch 0:   6%| | 834/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=2.230\r",
+      "Epoch 0:   6%| | 834/14932 [01:20<22:43, 10.34it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8731,8 +8704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 833/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=2.170\r",
-      "Epoch 0:   6%| | 833/14932 [01:22<23:20, 10.07it/s, v_num=o30c, train/loss=2.950"
+      "Epoch 0:   6%| | 835/14932 [01:21<22:49, 10.29it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   6%| | 835/14932 [01:21<22:49, 10.29it/s, v_num=ui8w, train/loss=3.750"
      ]
     },
     {
@@ -8740,8 +8713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 834/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=2.950\r",
-      "Epoch 0:   6%| | 834/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=3.230"
+      "Epoch 0:   6%| | 836/14932 [01:21<22:49, 10.29it/s, v_num=ui8w, train/loss=3.750\r",
+      "Epoch 0:   6%| | 836/14932 [01:21<22:49, 10.29it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -8749,8 +8722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 835/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=3.230\r",
-      "Epoch 0:   6%| | 835/14932 [01:22<23:19, 10.07it/s, v_num=o30c, train/loss=2.940"
+      "Epoch 0:   6%| | 837/14932 [01:21<22:48, 10.30it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   6%| | 837/14932 [01:21<22:48, 10.30it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -8758,8 +8731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 836/14932 [01:22<23:18, 10.08it/s, v_num=o30c, train/loss=2.940\r",
-      "Epoch 0:   6%| | 836/14932 [01:22<23:18, 10.08it/s, v_num=o30c, train/loss=3.500"
+      "Epoch 0:   6%| | 838/14932 [01:21<22:48, 10.30it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   6%| | 838/14932 [01:21<22:48, 10.30it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -8767,8 +8740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 837/14932 [01:23<23:18, 10.08it/s, v_num=o30c, train/loss=3.500\r",
-      "Epoch 0:   6%| | 837/14932 [01:23<23:18, 10.08it/s, v_num=o30c, train/loss=2.670"
+      "Epoch 0:   6%| | 839/14932 [01:21<22:47, 10.30it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   6%| | 839/14932 [01:21<22:47, 10.30it/s, v_num=ui8w, train/loss=3.390"
      ]
     },
     {
@@ -8776,8 +8749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 838/14932 [01:23<23:17, 10.08it/s, v_num=o30c, train/loss=2.670\r",
-      "Epoch 0:   6%| | 838/14932 [01:23<23:17, 10.08it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   6%| | 840/14932 [01:21<22:47, 10.31it/s, v_num=ui8w, train/loss=3.390\r",
+      "Epoch 0:   6%| | 840/14932 [01:21<22:47, 10.31it/s, v_num=ui8w, train/loss=3.020"
      ]
     },
     {
@@ -8785,8 +8758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 839/14932 [01:23<23:17, 10.09it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   6%| | 839/14932 [01:23<23:17, 10.09it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 841/14932 [01:21<22:46, 10.31it/s, v_num=ui8w, train/loss=3.020\r",
+      "Epoch 0:   6%| | 841/14932 [01:21<22:46, 10.31it/s, v_num=ui8w, train/loss=2.120"
      ]
     },
     {
@@ -8794,8 +8767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 840/14932 [01:23<23:16, 10.09it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 840/14932 [01:23<23:16, 10.09it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 842/14932 [01:21<22:46, 10.31it/s, v_num=ui8w, train/loss=2.120\r",
+      "Epoch 0:   6%| | 842/14932 [01:21<22:46, 10.31it/s, v_num=ui8w, train/loss=1.840"
      ]
     },
     {
@@ -8803,8 +8776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 841/14932 [01:23<23:16, 10.09it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 841/14932 [01:23<23:16, 10.09it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   6%| | 843/14932 [01:21<22:45, 10.32it/s, v_num=ui8w, train/loss=1.840\r",
+      "Epoch 0:   6%| | 843/14932 [01:21<22:45, 10.32it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -8812,8 +8785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 842/14932 [01:23<23:15, 10.09it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   6%| | 842/14932 [01:23<23:15, 10.09it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   6%| | 844/14932 [01:21<22:45, 10.32it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   6%| | 844/14932 [01:21<22:45, 10.32it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -8821,8 +8794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 843/14932 [01:23<23:15, 10.10it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   6%| | 843/14932 [01:23<23:15, 10.10it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   6%| | 845/14932 [01:21<22:44, 10.32it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   6%| | 845/14932 [01:21<22:44, 10.32it/s, v_num=ui8w, train/loss=2.250"
      ]
     },
     {
@@ -8830,8 +8803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 844/14932 [01:23<23:14, 10.10it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   6%| | 844/14932 [01:23<23:14, 10.10it/s, v_num=o30c, train/loss=2.800"
+      "Epoch 0:   6%| | 846/14932 [01:21<22:44, 10.33it/s, v_num=ui8w, train/loss=2.250\r",
+      "Epoch 0:   6%| | 846/14932 [01:21<22:44, 10.33it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -8839,8 +8812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 845/14932 [01:23<23:13, 10.11it/s, v_num=o30c, train/loss=2.800\r",
-      "Epoch 0:   6%| | 845/14932 [01:23<23:13, 10.11it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   6%| | 847/14932 [01:22<22:43, 10.33it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   6%| | 847/14932 [01:22<22:43, 10.33it/s, v_num=ui8w, train/loss=3.980"
      ]
     },
     {
@@ -8848,8 +8821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 846/14932 [01:23<23:14, 10.10it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   6%| | 846/14932 [01:23<23:14, 10.10it/s, v_num=o30c, train/loss=4.280"
+      "Epoch 0:   6%| | 848/14932 [01:22<22:43, 10.33it/s, v_num=ui8w, train/loss=3.980\r",
+      "Epoch 0:   6%| | 848/14932 [01:22<22:43, 10.33it/s, v_num=ui8w, train/loss=1.970"
      ]
     },
     {
@@ -8857,8 +8830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 847/14932 [01:23<23:13, 10.10it/s, v_num=o30c, train/loss=4.280\r",
-      "Epoch 0:   6%| | 847/14932 [01:23<23:13, 10.10it/s, v_num=o30c, train/loss=3.170"
+      "Epoch 0:   6%| | 849/14932 [01:22<22:42, 10.34it/s, v_num=ui8w, train/loss=1.970\r",
+      "Epoch 0:   6%| | 849/14932 [01:22<22:42, 10.34it/s, v_num=ui8w, train/loss=1.640"
      ]
     },
     {
@@ -8866,8 +8839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 848/14932 [01:23<23:13, 10.11it/s, v_num=o30c, train/loss=3.170\r",
-      "Epoch 0:   6%| | 848/14932 [01:23<23:13, 10.11it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   6%| | 850/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=1.640\r",
+      "Epoch 0:   6%| | 850/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.390"
      ]
     },
     {
@@ -8875,8 +8848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 849/14932 [01:23<23:12, 10.11it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   6%| | 849/14932 [01:23<23:12, 10.11it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 851/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.390\r",
+      "Epoch 0:   6%| | 851/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -8884,8 +8857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 850/14932 [01:24<23:12, 10.11it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 850/14932 [01:24<23:12, 10.11it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   6%| | 852/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   6%| | 852/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8893,8 +8866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 851/14932 [01:24<23:11, 10.12it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   6%| | 851/14932 [01:24<23:11, 10.12it/s, v_num=o30c, train/loss=3.200"
+      "Epoch 0:   6%| | 853/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   6%| | 853/14932 [01:22<22:41, 10.34it/s, v_num=ui8w, train/loss=1.290"
      ]
     },
     {
@@ -8902,8 +8875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 852/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.200\r",
-      "Epoch 0:   6%| | 852/14932 [01:24<23:11, 10.12it/s, v_num=o30c, train/loss=3.560"
+      "Epoch 0:   6%| | 854/14932 [01:22<22:40, 10.34it/s, v_num=ui8w, train/loss=1.290\r",
+      "Epoch 0:   6%| | 854/14932 [01:22<22:40, 10.34it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -8911,8 +8884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 853/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.560\r",
-      "Epoch 0:   6%| | 853/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.980"
+      "Epoch 0:   6%| | 855/14932 [01:22<22:40, 10.35it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   6%| | 855/14932 [01:22<22:40, 10.35it/s, v_num=ui8w, train/loss=2.230"
      ]
     },
     {
@@ -8920,8 +8893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 854/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=3.980\r",
-      "Epoch 0:   6%| | 854/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   6%| | 856/14932 [01:22<22:39, 10.35it/s, v_num=ui8w, train/loss=2.230\r",
+      "Epoch 0:   6%| | 856/14932 [01:22<22:39, 10.35it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -8929,8 +8902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 855/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   6%| | 855/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   6%| | 857/14932 [01:22<22:39, 10.35it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   6%| | 857/14932 [01:22<22:39, 10.35it/s, v_num=ui8w, train/loss=3.380"
      ]
     },
     {
@@ -8938,8 +8911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 856/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   6%| | 856/14932 [01:24<23:10, 10.12it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   6%| | 858/14932 [01:22<22:38, 10.36it/s, v_num=ui8w, train/loss=3.380\r",
+      "Epoch 0:   6%| | 858/14932 [01:22<22:38, 10.36it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -8947,8 +8920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 857/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   6%| | 857/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=1.780"
+      "Epoch 0:   6%| | 859/14932 [01:22<22:38, 10.36it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   6%| | 859/14932 [01:22<22:38, 10.36it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -8956,8 +8929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 858/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=1.780\r",
-      "Epoch 0:   6%| | 858/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=1.110"
+      "Epoch 0:   6%| | 860/14932 [01:22<22:37, 10.36it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   6%| | 860/14932 [01:22<22:37, 10.36it/s, v_num=ui8w, train/loss=2.140"
      ]
     },
     {
@@ -8965,8 +8938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 859/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=1.110\r",
-      "Epoch 0:   6%| | 859/14932 [01:24<23:09, 10.13it/s, v_num=o30c, train/loss=3.330"
+      "Epoch 0:   6%| | 861/14932 [01:23<22:37, 10.37it/s, v_num=ui8w, train/loss=2.140\r",
+      "Epoch 0:   6%| | 861/14932 [01:23<22:37, 10.37it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -8974,8 +8947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 860/14932 [01:24<23:08, 10.13it/s, v_num=o30c, train/loss=3.330\r",
-      "Epoch 0:   6%| | 860/14932 [01:24<23:08, 10.13it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   6%| | 862/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   6%| | 862/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=4.190"
      ]
     },
     {
@@ -8983,8 +8956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 861/14932 [01:24<23:08, 10.14it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   6%| | 861/14932 [01:24<23:08, 10.14it/s, v_num=o30c, train/loss=1.650"
+      "Epoch 0:   6%| | 863/14932 [01:23<22:35, 10.38it/s, v_num=ui8w, train/loss=4.190\r",
+      "Epoch 0:   6%| | 863/14932 [01:23<22:35, 10.38it/s, v_num=ui8w, train/loss=3.250"
      ]
     },
     {
@@ -8992,8 +8965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 862/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=1.650\r",
-      "Epoch 0:   6%| | 862/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 864/14932 [01:23<22:37, 10.36it/s, v_num=ui8w, train/loss=3.250\r",
+      "Epoch 0:   6%| | 864/14932 [01:23<22:37, 10.36it/s, v_num=ui8w, train/loss=3.550"
      ]
     },
     {
@@ -9001,8 +8974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 863/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 863/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   6%| | 865/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=3.550\r",
+      "Epoch 0:   6%| | 865/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=2.840"
      ]
     },
     {
@@ -9010,8 +8983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 864/14932 [01:25<23:08, 10.13it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   6%| | 864/14932 [01:25<23:08, 10.13it/s, v_num=o30c, train/loss=2.620"
+      "Epoch 0:   6%| | 866/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=2.840\r",
+      "Epoch 0:   6%| | 866/14932 [01:23<22:36, 10.37it/s, v_num=ui8w, train/loss=3.950"
      ]
     },
     {
@@ -9019,8 +8992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 865/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=2.620\r",
-      "Epoch 0:   6%| | 865/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 867/14932 [01:23<22:35, 10.37it/s, v_num=ui8w, train/loss=3.950\r",
+      "Epoch 0:   6%| | 867/14932 [01:23<22:35, 10.37it/s, v_num=ui8w, train/loss=2.970"
      ]
     },
     {
@@ -9028,8 +9001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 866/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 866/14932 [01:25<23:07, 10.14it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   6%| | 868/14932 [01:23<22:35, 10.38it/s, v_num=ui8w, train/loss=2.970\r",
+      "Epoch 0:   6%| | 868/14932 [01:23<22:35, 10.38it/s, v_num=ui8w, train/loss=2.700"
      ]
     },
     {
@@ -9037,8 +9010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 867/14932 [01:25<23:06, 10.14it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   6%| | 867/14932 [01:25<23:06, 10.14it/s, v_num=o30c, train/loss=2.050"
+      "Epoch 0:   6%| | 869/14932 [01:23<22:34, 10.38it/s, v_num=ui8w, train/loss=2.700\r",
+      "Epoch 0:   6%| | 869/14932 [01:23<22:34, 10.38it/s, v_num=ui8w, train/loss=3.800"
      ]
     },
     {
@@ -9046,8 +9019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 868/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=2.050\r",
-      "Epoch 0:   6%| | 868/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=4.840"
+      "Epoch 0:   6%| | 870/14932 [01:23<22:34, 10.38it/s, v_num=ui8w, train/loss=3.800\r",
+      "Epoch 0:   6%| | 870/14932 [01:23<22:34, 10.38it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -9055,8 +9028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 869/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=4.840\r",
-      "Epoch 0:   6%| | 869/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   6%| | 871/14932 [01:23<22:33, 10.39it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   6%| | 871/14932 [01:23<22:33, 10.39it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -9064,8 +9037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 870/14932 [01:25<23:04, 10.16it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   6%| | 870/14932 [01:25<23:04, 10.16it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   6%| | 872/14932 [01:23<22:33, 10.39it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   6%| | 872/14932 [01:23<22:33, 10.39it/s, v_num=ui8w, train/loss=2.830"
      ]
     },
     {
@@ -9073,8 +9046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 871/14932 [01:25<23:06, 10.14it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   6%| | 871/14932 [01:25<23:06, 10.14it/s, v_num=o30c, train/loss=5.160"
+      "Epoch 0:   6%| | 873/14932 [01:24<22:32, 10.39it/s, v_num=ui8w, train/loss=2.830\r",
+      "Epoch 0:   6%| | 873/14932 [01:24<22:32, 10.39it/s, v_num=ui8w, train/loss=2.340"
      ]
     },
     {
@@ -9082,8 +9055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 872/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=5.160\r",
-      "Epoch 0:   6%| | 872/14932 [01:25<23:05, 10.15it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   6%| | 874/14932 [01:24<22:32, 10.39it/s, v_num=ui8w, train/loss=2.340\r",
+      "Epoch 0:   6%| | 874/14932 [01:24<22:32, 10.39it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -9091,8 +9064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 873/14932 [01:25<23:04, 10.15it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   6%| | 873/14932 [01:26<23:04, 10.15it/s, v_num=o30c, train/loss=2.200"
+      "Epoch 0:   6%| | 875/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   6%| | 875/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=2.660"
      ]
     },
     {
@@ -9100,8 +9073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 874/14932 [01:26<23:04, 10.15it/s, v_num=o30c, train/loss=2.200\r",
-      "Epoch 0:   6%| | 874/14932 [01:26<23:04, 10.15it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   6%| | 876/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=2.660\r",
+      "Epoch 0:   6%| | 876/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=2.250"
      ]
     },
     {
@@ -9109,8 +9082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 875/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   6%| | 875/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=4.310"
+      "Epoch 0:   6%| | 877/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=2.250\r",
+      "Epoch 0:   6%| | 877/14932 [01:24<22:31, 10.40it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -9118,8 +9091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 876/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=4.310\r",
-      "Epoch 0:   6%| | 876/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=2.920"
+      "Epoch 0:   6%| | 878/14932 [01:24<22:30, 10.41it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   6%| | 878/14932 [01:24<22:30, 10.41it/s, v_num=ui8w, train/loss=3.330"
      ]
     },
     {
@@ -9127,8 +9100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 877/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=2.920\r",
-      "Epoch 0:   6%| | 877/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=2.910"
+      "Epoch 0:   6%| | 879/14932 [01:24<22:30, 10.41it/s, v_num=ui8w, train/loss=3.330\r",
+      "Epoch 0:   6%| | 879/14932 [01:24<22:30, 10.41it/s, v_num=ui8w, train/loss=4.500"
      ]
     },
     {
@@ -9136,8 +9109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 878/14932 [01:26<23:02, 10.16it/s, v_num=o30c, train/loss=2.910\r",
-      "Epoch 0:   6%| | 878/14932 [01:26<23:03, 10.16it/s, v_num=o30c, train/loss=2.860"
+      "Epoch 0:   6%| | 880/14932 [01:24<22:29, 10.41it/s, v_num=ui8w, train/loss=4.500\r",
+      "Epoch 0:   6%| | 880/14932 [01:24<22:29, 10.41it/s, v_num=ui8w, train/loss=4.000"
      ]
     },
     {
@@ -9145,8 +9118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 879/14932 [01:26<23:02, 10.17it/s, v_num=o30c, train/loss=2.860\r",
-      "Epoch 0:   6%| | 879/14932 [01:26<23:02, 10.17it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 881/14932 [01:24<22:29, 10.42it/s, v_num=ui8w, train/loss=4.000\r",
+      "Epoch 0:   6%| | 881/14932 [01:24<22:29, 10.41it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -9154,8 +9127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 880/14932 [01:26<23:01, 10.17it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 880/14932 [01:26<23:01, 10.17it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   6%| | 882/14932 [01:24<22:28, 10.42it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   6%| | 882/14932 [01:24<22:28, 10.42it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -9163,8 +9136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 881/14932 [01:26<23:01, 10.17it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   6%| | 881/14932 [01:26<23:01, 10.17it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   6%| | 883/14932 [01:24<22:28, 10.42it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   6%| | 883/14932 [01:24<22:28, 10.42it/s, v_num=ui8w, train/loss=2.250"
      ]
     },
     {
@@ -9172,8 +9145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 882/14932 [01:26<23:00, 10.18it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   6%| | 882/14932 [01:26<23:00, 10.18it/s, v_num=o30c, train/loss=2.090"
+      "Epoch 0:   6%| | 884/14932 [01:24<22:27, 10.43it/s, v_num=ui8w, train/loss=2.250\r",
+      "Epoch 0:   6%| | 884/14932 [01:24<22:27, 10.43it/s, v_num=ui8w, train/loss=3.170"
      ]
     },
     {
@@ -9181,8 +9154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 883/14932 [01:26<23:00, 10.18it/s, v_num=o30c, train/loss=2.090\r",
-      "Epoch 0:   6%| | 883/14932 [01:26<23:00, 10.18it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   6%| | 885/14932 [01:24<22:27, 10.43it/s, v_num=ui8w, train/loss=3.170\r",
+      "Epoch 0:   6%| | 885/14932 [01:24<22:27, 10.43it/s, v_num=ui8w, train/loss=2.770"
      ]
     },
     {
@@ -9190,8 +9163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 884/14932 [01:26<22:59, 10.18it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   6%| | 884/14932 [01:26<22:59, 10.18it/s, v_num=o30c, train/loss=1.790"
+      "Epoch 0:   6%| | 886/14932 [01:24<22:26, 10.43it/s, v_num=ui8w, train/loss=2.770\r",
+      "Epoch 0:   6%| | 886/14932 [01:24<22:26, 10.43it/s, v_num=ui8w, train/loss=3.920"
      ]
     },
     {
@@ -9199,8 +9172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 885/14932 [01:26<22:59, 10.18it/s, v_num=o30c, train/loss=1.790\r",
-      "Epoch 0:   6%| | 885/14932 [01:26<22:59, 10.18it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   6%| | 887/14932 [01:25<22:26, 10.43it/s, v_num=ui8w, train/loss=3.920\r",
+      "Epoch 0:   6%| | 887/14932 [01:25<22:26, 10.43it/s, v_num=ui8w, train/loss=3.660"
      ]
     },
     {
@@ -9208,8 +9181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 886/14932 [01:26<22:58, 10.19it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   6%| | 886/14932 [01:26<22:58, 10.19it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 888/14932 [01:25<22:25, 10.44it/s, v_num=ui8w, train/loss=3.660\r",
+      "Epoch 0:   6%| | 888/14932 [01:25<22:25, 10.44it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -9217,8 +9190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 887/14932 [01:27<22:58, 10.19it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 887/14932 [01:27<22:58, 10.19it/s, v_num=o30c, train/loss=2.450"
+      "Epoch 0:   6%| | 889/14932 [01:25<22:25, 10.44it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   6%| | 889/14932 [01:25<22:25, 10.44it/s, v_num=ui8w, train/loss=4.120"
      ]
     },
     {
@@ -9226,8 +9199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 888/14932 [01:27<22:57, 10.20it/s, v_num=o30c, train/loss=2.450\r",
-      "Epoch 0:   6%| | 888/14932 [01:27<22:57, 10.20it/s, v_num=o30c, train/loss=3.020"
+      "Epoch 0:   6%| | 890/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=4.120\r",
+      "Epoch 0:   6%| | 890/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=3.280"
      ]
     },
     {
@@ -9235,8 +9208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 889/14932 [01:27<22:58, 10.19it/s, v_num=o30c, train/loss=3.020\r",
-      "Epoch 0:   6%| | 889/14932 [01:27<22:58, 10.19it/s, v_num=o30c, train/loss=4.410"
+      "Epoch 0:   6%| | 891/14932 [01:25<22:24, 10.45it/s, v_num=ui8w, train/loss=3.280\r",
+      "Epoch 0:   6%| | 891/14932 [01:25<22:24, 10.45it/s, v_num=ui8w, train/loss=3.950"
      ]
     },
     {
@@ -9244,8 +9217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 890/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=4.410\r",
-      "Epoch 0:   6%| | 890/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=3.280"
+      "Epoch 0:   6%| | 892/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=3.950\r",
+      "Epoch 0:   6%| | 892/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=3.730"
      ]
     },
     {
@@ -9253,8 +9226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 891/14932 [01:27<22:57, 10.20it/s, v_num=o30c, train/loss=3.280\r",
-      "Epoch 0:   6%| | 891/14932 [01:27<22:57, 10.20it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 893/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=3.730\r",
+      "Epoch 0:   6%| | 893/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -9262,8 +9235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 892/14932 [01:27<22:56, 10.20it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 892/14932 [01:27<22:56, 10.20it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   6%| | 894/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   6%| | 894/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -9271,8 +9244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 893/14932 [01:27<22:56, 10.20it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   6%| | 893/14932 [01:27<22:56, 10.20it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   6%| | 895/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   6%| | 895/14932 [01:25<22:23, 10.45it/s, v_num=ui8w, train/loss=4.090"
      ]
     },
     {
@@ -9280,8 +9253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 894/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   6%| | 894/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=4.810"
+      "Epoch 0:   6%| | 896/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=4.090\r",
+      "Epoch 0:   6%| | 896/14932 [01:25<22:25, 10.44it/s, v_num=ui8w, train/loss=3.780"
      ]
     },
     {
@@ -9289,8 +9262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 895/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=4.810\r",
-      "Epoch 0:   6%| | 895/14932 [01:27<22:57, 10.19it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   6%| | 897/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=3.780\r",
+      "Epoch 0:   6%| | 897/14932 [01:25<22:24, 10.44it/s, v_num=ui8w, train/loss=2.340"
      ]
     },
     {
@@ -9298,8 +9271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 896/14932 [01:27<22:58, 10.18it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   6%| | 896/14932 [01:27<22:58, 10.18it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   6%| | 898/14932 [01:26<22:24, 10.44it/s, v_num=ui8w, train/loss=2.340\r",
+      "Epoch 0:   6%| | 898/14932 [01:26<22:24, 10.44it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -9307,8 +9280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 897/14932 [01:28<22:57, 10.19it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   6%| | 897/14932 [01:28<22:57, 10.19it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   6%| | 899/14932 [01:26<22:23, 10.44it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   6%| | 899/14932 [01:26<22:23, 10.44it/s, v_num=ui8w, train/loss=2.920"
      ]
     },
     {
@@ -9316,8 +9289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 898/14932 [01:28<22:57, 10.19it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   6%| | 898/14932 [01:28<22:57, 10.19it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   6%| | 900/14932 [01:26<22:23, 10.45it/s, v_num=ui8w, train/loss=2.920\r",
+      "Epoch 0:   6%| | 900/14932 [01:26<22:23, 10.45it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -9325,8 +9298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 899/14932 [01:28<22:56, 10.19it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   6%| | 899/14932 [01:28<22:56, 10.19it/s, v_num=o30c, train/loss=4.310"
+      "Epoch 0:   6%| | 901/14932 [01:26<22:22, 10.45it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   6%| | 901/14932 [01:26<22:22, 10.45it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -9334,8 +9307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 900/14932 [01:28<22:56, 10.19it/s, v_num=o30c, train/loss=4.310\r",
-      "Epoch 0:   6%| | 900/14932 [01:28<22:56, 10.19it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   6%| | 902/14932 [01:26<22:22, 10.45it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   6%| | 902/14932 [01:26<22:22, 10.45it/s, v_num=ui8w, train/loss=1.880"
      ]
     },
     {
@@ -9343,8 +9316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 901/14932 [01:28<22:56, 10.20it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   6%| | 901/14932 [01:28<22:56, 10.20it/s, v_num=o30c, train/loss=2.310"
+      "Epoch 0:   6%| | 903/14932 [01:26<22:21, 10.46it/s, v_num=ui8w, train/loss=1.880\r",
+      "Epoch 0:   6%| | 903/14932 [01:26<22:21, 10.46it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -9352,8 +9325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 902/14932 [01:28<22:55, 10.20it/s, v_num=o30c, train/loss=2.310\r",
-      "Epoch 0:   6%| | 902/14932 [01:28<22:55, 10.20it/s, v_num=o30c, train/loss=4.750"
+      "Epoch 0:   6%| | 904/14932 [01:26<22:21, 10.46it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   6%| | 904/14932 [01:26<22:21, 10.46it/s, v_num=ui8w, train/loss=4.310"
      ]
     },
     {
@@ -9361,8 +9334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 903/14932 [01:28<22:54, 10.20it/s, v_num=o30c, train/loss=4.750\r",
-      "Epoch 0:   6%| | 903/14932 [01:28<22:54, 10.20it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   6%| | 905/14932 [01:26<22:20, 10.46it/s, v_num=ui8w, train/loss=4.310\r",
+      "Epoch 0:   6%| | 905/14932 [01:26<22:20, 10.46it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -9370,8 +9343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 904/14932 [01:28<22:54, 10.21it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   6%| | 904/14932 [01:28<22:54, 10.21it/s, v_num=o30c, train/loss=2.590"
+      "Epoch 0:   6%| | 906/14932 [01:26<22:20, 10.47it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   6%| | 906/14932 [01:26<22:20, 10.47it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -9379,8 +9352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 905/14932 [01:28<22:54, 10.21it/s, v_num=o30c, train/loss=2.590\r",
-      "Epoch 0:   6%| | 905/14932 [01:28<22:54, 10.21it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 907/14932 [01:26<22:19, 10.47it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   6%| | 907/14932 [01:26<22:19, 10.47it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -9388,8 +9361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 906/14932 [01:28<22:53, 10.21it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 906/14932 [01:28<22:53, 10.21it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   6%| | 908/14932 [01:26<22:19, 10.47it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   6%| | 908/14932 [01:26<22:19, 10.47it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -9397,8 +9370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 907/14932 [01:28<22:53, 10.21it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   6%| | 907/14932 [01:28<22:53, 10.21it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   6%| | 909/14932 [01:26<22:18, 10.47it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   6%| | 909/14932 [01:26<22:18, 10.47it/s, v_num=ui8w, train/loss=2.780"
      ]
     },
     {
@@ -9406,8 +9379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 908/14932 [01:28<22:52, 10.22it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   6%| | 908/14932 [01:28<22:52, 10.22it/s, v_num=o30c, train/loss=3.000"
+      "Epoch 0:   6%| | 910/14932 [01:26<22:18, 10.48it/s, v_num=ui8w, train/loss=2.780\r",
+      "Epoch 0:   6%| | 910/14932 [01:26<22:18, 10.48it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -9415,8 +9388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 909/14932 [01:28<22:52, 10.22it/s, v_num=o30c, train/loss=3.000\r",
-      "Epoch 0:   6%| | 909/14932 [01:28<22:52, 10.22it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   6%| | 911/14932 [01:26<22:17, 10.48it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   6%| | 911/14932 [01:26<22:17, 10.48it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -9424,8 +9397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 910/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   6%| | 910/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=4.560"
+      "Epoch 0:   6%| | 912/14932 [01:27<22:17, 10.48it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   6%| | 912/14932 [01:27<22:17, 10.48it/s, v_num=ui8w, train/loss=3.140"
      ]
     },
     {
@@ -9433,8 +9406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 911/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=4.560\r",
-      "Epoch 0:   6%| | 911/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 913/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=3.140\r",
+      "Epoch 0:   6%| | 913/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=4.250"
      ]
     },
     {
@@ -9442,8 +9415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 912/14932 [01:29<22:52, 10.21it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 912/14932 [01:29<22:52, 10.21it/s, v_num=o30c, train/loss=4.060"
+      "Epoch 0:   6%| | 914/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=4.250\r",
+      "Epoch 0:   6%| | 914/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -9451,8 +9424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 913/14932 [01:29<22:52, 10.22it/s, v_num=o30c, train/loss=4.060\r",
-      "Epoch 0:   6%| | 913/14932 [01:29<22:52, 10.22it/s, v_num=o30c, train/loss=3.690"
+      "Epoch 0:   6%| | 915/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   6%| | 915/14932 [01:27<22:16, 10.49it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -9460,8 +9433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 914/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=3.690\r",
-      "Epoch 0:   6%| | 914/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=3.310"
+      "Epoch 0:   6%| | 916/14932 [01:27<22:15, 10.49it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   6%| | 916/14932 [01:27<22:15, 10.49it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -9469,8 +9442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 915/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=3.310\r",
-      "Epoch 0:   6%| | 915/14932 [01:29<22:51, 10.22it/s, v_num=o30c, train/loss=2.340"
+      "Epoch 0:   6%| | 917/14932 [01:27<22:15, 10.50it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   6%| | 917/14932 [01:27<22:15, 10.50it/s, v_num=ui8w, train/loss=3.590"
      ]
     },
     {
@@ -9478,8 +9451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 916/14932 [01:29<22:50, 10.22it/s, v_num=o30c, train/loss=2.340\r",
-      "Epoch 0:   6%| | 916/14932 [01:29<22:50, 10.22it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   6%| | 918/14932 [01:27<22:14, 10.50it/s, v_num=ui8w, train/loss=3.590\r",
+      "Epoch 0:   6%| | 918/14932 [01:27<22:14, 10.50it/s, v_num=ui8w, train/loss=3.560"
      ]
     },
     {
@@ -9487,8 +9460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 917/14932 [01:29<22:50, 10.23it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   6%| | 917/14932 [01:29<22:50, 10.23it/s, v_num=o30c, train/loss=1.410"
+      "Epoch 0:   6%| | 919/14932 [01:27<22:14, 10.50it/s, v_num=ui8w, train/loss=3.560\r",
+      "Epoch 0:   6%| | 919/14932 [01:27<22:14, 10.50it/s, v_num=ui8w, train/loss=3.080"
      ]
     },
     {
@@ -9496,8 +9469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 918/14932 [01:29<22:49, 10.23it/s, v_num=o30c, train/loss=1.410\r",
-      "Epoch 0:   6%| | 918/14932 [01:29<22:49, 10.23it/s, v_num=o30c, train/loss=4.470"
+      "Epoch 0:   6%| | 920/14932 [01:27<22:13, 10.50it/s, v_num=ui8w, train/loss=3.080\r",
+      "Epoch 0:   6%| | 920/14932 [01:27<22:13, 10.50it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -9505,8 +9478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 919/14932 [01:29<22:49, 10.23it/s, v_num=o30c, train/loss=4.470\r",
-      "Epoch 0:   6%| | 919/14932 [01:29<22:49, 10.23it/s, v_num=o30c, train/loss=4.250"
+      "Epoch 0:   6%| | 921/14932 [01:27<22:13, 10.51it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   6%| | 921/14932 [01:27<22:13, 10.51it/s, v_num=ui8w, train/loss=1.290"
      ]
     },
     {
@@ -9514,8 +9487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 920/14932 [01:30<22:52, 10.21it/s, v_num=o30c, train/loss=4.250\r",
-      "Epoch 0:   6%| | 920/14932 [01:30<22:52, 10.21it/s, v_num=o30c, train/loss=3.880"
+      "Epoch 0:   6%| | 922/14932 [01:27<22:12, 10.51it/s, v_num=ui8w, train/loss=1.290\r",
+      "Epoch 0:   6%| | 922/14932 [01:27<22:12, 10.51it/s, v_num=ui8w, train/loss=3.690"
      ]
     },
     {
@@ -9523,8 +9496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 921/14932 [01:30<22:51, 10.22it/s, v_num=o30c, train/loss=3.880\r",
-      "Epoch 0:   6%| | 921/14932 [01:30<22:51, 10.22it/s, v_num=o30c, train/loss=3.610"
+      "Epoch 0:   6%| | 923/14932 [01:27<22:12, 10.51it/s, v_num=ui8w, train/loss=3.690\r",
+      "Epoch 0:   6%| | 923/14932 [01:27<22:12, 10.51it/s, v_num=ui8w, train/loss=1.990"
      ]
     },
     {
@@ -9532,8 +9505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 922/14932 [01:30<22:51, 10.22it/s, v_num=o30c, train/loss=3.610\r",
-      "Epoch 0:   6%| | 922/14932 [01:30<22:51, 10.22it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   6%| | 924/14932 [01:27<22:11, 10.52it/s, v_num=ui8w, train/loss=1.990\r",
+      "Epoch 0:   6%| | 924/14932 [01:27<22:11, 10.52it/s, v_num=ui8w, train/loss=3.860"
      ]
     },
     {
@@ -9541,8 +9514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 923/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   6%| | 923/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   6%| | 925/14932 [01:27<22:11, 10.52it/s, v_num=ui8w, train/loss=3.860\r",
+      "Epoch 0:   6%| | 925/14932 [01:27<22:11, 10.52it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -9550,8 +9523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 924/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   6%| | 924/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=3.670"
+      "Epoch 0:   6%| | 926/14932 [01:27<22:10, 10.52it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   6%| | 926/14932 [01:27<22:10, 10.52it/s, v_num=ui8w, train/loss=3.920"
      ]
     },
     {
@@ -9559,8 +9532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 925/14932 [01:30<22:49, 10.22it/s, v_num=o30c, train/loss=3.670\r",
-      "Epoch 0:   6%| | 925/14932 [01:30<22:49, 10.22it/s, v_num=o30c, train/loss=3.890"
+      "Epoch 0:   6%| | 927/14932 [01:28<22:10, 10.53it/s, v_num=ui8w, train/loss=3.920\r",
+      "Epoch 0:   6%| | 927/14932 [01:28<22:10, 10.53it/s, v_num=ui8w, train/loss=4.060"
      ]
     },
     {
@@ -9568,8 +9541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 926/14932 [01:30<22:49, 10.23it/s, v_num=o30c, train/loss=3.890\r",
-      "Epoch 0:   6%| | 926/14932 [01:30<22:49, 10.23it/s, v_num=o30c, train/loss=3.770"
+      "Epoch 0:   6%| | 928/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=4.060\r",
+      "Epoch 0:   6%| | 928/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=3.110"
      ]
     },
     {
@@ -9577,8 +9550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 927/14932 [01:30<22:48, 10.23it/s, v_num=o30c, train/loss=3.770\r",
-      "Epoch 0:   6%| | 927/14932 [01:30<22:48, 10.23it/s, v_num=o30c, train/loss=4.030"
+      "Epoch 0:   6%| | 929/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=3.110\r",
+      "Epoch 0:   6%| | 929/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=4.410"
      ]
     },
     {
@@ -9586,8 +9559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 928/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=4.030\r",
-      "Epoch 0:   6%| | 928/14932 [01:30<22:50, 10.22it/s, v_num=o30c, train/loss=4.160"
+      "Epoch 0:   6%| | 930/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=4.410\r",
+      "Epoch 0:   6%| | 930/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -9595,8 +9568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 929/14932 [01:30<22:49, 10.22it/s, v_num=o30c, train/loss=4.160\r",
-      "Epoch 0:   6%| | 929/14932 [01:30<22:49, 10.22it/s, v_num=o30c, train/loss=2.500"
+      "Epoch 0:   6%| | 931/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   6%| | 931/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=3.310"
      ]
     },
     {
@@ -9604,8 +9577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 930/14932 [01:30<22:49, 10.23it/s, v_num=o30c, train/loss=2.500\r",
-      "Epoch 0:   6%| | 930/14932 [01:30<22:49, 10.23it/s, v_num=o30c, train/loss=4.220"
+      "Epoch 0:   6%| | 932/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=3.310\r",
+      "Epoch 0:   6%| | 932/14932 [01:28<22:11, 10.52it/s, v_num=ui8w, train/loss=3.300"
      ]
     },
     {
@@ -9613,8 +9586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 931/14932 [01:31<22:48, 10.23it/s, v_num=o30c, train/loss=4.220\r",
-      "Epoch 0:   6%| | 931/14932 [01:31<22:48, 10.23it/s, v_num=o30c, train/loss=1.840"
+      "Epoch 0:   6%| | 933/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=3.300\r",
+      "Epoch 0:   6%| | 933/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=4.340"
      ]
     },
     {
@@ -9622,8 +9595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 932/14932 [01:31<22:48, 10.23it/s, v_num=o30c, train/loss=1.840\r",
-      "Epoch 0:   6%| | 932/14932 [01:31<22:48, 10.23it/s, v_num=o30c, train/loss=1.380"
+      "Epoch 0:   6%| | 934/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=4.340\r",
+      "Epoch 0:   6%| | 934/14932 [01:28<22:11, 10.51it/s, v_num=ui8w, train/loss=4.280"
      ]
     },
     {
@@ -9631,8 +9604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 933/14932 [01:31<22:47, 10.23it/s, v_num=o30c, train/loss=1.380\r",
-      "Epoch 0:   6%| | 933/14932 [01:31<22:47, 10.23it/s, v_num=o30c, train/loss=2.530"
+      "Epoch 0:   6%| | 935/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=4.280\r",
+      "Epoch 0:   6%| | 935/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -9640,8 +9613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 934/14932 [01:31<22:47, 10.24it/s, v_num=o30c, train/loss=2.530\r",
-      "Epoch 0:   6%| | 934/14932 [01:31<22:47, 10.24it/s, v_num=o30c, train/loss=2.860"
+      "Epoch 0:   6%| | 936/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   6%| | 936/14932 [01:28<22:10, 10.52it/s, v_num=ui8w, train/loss=2.520"
      ]
     },
     {
@@ -9649,8 +9622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 935/14932 [01:31<22:46, 10.24it/s, v_num=o30c, train/loss=2.860\r",
-      "Epoch 0:   6%| | 935/14932 [01:31<22:46, 10.24it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   6%| | 937/14932 [01:29<22:10, 10.52it/s, v_num=ui8w, train/loss=2.520\r",
+      "Epoch 0:   6%| | 937/14932 [01:29<22:10, 10.52it/s, v_num=ui8w, train/loss=1.540"
      ]
     },
     {
@@ -9658,8 +9631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 936/14932 [01:31<22:46, 10.24it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   6%| | 936/14932 [01:31<22:46, 10.24it/s, v_num=o30c, train/loss=2.780"
+      "Epoch 0:   6%| | 938/14932 [01:29<22:09, 10.53it/s, v_num=ui8w, train/loss=1.540\r",
+      "Epoch 0:   6%| | 938/14932 [01:29<22:09, 10.53it/s, v_num=ui8w, train/loss=1.930"
      ]
     },
     {
@@ -9667,8 +9640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 937/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=2.780\r",
-      "Epoch 0:   6%| | 937/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=2.050"
+      "Epoch 0:   6%| | 939/14932 [01:29<22:08, 10.53it/s, v_num=ui8w, train/loss=1.930\r",
+      "Epoch 0:   6%| | 939/14932 [01:29<22:08, 10.53it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -9676,8 +9649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 938/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=2.050\r",
-      "Epoch 0:   6%| | 938/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   6%| | 940/14932 [01:29<22:08, 10.53it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   6%| | 940/14932 [01:29<22:08, 10.53it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -9685,8 +9658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 939/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   6%| | 939/14932 [01:31<22:45, 10.25it/s, v_num=o30c, train/loss=3.450"
+      "Epoch 0:   6%| | 941/14932 [01:29<22:07, 10.54it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   6%| | 941/14932 [01:29<22:08, 10.54it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -9694,8 +9667,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 940/14932 [01:31<22:44, 10.25it/s, v_num=o30c, train/loss=3.450\r",
-      "Epoch 0:   6%| | 940/14932 [01:31<22:44, 10.25it/s, v_num=o30c, train/loss=2.880"
+      "Epoch 0:   6%| | 942/14932 [01:29<22:07, 10.54it/s, v_num=ui8w, train/loss=3.470"
      ]
     },
     {
@@ -9703,8 +9675,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 941/14932 [01:31<22:44, 10.26it/s, v_num=o30c, train/loss=2.880\r",
-      "Epoch 0:   6%| | 941/14932 [01:31<22:44, 10.26it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   6%| | 942/14932 [01:29<22:07, 10.54it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -9712,8 +9683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 942/14932 [01:31<22:43, 10.26it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   6%| | 942/14932 [01:31<22:43, 10.26it/s, v_num=o30c, train/loss=3.480"
+      "Epoch 0:   6%| | 943/14932 [01:29<22:07, 10.54it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   6%| | 943/14932 [01:29<22:07, 10.54it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -9721,8 +9692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 943/14932 [01:31<22:43, 10.26it/s, v_num=o30c, train/loss=3.480\r",
-      "Epoch 0:   6%| | 943/14932 [01:31<22:43, 10.26it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   6%| | 944/14932 [01:29<22:06, 10.54it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   6%| | 944/14932 [01:29<22:06, 10.54it/s, v_num=ui8w, train/loss=3.480"
      ]
     },
     {
@@ -9730,8 +9701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 944/14932 [01:31<22:42, 10.26it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   6%| | 944/14932 [01:31<22:42, 10.26it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   6%| | 945/14932 [01:29<22:06, 10.55it/s, v_num=ui8w, train/loss=3.480\r",
+      "Epoch 0:   6%| | 945/14932 [01:29<22:06, 10.55it/s, v_num=ui8w, train/loss=3.410"
      ]
     },
     {
@@ -9739,8 +9710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 945/14932 [01:32<22:42, 10.27it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   6%| | 945/14932 [01:32<22:42, 10.27it/s, v_num=o30c, train/loss=2.840"
+      "Epoch 0:   6%| | 946/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=3.410\r",
+      "Epoch 0:   6%| | 946/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -9748,8 +9719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 946/14932 [01:32<22:41, 10.27it/s, v_num=o30c, train/loss=2.840\r",
-      "Epoch 0:   6%| | 946/14932 [01:32<22:41, 10.27it/s, v_num=o30c, train/loss=3.270"
+      "Epoch 0:   6%| | 947/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   6%| | 947/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=2.560"
      ]
     },
     {
@@ -9757,8 +9728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 947/14932 [01:32<22:41, 10.27it/s, v_num=o30c, train/loss=3.270\r",
-      "Epoch 0:   6%| | 947/14932 [01:32<22:41, 10.27it/s, v_num=o30c, train/loss=4.090"
+      "Epoch 0:   6%| | 948/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=2.560\r",
+      "Epoch 0:   6%| | 948/14932 [01:29<22:05, 10.55it/s, v_num=ui8w, train/loss=2.480"
      ]
     },
     {
@@ -9766,8 +9737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 948/14932 [01:32<22:40, 10.28it/s, v_num=o30c, train/loss=4.090\r",
-      "Epoch 0:   6%| | 948/14932 [01:32<22:40, 10.27it/s, v_num=o30c, train/loss=4.690"
+      "Epoch 0:   6%| | 949/14932 [01:29<22:04, 10.56it/s, v_num=ui8w, train/loss=2.480\r",
+      "Epoch 0:   6%| | 949/14932 [01:29<22:04, 10.56it/s, v_num=ui8w, train/loss=2.520"
      ]
     },
     {
@@ -9775,8 +9746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 949/14932 [01:32<22:40, 10.28it/s, v_num=o30c, train/loss=4.690\r",
-      "Epoch 0:   6%| | 949/14932 [01:32<22:40, 10.28it/s, v_num=o30c, train/loss=3.380"
+      "Epoch 0:   6%| | 950/14932 [01:29<22:04, 10.56it/s, v_num=ui8w, train/loss=2.520\r",
+      "Epoch 0:   6%| | 950/14932 [01:29<22:04, 10.56it/s, v_num=ui8w, train/loss=2.310"
      ]
     },
     {
@@ -9784,8 +9755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 950/14932 [01:32<22:40, 10.28it/s, v_num=o30c, train/loss=3.380\r",
-      "Epoch 0:   6%| | 950/14932 [01:32<22:40, 10.28it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   6%| | 951/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=2.310\r",
+      "Epoch 0:   6%| | 951/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=3.620"
      ]
     },
     {
@@ -9793,8 +9764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 951/14932 [01:32<22:39, 10.28it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   6%| | 951/14932 [01:32<22:39, 10.28it/s, v_num=o30c, train/loss=3.200"
+      "Epoch 0:   6%| | 952/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=3.620\r",
+      "Epoch 0:   6%| | 952/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=3.030"
      ]
     },
     {
@@ -9802,8 +9773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 952/14932 [01:32<22:39, 10.29it/s, v_num=o30c, train/loss=3.200\r",
-      "Epoch 0:   6%| | 952/14932 [01:32<22:39, 10.29it/s, v_num=o30c, train/loss=3.920"
+      "Epoch 0:   6%| | 953/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=3.030\r",
+      "Epoch 0:   6%| | 953/14932 [01:30<22:03, 10.56it/s, v_num=ui8w, train/loss=3.420"
      ]
     },
     {
@@ -9811,8 +9782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 953/14932 [01:32<22:38, 10.29it/s, v_num=o30c, train/loss=3.920\r",
-      "Epoch 0:   6%| | 953/14932 [01:32<22:38, 10.29it/s, v_num=o30c, train/loss=3.190"
+      "Epoch 0:   6%| | 954/14932 [01:30<22:02, 10.57it/s, v_num=ui8w, train/loss=3.420\r",
+      "Epoch 0:   6%| | 954/14932 [01:30<22:02, 10.57it/s, v_num=ui8w, train/loss=3.670"
      ]
     },
     {
@@ -9820,8 +9791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 954/14932 [01:32<22:38, 10.29it/s, v_num=o30c, train/loss=3.190\r",
-      "Epoch 0:   6%| | 954/14932 [01:32<22:38, 10.29it/s, v_num=o30c, train/loss=3.980"
+      "Epoch 0:   6%| | 955/14932 [01:30<22:02, 10.57it/s, v_num=ui8w, train/loss=3.670\r",
+      "Epoch 0:   6%| | 955/14932 [01:30<22:02, 10.57it/s, v_num=ui8w, train/loss=2.020"
      ]
     },
     {
@@ -9829,8 +9800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 955/14932 [01:32<22:37, 10.29it/s, v_num=o30c, train/loss=3.980\r",
-      "Epoch 0:   6%| | 955/14932 [01:32<22:37, 10.29it/s, v_num=o30c, train/loss=4.340"
+      "Epoch 0:   6%| | 956/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=2.020\r",
+      "Epoch 0:   6%| | 956/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=2.480"
      ]
     },
     {
@@ -9838,8 +9809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 956/14932 [01:32<22:37, 10.30it/s, v_num=o30c, train/loss=4.340\r",
-      "Epoch 0:   6%| | 956/14932 [01:32<22:37, 10.30it/s, v_num=o30c, train/loss=2.980"
+      "Epoch 0:   6%| | 957/14932 [01:30<22:01, 10.58it/s, v_num=ui8w, train/loss=2.480\r",
+      "Epoch 0:   6%| | 957/14932 [01:30<22:01, 10.58it/s, v_num=ui8w, train/loss=3.050"
      ]
     },
     {
@@ -9847,8 +9818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 957/14932 [01:32<22:37, 10.30it/s, v_num=o30c, train/loss=2.980\r",
-      "Epoch 0:   6%| | 957/14932 [01:32<22:37, 10.30it/s, v_num=o30c, train/loss=3.860"
+      "Epoch 0:   6%| | 958/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=3.050\r",
+      "Epoch 0:   6%| | 958/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=2.940"
      ]
     },
     {
@@ -9856,8 +9827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 958/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.860\r",
-      "Epoch 0:   6%| | 958/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   6%| | 959/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=2.940\r",
+      "Epoch 0:   6%| | 959/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -9865,8 +9836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 959/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   6%| | 959/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=2.750"
+      "Epoch 0:   6%| | 960/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   6%| | 960/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=2.880"
      ]
     },
     {
@@ -9874,8 +9845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 960/14932 [01:33<22:37, 10.29it/s, v_num=o30c, train/loss=2.750\r",
-      "Epoch 0:   6%| | 960/14932 [01:33<22:37, 10.29it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   6%| | 961/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=2.880\r",
+      "Epoch 0:   6%| | 961/14932 [01:30<22:01, 10.57it/s, v_num=ui8w, train/loss=3.720"
      ]
     },
     {
@@ -9883,8 +9854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 961/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   6%| | 961/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.810"
+      "Epoch 0:   6%| | 962/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=3.720\r",
+      "Epoch 0:   6%| | 962/14932 [01:30<22:00, 10.58it/s, v_num=ui8w, train/loss=2.520"
      ]
     },
     {
@@ -9892,8 +9863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 962/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.810\r",
-      "Epoch 0:   6%| | 962/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.120"
+      "Epoch 0:   6%| | 963/14932 [01:31<22:00, 10.58it/s, v_num=ui8w, train/loss=2.520\r",
+      "Epoch 0:   6%| | 963/14932 [01:31<22:00, 10.58it/s, v_num=ui8w, train/loss=2.610"
      ]
     },
     {
@@ -9901,8 +9872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 963/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=3.120\r",
-      "Epoch 0:   6%| | 963/14932 [01:33<22:36, 10.30it/s, v_num=o30c, train/loss=2.390"
+      "Epoch 0:   6%| | 964/14932 [01:31<21:59, 10.58it/s, v_num=ui8w, train/loss=2.610\r",
+      "Epoch 0:   6%| | 964/14932 [01:31<21:59, 10.58it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -9910,8 +9881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 964/14932 [01:33<22:35, 10.30it/s, v_num=o30c, train/loss=2.390\r",
-      "Epoch 0:   6%| | 964/14932 [01:33<22:35, 10.30it/s, v_num=o30c, train/loss=3.420"
+      "Epoch 0:   6%| | 965/14932 [01:31<21:59, 10.58it/s, v_num=ui8w, train/loss=2.720\r",
+      "Epoch 0:   6%| | 965/14932 [01:31<21:59, 10.58it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -9919,8 +9890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 965/14932 [01:33<22:35, 10.31it/s, v_num=o30c, train/loss=3.420\r",
-      "Epoch 0:   6%| | 965/14932 [01:33<22:35, 10.31it/s, v_num=o30c, train/loss=1.610"
+      "Epoch 0:   6%| | 966/14932 [01:31<21:59, 10.59it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   6%| | 966/14932 [01:31<21:59, 10.59it/s, v_num=ui8w, train/loss=3.970"
      ]
     },
     {
@@ -9928,8 +9899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 966/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=1.610\r",
-      "Epoch 0:   6%| | 966/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=3.590"
+      "Epoch 0:   6%| | 967/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=3.970\r",
+      "Epoch 0:   6%| | 967/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -9937,8 +9908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 967/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=3.590\r",
-      "Epoch 0:   6%| | 967/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=3.250"
+      "Epoch 0:   6%| | 968/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   6%| | 968/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=2.690"
      ]
     },
     {
@@ -9946,8 +9917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 968/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=3.250\r",
-      "Epoch 0:   6%| | 968/14932 [01:33<22:34, 10.31it/s, v_num=o30c, train/loss=3.410"
+      "Epoch 0:   6%| | 969/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=2.690\r",
+      "Epoch 0:   6%| | 969/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=2.730"
      ]
     },
     {
@@ -9955,8 +9926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 969/14932 [01:33<22:33, 10.32it/s, v_num=o30c, train/loss=3.410\r",
-      "Epoch 0:   6%| | 969/14932 [01:33<22:33, 10.32it/s, v_num=o30c, train/loss=2.550"
+      "Epoch 0:   6%| | 970/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=2.730\r",
+      "Epoch 0:   6%| | 970/14932 [01:31<21:58, 10.59it/s, v_num=ui8w, train/loss=3.880"
      ]
     },
     {
@@ -9964,8 +9935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   6%| | 970/14932 [01:34<22:33, 10.32it/s, v_num=o30c, train/loss=2.550\r",
-      "Epoch 0:   6%| | 970/14932 [01:34<22:33, 10.32it/s, v_num=o30c, train/loss=5.030"
+      "Epoch 0:   7%| | 971/14932 [01:31<21:57, 10.59it/s, v_num=ui8w, train/loss=3.880\r",
+      "Epoch 0:   7%| | 971/14932 [01:31<21:57, 10.59it/s, v_num=ui8w, train/loss=3.190"
      ]
     },
     {
@@ -9973,8 +9944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 971/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=5.030\r",
-      "Epoch 0:   7%| | 971/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=3.620"
+      "Epoch 0:   7%| | 972/14932 [01:31<21:57, 10.60it/s, v_num=ui8w, train/loss=3.190\r",
+      "Epoch 0:   7%| | 972/14932 [01:31<21:57, 10.60it/s, v_num=ui8w, train/loss=3.160"
      ]
     },
     {
@@ -9982,8 +9953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 972/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=3.620\r",
-      "Epoch 0:   7%| | 972/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=3.780"
+      "Epoch 0:   7%| | 973/14932 [01:31<21:57, 10.60it/s, v_num=ui8w, train/loss=3.160\r",
+      "Epoch 0:   7%| | 973/14932 [01:31<21:57, 10.60it/s, v_num=ui8w, train/loss=2.330"
      ]
     },
     {
@@ -9991,8 +9962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 973/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=3.780\r",
-      "Epoch 0:   7%| | 973/14932 [01:34<22:32, 10.32it/s, v_num=o30c, train/loss=3.970"
+      "Epoch 0:   7%| | 974/14932 [01:31<21:56, 10.60it/s, v_num=ui8w, train/loss=2.330\r",
+      "Epoch 0:   7%| | 974/14932 [01:31<21:56, 10.60it/s, v_num=ui8w, train/loss=3.440"
      ]
     },
     {
@@ -10000,8 +9971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 974/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=3.970\r",
-      "Epoch 0:   7%| | 974/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   7%| | 975/14932 [01:31<21:56, 10.60it/s, v_num=ui8w, train/loss=3.440\r",
+      "Epoch 0:   7%| | 975/14932 [01:31<21:56, 10.60it/s, v_num=ui8w, train/loss=3.200"
      ]
     },
     {
@@ -10009,8 +9980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 975/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   7%| | 975/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   7%| | 976/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.200\r",
+      "Epoch 0:   7%| | 976/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.520"
      ]
     },
     {
@@ -10018,8 +9989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 976/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   7%| | 976/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=4.440"
+      "Epoch 0:   7%| | 977/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.520\r",
+      "Epoch 0:   7%| | 977/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.610"
      ]
     },
     {
@@ -10027,8 +9998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 977/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=4.440\r",
-      "Epoch 0:   7%| | 977/14932 [01:34<22:31, 10.33it/s, v_num=o30c, train/loss=3.340"
+      "Epoch 0:   7%| | 978/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.610\r",
+      "Epoch 0:   7%| | 978/14932 [01:32<21:55, 10.61it/s, v_num=ui8w, train/loss=3.830"
      ]
     },
     {
@@ -10036,8 +10007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 978/14932 [01:34<22:30, 10.33it/s, v_num=o30c, train/loss=3.340\r",
-      "Epoch 0:   7%| | 978/14932 [01:34<22:30, 10.33it/s, v_num=o30c, train/loss=1.880"
+      "Epoch 0:   7%| | 979/14932 [01:32<21:54, 10.61it/s, v_num=ui8w, train/loss=3.830\r",
+      "Epoch 0:   7%| | 979/14932 [01:32<21:54, 10.61it/s, v_num=ui8w, train/loss=4.030"
      ]
     },
     {
@@ -10045,8 +10016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 979/14932 [01:34<22:30, 10.33it/s, v_num=o30c, train/loss=1.880\r",
-      "Epoch 0:   7%| | 979/14932 [01:34<22:30, 10.33it/s, v_num=o30c, train/loss=3.470"
+      "Epoch 0:   7%| | 980/14932 [01:32<21:54, 10.62it/s, v_num=ui8w, train/loss=4.030\r",
+      "Epoch 0:   7%| | 980/14932 [01:32<21:54, 10.62it/s, v_num=ui8w, train/loss=2.170"
      ]
     },
     {
@@ -10054,8 +10025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 980/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=3.470\r",
-      "Epoch 0:   7%| | 980/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=4.190"
+      "Epoch 0:   7%| | 981/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=2.170\r",
+      "Epoch 0:   7%| | 981/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=3.230"
      ]
     },
     {
@@ -10063,8 +10034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 981/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=4.190\r",
-      "Epoch 0:   7%| | 981/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=3.550"
+      "Epoch 0:   7%| | 982/14932 [01:32<21:54, 10.61it/s, v_num=ui8w, train/loss=3.230\r",
+      "Epoch 0:   7%| | 982/14932 [01:32<21:54, 10.61it/s, v_num=ui8w, train/loss=2.840"
      ]
     },
     {
@@ -10072,8 +10043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 982/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=3.550\r",
-      "Epoch 0:   7%| | 982/14932 [01:34<22:29, 10.34it/s, v_num=o30c, train/loss=3.580"
+      "Epoch 0:   7%| | 983/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=2.840\r",
+      "Epoch 0:   7%| | 983/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=4.750"
      ]
     },
     {
@@ -10081,8 +10052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 983/14932 [01:35<22:28, 10.34it/s, v_num=o30c, train/loss=3.580\r",
-      "Epoch 0:   7%| | 983/14932 [01:35<22:28, 10.34it/s, v_num=o30c, train/loss=2.560"
+      "Epoch 0:   7%| | 984/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=4.750\r",
+      "Epoch 0:   7%| | 984/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=4.440"
      ]
     },
     {
@@ -10090,8 +10061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 984/14932 [01:35<22:28, 10.35it/s, v_num=o30c, train/loss=2.560\r",
-      "Epoch 0:   7%| | 984/14932 [01:35<22:28, 10.35it/s, v_num=o30c, train/loss=2.160"
+      "Epoch 0:   7%| | 985/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=4.440\r",
+      "Epoch 0:   7%| | 985/14932 [01:32<21:53, 10.62it/s, v_num=ui8w, train/loss=3.940"
      ]
     },
     {
@@ -10099,8 +10070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 985/14932 [01:35<22:27, 10.35it/s, v_num=o30c, train/loss=2.160\r",
-      "Epoch 0:   7%| | 985/14932 [01:35<22:27, 10.35it/s, v_num=o30c, train/loss=2.620"
+      "Epoch 0:   7%| | 986/14932 [01:32<21:52, 10.62it/s, v_num=ui8w, train/loss=3.940\r",
+      "Epoch 0:   7%| | 986/14932 [01:32<21:52, 10.62it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -10108,8 +10079,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 986/14932 [01:35<22:27, 10.35it/s, v_num=o30c, train/loss=2.620\r",
-      "Epoch 0:   7%| | 986/14932 [01:35<22:27, 10.35it/s, v_num=o30c, train/loss=4.120"
+      "Epoch 0:   7%| | 987/14932 [01:32<21:52, 10.63it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -10117,8 +10087,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 987/14932 [01:35<22:26, 10.35it/s, v_num=o30c, train/loss=4.120\r",
-      "Epoch 0:   7%| | 987/14932 [01:35<22:26, 10.35it/s, v_num=o30c, train/loss=3.080"
+      "Epoch 0:   7%| | 987/14932 [01:32<21:52, 10.63it/s, v_num=ui8w, train/loss=4.220"
      ]
     },
     {
@@ -10126,8 +10095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 988/14932 [01:35<22:26, 10.36it/s, v_num=o30c, train/loss=3.080\r",
-      "Epoch 0:   7%| | 988/14932 [01:35<22:26, 10.36it/s, v_num=o30c, train/loss=3.750"
+      "Epoch 0:   7%| | 988/14932 [01:32<21:51, 10.63it/s, v_num=ui8w, train/loss=4.220\r",
+      "Epoch 0:   7%| | 988/14932 [01:32<21:51, 10.63it/s, v_num=ui8w, train/loss=1.560"
      ]
     },
     {
@@ -10135,8 +10104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 989/14932 [01:35<22:26, 10.36it/s, v_num=o30c, train/loss=3.750\r",
-      "Epoch 0:   7%| | 989/14932 [01:35<22:26, 10.36it/s, v_num=o30c, train/loss=2.360"
+      "Epoch 0:   7%| | 989/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=1.560\r",
+      "Epoch 0:   7%| | 989/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=3.770"
      ]
     },
     {
@@ -10144,8 +10113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 990/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=2.360\r",
-      "Epoch 0:   7%| | 990/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=1.910"
+      "Epoch 0:   7%| | 990/14932 [01:33<21:52, 10.63it/s, v_num=ui8w, train/loss=3.770\r",
+      "Epoch 0:   7%| | 990/14932 [01:33<21:52, 10.63it/s, v_num=ui8w, train/loss=2.500"
      ]
     },
     {
@@ -10153,8 +10122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 991/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=1.910\r",
-      "Epoch 0:   7%| | 991/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=3.700"
+      "Epoch 0:   7%| | 991/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=2.500\r",
+      "Epoch 0:   7%| | 991/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=3.500"
      ]
     },
     {
@@ -10162,8 +10131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 992/14932 [01:35<22:26, 10.35it/s, v_num=o30c, train/loss=3.700\r",
-      "Epoch 0:   7%| | 992/14932 [01:35<22:26, 10.35it/s, v_num=o30c, train/loss=3.140"
+      "Epoch 0:   7%| | 992/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=3.500\r",
+      "Epoch 0:   7%| | 992/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=2.810"
      ]
     },
     {
@@ -10171,8 +10140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 993/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=3.140\r",
-      "Epoch 0:   7%| | 993/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=3.360"
+      "Epoch 0:   7%| | 993/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=2.810\r",
+      "Epoch 0:   7%| | 993/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=3.360"
      ]
     },
     {
@@ -10180,8 +10149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 994/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=3.360\r",
-      "Epoch 0:   7%| | 994/14932 [01:35<22:25, 10.36it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   7%| | 994/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=3.360\r",
+      "Epoch 0:   7%| | 994/14932 [01:33<21:52, 10.62it/s, v_num=ui8w, train/loss=3.220"
      ]
     },
     {
@@ -10189,8 +10158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 995/14932 [01:36<22:25, 10.36it/s, v_num=o30c, train/loss=3.830\r",
-      "Epoch 0:   7%| | 995/14932 [01:36<22:25, 10.36it/s, v_num=o30c, train/loss=2.830"
+      "Epoch 0:   7%| | 995/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=3.220\r",
+      "Epoch 0:   7%| | 995/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=3.000"
      ]
     },
     {
@@ -10198,8 +10167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 996/14932 [01:36<22:24, 10.36it/s, v_num=o30c, train/loss=2.830\r",
-      "Epoch 0:   7%| | 996/14932 [01:36<22:24, 10.36it/s, v_num=o30c, train/loss=2.610"
+      "Epoch 0:   7%| | 996/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=3.000\r",
+      "Epoch 0:   7%| | 996/14932 [01:33<21:51, 10.63it/s, v_num=ui8w, train/loss=1.950"
      ]
     },
     {
@@ -10207,8 +10176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 997/14932 [01:36<22:24, 10.37it/s, v_num=o30c, train/loss=2.610\r",
-      "Epoch 0:   7%| | 997/14932 [01:36<22:24, 10.37it/s, v_num=o30c, train/loss=2.730"
+      "Epoch 0:   7%| | 997/14932 [01:33<21:50, 10.63it/s, v_num=ui8w, train/loss=1.950\r",
+      "Epoch 0:   7%| | 997/14932 [01:33<21:50, 10.63it/s, v_num=ui8w, train/loss=3.450"
      ]
     },
     {
@@ -10216,8 +10185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 998/14932 [01:36<22:23, 10.37it/s, v_num=o30c, train/loss=2.730\r",
-      "Epoch 0:   7%| | 998/14932 [01:36<22:23, 10.37it/s, v_num=o30c, train/loss=3.950"
+      "Epoch 0:   7%| | 998/14932 [01:33<21:50, 10.63it/s, v_num=ui8w, train/loss=3.450\r",
+      "Epoch 0:   7%| | 998/14932 [01:33<21:50, 10.63it/s, v_num=ui8w, train/loss=3.640"
      ]
     },
     {
@@ -10225,8 +10194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 999/14932 [01:36<22:23, 10.37it/s, v_num=o30c, train/loss=3.950\r",
-      "Epoch 0:   7%| | 999/14932 [01:36<22:23, 10.37it/s, v_num=o30c, train/loss=3.830"
+      "Epoch 0:   7%| | 999/14932 [01:33<21:50, 10.64it/s, v_num=ui8w, train/loss=3.640\r",
+      "Epoch 0:   7%| | 999/14932 [01:33<21:50, 10.64it/s, v_num=ui8w, train/loss=2.720"
      ]
     },
     {
@@ -10234,8 +10203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1000/14932 [01:36<22:22, 10.37it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:   7%| | 1000/14932 [01:36<22:22, 10.37it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:   7%| | 1000/14932 [01:34<21:49, 10.64it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   7%| | 1000/14932 [01:34<21:49, 10.64it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -10243,8 +10212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1001/14932 [01:36<22:22, 10.38it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:   7%| | 1001/14932 [01:36<22:22, 10.38it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:   7%| | 1001/14932 [01:34<21:49, 10.64it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:   7%| | 1001/14932 [01:34<21:49, 10.64it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -10252,8 +10221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1002/14932 [01:36<22:22, 10.38it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:   7%| | 1002/14932 [01:36<22:22, 10.38it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   7%| | 1002/14932 [01:34<21:48, 10.64it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:   7%| | 1002/14932 [01:34<21:48, 10.64it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -10261,8 +10230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1003/14932 [01:36<22:21, 10.38it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   7%| | 1003/14932 [01:36<22:21, 10.38it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:   7%| | 1003/14932 [01:34<21:48, 10.65it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   7%| | 1003/14932 [01:34<21:48, 10.65it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -10270,8 +10239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1004/14932 [01:36<22:21, 10.39it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:   7%| | 1004/14932 [01:36<22:21, 10.39it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:   7%| | 1004/14932 [01:34<21:48, 10.65it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:   7%| | 1004/14932 [01:34<21:48, 10.65it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -10279,8 +10248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1005/14932 [01:36<22:20, 10.39it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:   7%| | 1005/14932 [01:36<22:20, 10.39it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:   7%| | 1005/14932 [01:34<21:47, 10.65it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:   7%| | 1005/14932 [01:34<21:47, 10.65it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -10288,8 +10257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1006/14932 [01:36<22:21, 10.38it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:   7%| | 1006/14932 [01:36<22:21, 10.38it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:   7%| | 1006/14932 [01:34<21:47, 10.65it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   7%| | 1006/14932 [01:34<21:47, 10.65it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -10297,8 +10266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1007/14932 [01:36<22:20, 10.39it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:   7%| | 1007/14932 [01:36<22:20, 10.39it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:   7%| | 1007/14932 [01:34<21:46, 10.66it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:   7%| | 1007/14932 [01:34<21:46, 10.66it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -10306,8 +10275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1008/14932 [01:37<22:20, 10.39it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:   7%| | 1008/14932 [01:37<22:20, 10.39it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:   7%| | 1008/14932 [01:34<21:46, 10.66it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:   7%| | 1008/14932 [01:34<21:46, 10.66it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -10315,8 +10284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1009/14932 [01:37<22:19, 10.39it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:   7%| | 1009/14932 [01:37<22:19, 10.39it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:   7%| | 1009/14932 [01:34<21:45, 10.66it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   7%| | 1009/14932 [01:34<21:45, 10.66it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -10324,8 +10293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1010/14932 [01:37<22:19, 10.39it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:   7%| | 1010/14932 [01:37<22:19, 10.39it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:   7%| | 1010/14932 [01:34<21:45, 10.66it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   7%| | 1010/14932 [01:34<21:45, 10.66it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -10333,8 +10302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1011/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:   7%| | 1011/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:   7%| | 1011/14932 [01:34<21:45, 10.67it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:   7%| | 1011/14932 [01:34<21:45, 10.67it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -10342,8 +10311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1012/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:   7%| | 1012/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:   7%| | 1012/14932 [01:34<21:44, 10.67it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:   7%| | 1012/14932 [01:34<21:44, 10.67it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -10351,8 +10320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1013/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:   7%| | 1013/14932 [01:37<22:18, 10.40it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:   7%| | 1013/14932 [01:34<21:44, 10.67it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:   7%| | 1013/14932 [01:34<21:44, 10.67it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -10360,8 +10329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1014/14932 [01:37<22:17, 10.41it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:   7%| | 1014/14932 [01:37<22:17, 10.41it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:   7%| | 1014/14932 [01:35<21:44, 10.67it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:   7%| | 1014/14932 [01:35<21:44, 10.67it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -10369,8 +10338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1015/14932 [01:37<22:17, 10.41it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:   7%| | 1015/14932 [01:37<22:17, 10.41it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:   7%| | 1015/14932 [01:35<21:43, 10.67it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:   7%| | 1015/14932 [01:35<21:43, 10.67it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -10378,8 +10347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1016/14932 [01:37<22:16, 10.41it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:   7%| | 1016/14932 [01:37<22:16, 10.41it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:   7%| | 1016/14932 [01:35<21:43, 10.68it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:   7%| | 1016/14932 [01:35<21:43, 10.68it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -10387,8 +10356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1017/14932 [01:37<22:16, 10.41it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:   7%| | 1017/14932 [01:37<22:16, 10.41it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:   7%| | 1017/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:   7%| | 1017/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -10396,8 +10365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1018/14932 [01:37<22:15, 10.42it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:   7%| | 1018/14932 [01:37<22:15, 10.42it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:   7%| | 1018/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   7%| | 1018/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -10405,8 +10374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1019/14932 [01:37<22:15, 10.42it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:   7%| | 1019/14932 [01:37<22:15, 10.42it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:   7%| | 1019/14932 [01:35<21:43, 10.68it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   7%| | 1019/14932 [01:35<21:43, 10.68it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -10414,8 +10383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1020/14932 [01:37<22:14, 10.42it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:   7%| | 1020/14932 [01:37<22:14, 10.42it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   7%| | 1020/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:   7%| | 1020/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -10423,8 +10392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1021/14932 [01:37<22:14, 10.42it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:   7%| | 1021/14932 [01:37<22:14, 10.42it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:   7%| | 1021/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:   7%| | 1021/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -10432,8 +10401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1022/14932 [01:38<22:14, 10.43it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:   7%| | 1022/14932 [01:38<22:14, 10.43it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:   7%| | 1022/14932 [01:35<21:41, 10.68it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:   7%| | 1022/14932 [01:35<21:41, 10.68it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -10441,8 +10410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1023/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:   7%| | 1023/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   7%| | 1023/14932 [01:35<21:41, 10.69it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:   7%| | 1023/14932 [01:35<21:41, 10.69it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -10450,8 +10419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1024/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   7%| | 1024/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:   7%| | 1024/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:   7%| | 1024/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -10459,8 +10428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1025/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:   7%| | 1025/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:   7%| | 1025/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:   7%| | 1025/14932 [01:35<21:42, 10.68it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -10468,8 +10437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1026/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:   7%| | 1026/14932 [01:38<22:14, 10.42it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:   7%| | 1026/14932 [01:36<21:41, 10.68it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   7%| | 1026/14932 [01:36<21:41, 10.68it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -10477,8 +10446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1027/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:   7%| | 1027/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:   7%| | 1027/14932 [01:36<21:41, 10.68it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:   7%| | 1027/14932 [01:36<21:41, 10.68it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -10486,8 +10455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1028/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:   7%| | 1028/14932 [01:38<22:13, 10.43it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:   7%| | 1028/14932 [01:36<21:41, 10.69it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:   7%| | 1028/14932 [01:36<21:41, 10.69it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -10495,8 +10464,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1029/14932 [01:38<22:12, 10.43it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:   7%| | 1029/14932 [01:38<22:12, 10.43it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   7%| | 1029/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -10504,8 +10472,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1030/14932 [01:38<22:12, 10.43it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   7%| | 1030/14932 [01:38<22:12, 10.43it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:   7%| | 1029/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -10513,8 +10480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1031/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:   7%| | 1031/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:   7%| | 1030/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   7%| | 1030/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -10522,8 +10489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1032/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:   7%| | 1032/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   7%| | 1031/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   7%| | 1031/14932 [01:36<21:40, 10.69it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -10531,8 +10498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1033/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   7%| | 1033/14932 [01:38<22:11, 10.44it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   7%| | 1032/14932 [01:36<21:39, 10.69it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   7%| | 1032/14932 [01:36<21:39, 10.69it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -10540,8 +10507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1034/14932 [01:39<22:10, 10.44it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   7%| | 1034/14932 [01:39<22:10, 10.44it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:   7%| | 1033/14932 [01:36<21:39, 10.69it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:   7%| | 1033/14932 [01:36<21:39, 10.69it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -10549,8 +10516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1035/14932 [01:39<22:10, 10.45it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:   7%| | 1035/14932 [01:39<22:10, 10.45it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:   7%| | 1034/14932 [01:36<21:39, 10.70it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:   7%| | 1034/14932 [01:36<21:39, 10.70it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -10558,8 +10525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1036/14932 [01:39<22:10, 10.45it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:   7%| | 1036/14932 [01:39<22:10, 10.45it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   7%| | 1035/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   7%| | 1035/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -10567,8 +10534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1037/14932 [01:39<22:09, 10.45it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   7%| | 1037/14932 [01:39<22:09, 10.45it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:   7%| | 1036/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:   7%| | 1036/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -10576,8 +10543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1038/14932 [01:39<22:09, 10.45it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:   7%| | 1038/14932 [01:39<22:09, 10.45it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:   7%| | 1037/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:   7%| | 1037/14932 [01:36<21:38, 10.70it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -10585,8 +10552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1039/14932 [01:39<22:08, 10.46it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:   7%| | 1039/14932 [01:39<22:08, 10.46it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:   7%| | 1038/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:   7%| | 1038/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -10594,8 +10561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1040/14932 [01:39<22:08, 10.46it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:   7%| | 1040/14932 [01:39<22:08, 10.46it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:   7%| | 1039/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:   7%| | 1039/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -10603,8 +10570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1041/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:   7%| | 1041/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:   7%| | 1040/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:   7%| | 1040/14932 [01:37<21:38, 10.70it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -10612,8 +10579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1042/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:   7%| | 1042/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:   7%| | 1041/14932 [01:37<21:37, 10.70it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:   7%| | 1041/14932 [01:37<21:37, 10.70it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -10621,7 +10588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1043/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:   7%| | 1042/14932 [01:37<21:37, 10.71it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:   7%| | 1042/14932 [01:37<21:37, 10.71it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -10629,7 +10597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1043/14932 [01:39<22:07, 10.46it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:   7%| | 1043/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:   7%| | 1043/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -10637,8 +10606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1044/14932 [01:39<22:06, 10.47it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:   7%| | 1044/14932 [01:39<22:06, 10.47it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   7%| | 1044/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:   7%| | 1044/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -10646,8 +10615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1045/14932 [01:39<22:06, 10.47it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   7%| | 1045/14932 [01:39<22:06, 10.47it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:   7%| | 1045/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   7%| | 1045/14932 [01:37<21:36, 10.71it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -10655,8 +10624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1046/14932 [01:39<22:05, 10.47it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:   7%| | 1046/14932 [01:39<22:05, 10.47it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:   7%| | 1046/14932 [01:37<21:35, 10.71it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:   7%| | 1046/14932 [01:37<21:35, 10.71it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -10664,8 +10633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1047/14932 [01:39<22:05, 10.47it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:   7%| | 1047/14932 [01:39<22:05, 10.47it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:   7%| | 1047/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:   7%| | 1047/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -10673,8 +10642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1048/14932 [01:40<22:05, 10.48it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:   7%| | 1048/14932 [01:40<22:05, 10.48it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:   7%| | 1048/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:   7%| | 1048/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -10682,8 +10651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1049/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:   7%| | 1049/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   7%| | 1049/14932 [01:37<21:35, 10.71it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:   7%| | 1049/14932 [01:37<21:35, 10.71it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -10691,8 +10660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1050/14932 [01:40<22:05, 10.48it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   7%| | 1050/14932 [01:40<22:05, 10.48it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:   7%| | 1050/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:   7%| | 1050/14932 [01:37<21:35, 10.72it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -10700,8 +10669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1051/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:   7%| | 1051/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:   7%| | 1051/14932 [01:38<21:35, 10.72it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:   7%| | 1051/14932 [01:38<21:35, 10.72it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -10709,8 +10678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1052/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:   7%| | 1052/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   7%| | 1052/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:   7%| | 1052/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -10718,8 +10687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1053/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   7%| | 1053/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:   7%| | 1053/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   7%| | 1053/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -10727,8 +10696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1054/14932 [01:40<22:03, 10.49it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:   7%| | 1054/14932 [01:40<22:03, 10.48it/s, v_num=o30c, train/loss=5.22"
+      "Epoch 0:   7%| | 1054/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:   7%| | 1054/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -10736,8 +10705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1055/14932 [01:40<22:03, 10.49it/s, v_num=o30c, train/loss=5.22\r",
-      "Epoch 0:   7%| | 1055/14932 [01:40<22:03, 10.49it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:   7%| | 1055/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   7%| | 1055/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -10745,8 +10714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1056/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:   7%| | 1056/14932 [01:40<22:04, 10.48it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:   7%| | 1056/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   7%| | 1056/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -10754,8 +10723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1057/14932 [01:40<22:03, 10.48it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:   7%| | 1057/14932 [01:40<22:03, 10.48it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:   7%| | 1057/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:   7%| | 1057/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -10763,8 +10732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1058/14932 [01:40<22:03, 10.48it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:   7%| | 1058/14932 [01:40<22:03, 10.48it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:   7%| | 1058/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:   7%| | 1058/14932 [01:38<21:34, 10.72it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -10772,8 +10741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1059/14932 [01:40<22:02, 10.49it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:   7%| | 1059/14932 [01:40<22:02, 10.49it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   7%| | 1059/14932 [01:38<21:33, 10.72it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:   7%| | 1059/14932 [01:38<21:33, 10.72it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -10781,8 +10750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1060/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   7%| | 1060/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:   7%| | 1060/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   7%| | 1060/14932 [01:38<21:33, 10.73it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -10790,8 +10759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1061/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:   7%| | 1061/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:   7%| | 1061/14932 [01:38<21:32, 10.73it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   7%| | 1061/14932 [01:38<21:32, 10.73it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -10799,8 +10768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1062/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:   7%| | 1062/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:   7%| | 1062/14932 [01:38<21:32, 10.73it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:   7%| | 1062/14932 [01:38<21:32, 10.73it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -10808,8 +10777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1063/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:   7%| | 1063/14932 [01:41<22:02, 10.49it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:   7%| | 1063/14932 [01:39<21:32, 10.73it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:   7%| | 1063/14932 [01:39<21:32, 10.73it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -10817,8 +10786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1064/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:   7%| | 1064/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:   7%| | 1064/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   7%| | 1064/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -10826,8 +10795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1065/14932 [01:41<22:01, 10.50it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:   7%| | 1065/14932 [01:41<22:01, 10.50it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:   7%| | 1065/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:   7%| | 1065/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -10835,8 +10804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1066/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:   7%| | 1066/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   7%| | 1066/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   7%| | 1066/14932 [01:39<21:31, 10.74it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -10844,8 +10813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1067/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   7%| | 1067/14932 [01:41<22:01, 10.49it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:   7%| | 1067/14932 [01:39<21:30, 10.74it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:   7%| | 1067/14932 [01:39<21:30, 10.74it/s, v_num=ui8w, train/loss=4.97"
      ]
     },
     {
@@ -10853,8 +10822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1068/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:   7%| | 1068/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:   7%| | 1068/14932 [01:39<21:30, 10.74it/s, v_num=ui8w, train/loss=4.97\r",
+      "Epoch 0:   7%| | 1068/14932 [01:39<21:30, 10.74it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -10862,8 +10831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1069/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:   7%| | 1069/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:   7%| | 1069/14932 [01:39<21:30, 10.75it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:   7%| | 1069/14932 [01:39<21:30, 10.75it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -10871,8 +10840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1070/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:   7%| | 1070/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   7%| | 1070/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:   7%| | 1070/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -10880,8 +10849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1071/14932 [01:41<21:59, 10.50it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   7%| | 1071/14932 [01:41<22:00, 10.50it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:   7%| | 1071/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:   7%| | 1071/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -10889,8 +10858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1072/14932 [01:42<21:59, 10.50it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:   7%| | 1072/14932 [01:42<21:59, 10.50it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:   7%| | 1072/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:   7%| | 1072/14932 [01:39<21:29, 10.75it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -10898,8 +10867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1073/14932 [01:42<21:59, 10.51it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:   7%| | 1073/14932 [01:42<21:59, 10.51it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:   7%| | 1073/14932 [01:39<21:28, 10.76it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:   7%| | 1073/14932 [01:39<21:28, 10.76it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -10907,8 +10876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1074/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:   7%| | 1074/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:   7%| | 1074/14932 [01:39<21:28, 10.76it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:   7%| | 1074/14932 [01:39<21:28, 10.76it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -10916,8 +10885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1075/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:   7%| | 1075/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:   7%| | 1075/14932 [01:39<21:27, 10.76it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:   7%| | 1075/14932 [01:39<21:27, 10.76it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -10925,8 +10894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1076/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:   7%| | 1076/14932 [01:42<21:58, 10.51it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   7%| | 1076/14932 [01:39<21:27, 10.76it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:   7%| | 1076/14932 [01:39<21:27, 10.76it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -10934,8 +10903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1077/14932 [01:42<21:57, 10.51it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   7%| | 1077/14932 [01:42<21:57, 10.51it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:   7%| | 1077/14932 [01:40<21:27, 10.76it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   7%| | 1077/14932 [01:40<21:27, 10.76it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -10943,8 +10912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1078/14932 [01:42<21:57, 10.52it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:   7%| | 1078/14932 [01:42<21:57, 10.52it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:   7%| | 1078/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:   7%| | 1078/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -10952,8 +10921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1079/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:   7%| | 1079/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   7%| | 1079/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:   7%| | 1079/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -10961,8 +10930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1080/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   7%| | 1080/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:   7%| | 1080/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:   7%| | 1080/14932 [01:40<21:26, 10.77it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -10970,8 +10939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1081/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:   7%| | 1081/14932 [01:42<21:56, 10.52it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:   7%| | 1081/14932 [01:40<21:25, 10.77it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   7%| | 1081/14932 [01:40<21:25, 10.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -10979,8 +10948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1082/14932 [01:42<21:55, 10.53it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:   7%| | 1082/14932 [01:42<21:55, 10.53it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:   7%| | 1082/14932 [01:40<21:25, 10.78it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:   7%| | 1082/14932 [01:40<21:25, 10.78it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -10988,8 +10957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1083/14932 [01:42<21:55, 10.53it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:   7%| | 1083/14932 [01:42<21:55, 10.53it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:   7%| | 1083/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:   7%| | 1083/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -10997,8 +10966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1084/14932 [01:42<21:54, 10.53it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:   7%| | 1084/14932 [01:42<21:54, 10.53it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   7%| | 1084/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:   7%| | 1084/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -11006,8 +10975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1085/14932 [01:42<21:54, 10.53it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:   7%| | 1085/14932 [01:42<21:54, 10.53it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:   7%| | 1085/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:   7%| | 1085/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -11015,8 +10984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1086/14932 [01:43<21:54, 10.54it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:   7%| | 1086/14932 [01:43<21:54, 10.54it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:   7%| | 1086/14932 [01:40<21:23, 10.79it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:   7%| | 1086/14932 [01:40<21:23, 10.79it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -11024,8 +10993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1087/14932 [01:43<21:53, 10.54it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:   7%| | 1087/14932 [01:43<21:53, 10.54it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:   7%| | 1087/14932 [01:40<21:23, 10.79it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   7%| | 1087/14932 [01:40<21:23, 10.79it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -11033,8 +11002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1088/14932 [01:43<21:55, 10.52it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:   7%| | 1088/14932 [01:43<21:55, 10.52it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:   7%| | 1088/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:   7%| | 1088/14932 [01:40<21:24, 10.78it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -11042,8 +11011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1089/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:   7%| | 1089/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   7%| | 1089/14932 [01:41<21:23, 10.78it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:   7%| | 1089/14932 [01:41<21:23, 10.78it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -11051,8 +11020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1090/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   7%| | 1090/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   7%| | 1090/14932 [01:41<21:23, 10.78it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   7%| | 1090/14932 [01:41<21:23, 10.78it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -11060,8 +11029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1091/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   7%| | 1091/14932 [01:43<21:54, 10.53it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:   7%| | 1091/14932 [01:41<21:23, 10.79it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:   7%| | 1091/14932 [01:41<21:23, 10.79it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -11069,8 +11038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1092/14932 [01:43<21:53, 10.53it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:   7%| | 1092/14932 [01:43<21:53, 10.53it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:   7%| | 1092/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:   7%| | 1092/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -11078,8 +11047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1093/14932 [01:43<21:53, 10.54it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:   7%| | 1093/14932 [01:43<21:53, 10.54it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:   7%| | 1093/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:   7%| | 1093/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -11087,8 +11056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1094/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:   7%| | 1094/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:   7%| | 1094/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:   7%| | 1094/14932 [01:41<21:22, 10.79it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -11096,8 +11065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1095/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:   7%| | 1095/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   7%| | 1095/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:   7%| | 1095/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -11105,8 +11074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1096/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   7%| | 1096/14932 [01:43<21:52, 10.54it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:   7%| | 1096/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   7%| | 1096/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -11114,8 +11083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1097/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:   7%| | 1097/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:   7%| | 1097/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:   7%| | 1097/14932 [01:41<21:21, 10.80it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -11123,8 +11092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1098/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:   7%| | 1098/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   7%| | 1098/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:   7%| | 1098/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -11132,8 +11101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1099/14932 [01:44<21:51, 10.54it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   7%| | 1099/14932 [01:44<21:52, 10.54it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:   7%| | 1099/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   7%| | 1099/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -11141,8 +11110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1100/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:   7%| | 1100/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:   7%| | 1100/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:   7%| | 1100/14932 [01:41<21:20, 10.80it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -11150,8 +11119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1101/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:   7%| | 1101/14932 [01:44<21:51, 10.55it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   7%| | 1101/14932 [01:41<21:19, 10.81it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:   7%| | 1101/14932 [01:41<21:19, 10.81it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -11159,8 +11128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1102/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:   7%| | 1102/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:   7%| | 1102/14932 [01:41<21:19, 10.81it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:   7%| | 1102/14932 [01:41<21:19, 10.81it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -11168,8 +11137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1103/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:   7%| | 1103/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:   7%| | 1103/14932 [01:42<21:19, 10.81it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:   7%| | 1103/14932 [01:42<21:19, 10.81it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -11177,8 +11146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1104/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:   7%| | 1104/14932 [01:44<21:50, 10.55it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   7%| | 1104/14932 [01:42<21:19, 10.81it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:   7%| | 1104/14932 [01:42<21:19, 10.81it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -11186,8 +11155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1105/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:   7%| | 1105/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:   7%| | 1105/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   7%| | 1105/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -11195,8 +11164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1106/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:   7%| | 1106/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   7%| | 1106/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:   7%| | 1106/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -11204,8 +11173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1107/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   7%| | 1107/14932 [01:44<21:49, 10.56it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:   7%| | 1107/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:   7%| | 1107/14932 [01:42<21:18, 10.81it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -11213,8 +11182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1108/14932 [01:44<21:48, 10.56it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:   7%| | 1108/14932 [01:44<21:48, 10.56it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:   7%| | 1108/14932 [01:42<21:18, 10.82it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   7%| | 1108/14932 [01:42<21:18, 10.82it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -11222,8 +11191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1109/14932 [01:44<21:48, 10.57it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:   7%| | 1109/14932 [01:44<21:48, 10.57it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   7%| | 1109/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:   7%| | 1109/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -11231,8 +11200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1110/14932 [01:45<21:47, 10.57it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   7%| | 1110/14932 [01:45<21:47, 10.57it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:   7%| | 1110/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   7%| | 1110/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -11240,8 +11209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1111/14932 [01:45<21:47, 10.57it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:   7%| | 1111/14932 [01:45<21:47, 10.57it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   7%| | 1111/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   7%| | 1111/14932 [01:42<21:17, 10.82it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -11249,8 +11218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1112/14932 [01:45<21:46, 10.57it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   7%| | 1112/14932 [01:45<21:46, 10.57it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:   7%| | 1112/14932 [01:42<21:16, 10.82it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:   7%| | 1112/14932 [01:42<21:16, 10.82it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -11258,8 +11227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1113/14932 [01:45<21:46, 10.58it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:   7%| | 1113/14932 [01:45<21:46, 10.58it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:   7%| | 1113/14932 [01:42<21:16, 10.83it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:   7%| | 1113/14932 [01:42<21:16, 10.83it/s, v_num=ui8w, train/loss=4.97"
      ]
     },
     {
@@ -11267,8 +11236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1114/14932 [01:45<21:46, 10.58it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:   7%| | 1114/14932 [01:45<21:46, 10.58it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:   7%| | 1114/14932 [01:42<21:16, 10.83it/s, v_num=ui8w, train/loss=4.97\r",
+      "Epoch 0:   7%| | 1114/14932 [01:42<21:16, 10.83it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -11276,8 +11245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1115/14932 [01:45<21:45, 10.58it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:   7%| | 1115/14932 [01:45<21:45, 10.58it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:   7%| | 1115/14932 [01:42<21:15, 10.83it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:   7%| | 1115/14932 [01:42<21:15, 10.83it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -11285,8 +11254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1116/14932 [01:45<21:45, 10.59it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:   7%| | 1116/14932 [01:45<21:45, 10.59it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   7%| | 1116/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:   7%| | 1116/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -11294,8 +11263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1117/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   7%| | 1117/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:   7%| | 1117/14932 [01:43<21:14, 10.84it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:   7%| | 1117/14932 [01:43<21:15, 10.84it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -11303,8 +11272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1118/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:   7%| | 1118/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:   7%| | 1118/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:   7%| | 1118/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -11312,8 +11281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   7%| | 1119/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:   7%| | 1119/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:   7%| | 1119/14932 [01:43<21:14, 10.83it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   7%| | 1119/14932 [01:43<21:14, 10.83it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -11321,8 +11290,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1120/14932 [01:45<21:45, 10.58it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:   8%| | 1120/14932 [01:45<21:45, 10.58it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:   8%| | 1120/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -11330,8 +11298,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1121/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:   8%| | 1121/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:   8%| | 1120/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=5.06"
      ]
     },
     {
@@ -11339,8 +11306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1122/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:   8%| | 1122/14932 [01:45<21:44, 10.59it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:   8%| | 1121/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=5.06\r",
+      "Epoch 0:   8%| | 1121/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -11348,8 +11315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1123/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:   8%| | 1123/14932 [01:46<21:44, 10.59it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:   8%| | 1122/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:   8%| | 1122/14932 [01:43<21:16, 10.82it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -11357,8 +11324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1124/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:   8%| | 1124/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   8%| | 1123/14932 [01:43<21:15, 10.82it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:   8%| | 1123/14932 [01:43<21:15, 10.82it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -11366,8 +11333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1125/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   8%| | 1125/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   8%| | 1124/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:   8%| | 1124/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -11375,8 +11342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1126/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   8%| | 1126/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:   8%| | 1125/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:   8%| | 1125/14932 [01:43<21:15, 10.83it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -11384,8 +11351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1127/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:   8%| | 1127/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:   8%| | 1126/14932 [01:43<21:14, 10.83it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:   8%| | 1126/14932 [01:43<21:14, 10.83it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -11393,8 +11360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1128/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:   8%| | 1128/14932 [01:46<21:43, 10.59it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   8%| | 1127/14932 [01:44<21:14, 10.83it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:   8%| | 1127/14932 [01:44<21:14, 10.83it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -11402,8 +11369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1129/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:   8%| | 1129/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:   8%| | 1128/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:   8%| | 1128/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -11411,8 +11378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1130/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:   8%| | 1130/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   8%| | 1129/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:   8%| | 1129/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -11420,8 +11387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1131/14932 [01:46<21:42, 10.59it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   8%| | 1131/14932 [01:46<21:42, 10.59it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:   8%| | 1130/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:   8%| | 1130/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -11429,8 +11396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1132/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:   8%| | 1132/14932 [01:46<21:42, 10.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:   8%| | 1131/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:   8%| | 1131/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -11438,8 +11405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1133/14932 [01:46<21:41, 10.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:   8%| | 1133/14932 [01:46<21:41, 10.60it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:   8%| | 1132/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   8%| | 1132/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -11447,8 +11414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1134/14932 [01:46<21:41, 10.60it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:   8%| | 1134/14932 [01:46<21:41, 10.60it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   8%| | 1133/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:   8%| | 1133/14932 [01:44<21:13, 10.84it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -11456,8 +11423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1135/14932 [01:47<21:42, 10.59it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   8%| | 1135/14932 [01:47<21:42, 10.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   8%| | 1134/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:   8%| | 1134/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -11465,8 +11432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1136/14932 [01:47<21:42, 10.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   8%| | 1136/14932 [01:47<21:42, 10.59it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:   8%| | 1135/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:   8%| | 1135/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -11474,8 +11441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1137/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:   8%| | 1137/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:   8%| | 1136/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:   8%| | 1136/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -11483,8 +11450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1138/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:   8%| | 1138/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:   8%| | 1137/14932 [01:44<21:11, 10.85it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:   8%| | 1137/14932 [01:44<21:11, 10.85it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -11492,8 +11459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1139/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:   8%| | 1139/14932 [01:47<21:41, 10.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:   8%| | 1138/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:   8%| | 1138/14932 [01:44<21:12, 10.84it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -11501,8 +11468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1140/14932 [01:47<21:40, 10.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:   8%| | 1140/14932 [01:47<21:40, 10.60it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:   8%| | 1139/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:   8%| | 1139/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -11510,8 +11477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1141/14932 [01:47<21:40, 10.60it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:   8%| | 1141/14932 [01:47<21:40, 10.60it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:   8%| | 1140/14932 [01:45<21:11, 10.85it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:   8%| | 1140/14932 [01:45<21:11, 10.85it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -11519,8 +11486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1142/14932 [01:47<21:40, 10.61it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:   8%| | 1142/14932 [01:47<21:40, 10.61it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   8%| | 1141/14932 [01:45<21:12, 10.84it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:   8%| | 1141/14932 [01:45<21:12, 10.84it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -11528,8 +11495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1143/14932 [01:47<21:39, 10.61it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   8%| | 1143/14932 [01:47<21:39, 10.61it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:   8%| | 1142/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:   8%| | 1142/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -11537,8 +11504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1144/14932 [01:47<21:39, 10.61it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:   8%| | 1144/14932 [01:47<21:39, 10.61it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   8%| | 1143/14932 [01:45<21:11, 10.85it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:   8%| | 1143/14932 [01:45<21:11, 10.85it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -11546,8 +11513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1145/14932 [01:47<21:38, 10.61it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   8%| | 1145/14932 [01:47<21:38, 10.61it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:   8%| | 1144/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:   8%| | 1144/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -11555,8 +11522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1146/14932 [01:47<21:38, 10.62it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:   8%| | 1146/14932 [01:47<21:38, 10.62it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:   8%| | 1145/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:   8%| | 1145/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -11564,8 +11531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1147/14932 [01:48<21:38, 10.62it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:   8%| | 1147/14932 [01:48<21:38, 10.62it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:   8%| | 1146/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   8%| | 1146/14932 [01:45<21:11, 10.84it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -11573,8 +11540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1148/14932 [01:48<21:37, 10.62it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:   8%| | 1148/14932 [01:48<21:37, 10.62it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   8%| | 1147/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   8%| | 1147/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=5.28"
      ]
     },
     {
@@ -11582,8 +11549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1149/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   8%| | 1149/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:   8%| | 1148/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=5.28\r",
+      "Epoch 0:   8%| | 1148/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -11591,8 +11558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1150/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:   8%| | 1150/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   8%| | 1149/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:   8%| | 1149/14932 [01:45<21:10, 10.85it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -11600,8 +11567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1151/14932 [01:48<21:38, 10.62it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   8%| | 1151/14932 [01:48<21:38, 10.62it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:   8%| | 1150/14932 [01:45<21:09, 10.85it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:   8%| | 1150/14932 [01:45<21:09, 10.85it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -11609,8 +11576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1152/14932 [01:48<21:39, 10.61it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:   8%| | 1152/14932 [01:48<21:39, 10.61it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:   8%| | 1151/14932 [01:46<21:09, 10.86it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:   8%| | 1151/14932 [01:46<21:09, 10.86it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -11618,8 +11585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1153/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:   8%| | 1153/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   8%| | 1152/14932 [01:46<21:10, 10.85it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:   8%| | 1152/14932 [01:46<21:10, 10.85it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -11627,8 +11594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1154/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:   8%| | 1154/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   8%| | 1153/14932 [01:46<21:10, 10.85it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:   8%| | 1153/14932 [01:46<21:10, 10.85it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -11636,8 +11603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1155/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   8%| | 1155/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:   8%| | 1154/14932 [01:46<21:09, 10.85it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:   8%| | 1154/14932 [01:46<21:09, 10.85it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -11645,8 +11612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1156/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:   8%| | 1156/14932 [01:48<21:38, 10.61it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:   8%| | 1155/14932 [01:46<21:09, 10.85it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   8%| | 1155/14932 [01:46<21:09, 10.85it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -11654,8 +11621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1157/14932 [01:49<21:38, 10.61it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:   8%| | 1157/14932 [01:49<21:38, 10.61it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:   8%| | 1156/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:   8%| | 1156/14932 [01:46<21:09, 10.86it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -11663,8 +11630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1158/14932 [01:49<21:37, 10.61it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:   8%| | 1158/14932 [01:49<21:37, 10.61it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:   8%| | 1157/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:   8%| | 1157/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -11672,8 +11639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1159/14932 [01:49<21:37, 10.62it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:   8%| | 1159/14932 [01:49<21:37, 10.62it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:   8%| | 1158/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   8%| | 1158/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -11681,8 +11648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1160/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:   8%| | 1160/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:   8%| | 1159/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   8%| | 1159/14932 [01:46<21:08, 10.86it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -11690,8 +11657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1161/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:   8%| | 1161/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:   8%| | 1160/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:   8%| | 1160/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -11699,8 +11666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1162/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:   8%| | 1162/14932 [01:49<21:36, 10.62it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:   8%| | 1161/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:   8%| | 1161/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -11708,8 +11675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1163/14932 [01:49<21:35, 10.63it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:   8%| | 1163/14932 [01:49<21:35, 10.63it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:   8%| | 1162/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   8%| | 1162/14932 [01:46<21:07, 10.86it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -11717,8 +11684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1164/14932 [01:49<21:35, 10.63it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:   8%| | 1164/14932 [01:49<21:35, 10.63it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   8%| | 1163/14932 [01:47<21:07, 10.87it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:   8%| | 1163/14932 [01:47<21:07, 10.87it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -11726,8 +11693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1165/14932 [01:49<21:34, 10.63it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   8%| | 1165/14932 [01:49<21:34, 10.63it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   8%| | 1164/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   8%| | 1164/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -11735,8 +11702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1166/14932 [01:49<21:34, 10.63it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   8%| | 1166/14932 [01:49<21:34, 10.63it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:   8%| | 1165/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:   8%| | 1165/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -11744,8 +11711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1167/14932 [01:49<21:34, 10.64it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:   8%| | 1167/14932 [01:49<21:34, 10.64it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:   8%| | 1166/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:   8%| | 1166/14932 [01:47<21:06, 10.87it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -11753,8 +11720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1168/14932 [01:49<21:33, 10.64it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:   8%| | 1168/14932 [01:49<21:33, 10.64it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:   8%| | 1167/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:   8%| | 1167/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -11762,8 +11729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1169/14932 [01:49<21:33, 10.64it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:   8%| | 1169/14932 [01:49<21:33, 10.64it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   8%| | 1168/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:   8%| | 1168/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -11771,8 +11738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1170/14932 [01:49<21:32, 10.64it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   8%| | 1170/14932 [01:49<21:32, 10.64it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:   8%| | 1169/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:   8%| | 1169/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -11780,8 +11747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1171/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:   8%| | 1171/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   8%| | 1170/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:   8%| | 1170/14932 [01:47<21:05, 10.87it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -11789,8 +11756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1172/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   8%| | 1172/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:   8%| | 1171/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:   8%| | 1171/14932 [01:47<21:05, 10.88it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -11798,8 +11765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1173/14932 [01:50<21:34, 10.63it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:   8%| | 1173/14932 [01:50<21:34, 10.63it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:   8%| | 1172/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:   8%| | 1172/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -11807,8 +11774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1174/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:   8%| | 1174/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:   8%| | 1173/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   8%| | 1173/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -11816,8 +11783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1175/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:   8%| | 1175/14932 [01:50<21:33, 10.64it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:   8%| | 1174/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:   8%| | 1174/14932 [01:47<21:04, 10.88it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -11825,8 +11792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1176/14932 [01:50<21:32, 10.64it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:   8%| | 1176/14932 [01:50<21:32, 10.64it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:   8%| | 1175/14932 [01:48<21:04, 10.88it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   8%| | 1175/14932 [01:48<21:04, 10.88it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -11834,8 +11801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1177/14932 [01:50<21:32, 10.64it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:   8%| | 1177/14932 [01:50<21:32, 10.64it/s, v_num=o30c, train/loss=1.08"
+      "Epoch 0:   8%| | 1176/14932 [01:48<21:04, 10.88it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:   8%| | 1176/14932 [01:48<21:04, 10.88it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -11843,8 +11810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1178/14932 [01:50<21:32, 10.65it/s, v_num=o30c, train/loss=1.08\r",
-      "Epoch 0:   8%| | 1178/14932 [01:50<21:32, 10.65it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:   8%| | 1177/14932 [01:48<21:03, 10.88it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:   8%| | 1177/14932 [01:48<21:03, 10.88it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -11852,8 +11819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1179/14932 [01:50<21:31, 10.65it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:   8%| | 1179/14932 [01:50<21:31, 10.65it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:   8%| | 1178/14932 [01:48<21:03, 10.88it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:   8%| | 1178/14932 [01:48<21:03, 10.88it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -11861,8 +11828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1180/14932 [01:50<21:31, 10.65it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:   8%| | 1180/14932 [01:50<21:31, 10.65it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:   8%| | 1179/14932 [01:48<21:03, 10.89it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:   8%| | 1179/14932 [01:48<21:03, 10.89it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -11870,8 +11837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1181/14932 [01:50<21:30, 10.65it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:   8%| | 1181/14932 [01:50<21:30, 10.65it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:   8%| | 1180/14932 [01:48<21:03, 10.89it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:   8%| | 1180/14932 [01:48<21:03, 10.89it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -11879,8 +11846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1182/14932 [01:50<21:30, 10.65it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:   8%| | 1182/14932 [01:50<21:30, 10.65it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   8%| | 1181/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:   8%| | 1181/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -11888,8 +11855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1183/14932 [01:51<21:30, 10.66it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   8%| | 1183/14932 [01:51<21:30, 10.66it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:   8%| | 1182/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   8%| | 1182/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=5.31"
      ]
     },
     {
@@ -11897,8 +11864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1184/14932 [01:51<21:31, 10.65it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:   8%| | 1184/14932 [01:51<21:31, 10.65it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:   8%| | 1183/14932 [01:48<21:01, 10.89it/s, v_num=ui8w, train/loss=5.31\r",
+      "Epoch 0:   8%| | 1183/14932 [01:48<21:01, 10.89it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -11906,8 +11873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1185/14932 [01:51<21:30, 10.65it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:   8%| | 1185/14932 [01:51<21:30, 10.65it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   8%| | 1184/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:   8%| | 1184/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -11915,8 +11882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1186/14932 [01:51<21:30, 10.65it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   8%| | 1186/14932 [01:51<21:30, 10.65it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:   8%| | 1185/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:   8%| | 1185/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -11924,8 +11891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1187/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:   8%| | 1187/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:   8%| | 1186/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:   8%| | 1186/14932 [01:48<21:02, 10.89it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -11933,8 +11900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1188/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:   8%| | 1188/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:   8%| | 1187/14932 [01:48<21:01, 10.89it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:   8%| | 1187/14932 [01:48<21:01, 10.89it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -11942,8 +11909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1189/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:   8%| | 1189/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   8%| | 1188/14932 [01:49<21:01, 10.89it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:   8%| | 1188/14932 [01:49<21:01, 10.89it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -11951,8 +11918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1190/14932 [01:51<21:28, 10.66it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   8%| | 1190/14932 [01:51<21:29, 10.66it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:   8%| | 1189/14932 [01:49<21:01, 10.90it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:   8%| | 1189/14932 [01:49<21:01, 10.90it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -11960,8 +11927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1191/14932 [01:51<21:28, 10.66it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:   8%| | 1191/14932 [01:51<21:28, 10.66it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:   8%| | 1190/14932 [01:49<21:01, 10.90it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:   8%| | 1190/14932 [01:49<21:01, 10.90it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -11969,8 +11936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1192/14932 [01:51<21:28, 10.66it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:   8%| | 1192/14932 [01:51<21:28, 10.66it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:   8%| | 1191/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:   8%| | 1191/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -11978,8 +11945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1193/14932 [01:51<21:28, 10.67it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:   8%| | 1193/14932 [01:51<21:28, 10.67it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:   8%| | 1192/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:   8%| | 1192/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -11987,8 +11954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1194/14932 [01:51<21:27, 10.67it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:   8%| | 1194/14932 [01:51<21:27, 10.67it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   8%| | 1193/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:   8%| | 1193/14932 [01:49<21:00, 10.90it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -11996,8 +11963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1195/14932 [01:51<21:27, 10.67it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   8%| | 1195/14932 [01:51<21:27, 10.67it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:   8%| | 1194/14932 [01:49<20:59, 10.91it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:   8%| | 1194/14932 [01:49<20:59, 10.90it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -12005,8 +11972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1196/14932 [01:52<21:27, 10.67it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:   8%| | 1196/14932 [01:52<21:27, 10.67it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:   8%| | 1195/14932 [01:49<20:59, 10.91it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:   8%| | 1195/14932 [01:49<20:59, 10.91it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -12014,8 +11981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1197/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:   8%| | 1197/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:   8%| | 1196/14932 [01:49<20:59, 10.91it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   8%| | 1196/14932 [01:49<20:59, 10.91it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -12023,8 +11990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1198/14932 [01:52<21:26, 10.68it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:   8%| | 1198/14932 [01:52<21:26, 10.68it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:   8%| | 1197/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:   8%| | 1197/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -12032,8 +11999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1199/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:   8%| | 1199/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:   8%| | 1198/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:   8%| | 1198/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -12041,8 +12008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1200/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:   8%| | 1200/14932 [01:52<21:26, 10.67it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:   8%| | 1199/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:   8%| | 1199/14932 [01:49<20:58, 10.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -12050,8 +12017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1201/14932 [01:52<21:26, 10.68it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:   8%| | 1201/14932 [01:52<21:26, 10.68it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   8%| | 1200/14932 [01:49<20:57, 10.92it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:   8%| | 1200/14932 [01:49<20:57, 10.92it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -12059,8 +12026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1202/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   8%| | 1202/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:   8%| | 1201/14932 [01:49<20:57, 10.92it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:   8%| | 1201/14932 [01:49<20:57, 10.92it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -12068,8 +12035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1203/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:   8%| | 1203/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:   8%| | 1202/14932 [01:50<20:57, 10.92it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:   8%| | 1202/14932 [01:50<20:57, 10.92it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -12077,8 +12044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1204/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:   8%| | 1204/14932 [01:52<21:25, 10.68it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:   8%| | 1203/14932 [01:50<20:56, 10.92it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:   8%| | 1203/14932 [01:50<20:57, 10.92it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -12086,8 +12053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1205/14932 [01:52<21:24, 10.69it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:   8%| | 1205/14932 [01:52<21:24, 10.69it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:   8%| | 1204/14932 [01:50<20:56, 10.92it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:   8%| | 1204/14932 [01:50<20:56, 10.92it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -12095,8 +12062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1206/14932 [01:52<21:24, 10.69it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:   8%| | 1206/14932 [01:52<21:24, 10.69it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:   8%| | 1205/14932 [01:50<20:56, 10.93it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   8%| | 1205/14932 [01:50<20:56, 10.93it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -12104,8 +12071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1207/14932 [01:52<21:24, 10.68it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:   8%| | 1207/14932 [01:52<21:24, 10.68it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:   8%| | 1206/14932 [01:50<20:56, 10.93it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:   8%| | 1206/14932 [01:50<20:56, 10.93it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -12113,8 +12080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1208/14932 [01:53<21:24, 10.69it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:   8%| | 1208/14932 [01:53<21:24, 10.69it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:   8%| | 1207/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   8%| | 1207/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -12122,8 +12089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1209/14932 [01:53<21:24, 10.69it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:   8%| | 1209/14932 [01:53<21:24, 10.69it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:   8%| | 1208/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:   8%| | 1208/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -12131,8 +12098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1210/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:   8%| | 1210/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:   8%| | 1209/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:   8%| | 1209/14932 [01:50<20:55, 10.93it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -12140,8 +12107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1211/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:   8%| | 1211/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:   8%| | 1210/14932 [01:50<20:54, 10.94it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   8%| | 1210/14932 [01:50<20:54, 10.93it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -12149,8 +12116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1212/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:   8%| | 1212/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:   8%| | 1211/14932 [01:50<20:54, 10.94it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:   8%| | 1211/14932 [01:50<20:54, 10.94it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -12158,8 +12125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1213/14932 [01:53<21:22, 10.69it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:   8%| | 1213/14932 [01:53<21:22, 10.69it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:   8%| | 1212/14932 [01:50<20:54, 10.94it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   8%| | 1212/14932 [01:50<20:54, 10.94it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -12167,8 +12134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1214/14932 [01:53<21:22, 10.70it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:   8%| | 1214/14932 [01:53<21:22, 10.70it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:   8%| | 1213/14932 [01:50<20:53, 10.94it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:   8%| | 1213/14932 [01:50<20:53, 10.94it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -12176,8 +12143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1215/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:   8%| | 1215/14932 [01:53<21:23, 10.69it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   8%| | 1214/14932 [01:50<20:53, 10.94it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:   8%| | 1214/14932 [01:50<20:53, 10.94it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -12185,8 +12152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1216/14932 [01:53<21:24, 10.68it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   8%| | 1216/14932 [01:53<21:24, 10.68it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:   8%| | 1215/14932 [01:51<20:53, 10.95it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   8%| | 1215/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -12194,8 +12161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1217/14932 [01:53<21:24, 10.68it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:   8%| | 1217/14932 [01:53<21:24, 10.68it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   8%| | 1216/14932 [01:51<20:54, 10.94it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:   8%| | 1216/14932 [01:51<20:54, 10.94it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -12203,8 +12170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1218/14932 [01:54<21:23, 10.68it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   8%| | 1218/14932 [01:54<21:23, 10.68it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   8%| | 1217/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:   8%| | 1217/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -12212,8 +12179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1219/14932 [01:54<21:23, 10.68it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   8%| | 1219/14932 [01:54<21:23, 10.68it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:   8%| | 1218/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:   8%| | 1218/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -12221,8 +12188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1220/14932 [01:54<21:23, 10.69it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:   8%| | 1220/14932 [01:54<21:23, 10.69it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:   8%| | 1219/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:   8%| | 1219/14932 [01:51<20:53, 10.94it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -12230,8 +12197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1221/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:   8%| | 1221/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:   8%| | 1220/14932 [01:51<20:52, 10.94it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   8%| | 1220/14932 [01:51<20:52, 10.94it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -12239,8 +12206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1222/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:   8%| | 1222/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:   8%| | 1221/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   8%| | 1221/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -12248,8 +12215,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1223/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:   8%| | 1223/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:   8%| | 1222/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -12257,8 +12223,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1224/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:   8%| | 1224/14932 [01:54<21:22, 10.69it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   8%| | 1222/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -12266,8 +12231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1225/14932 [01:54<21:21, 10.69it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   8%| | 1225/14932 [01:54<21:21, 10.69it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:   8%| | 1223/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   8%| | 1223/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -12275,8 +12240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1226/14932 [01:54<21:21, 10.70it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:   8%| | 1226/14932 [01:54<21:21, 10.70it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   8%| | 1224/14932 [01:51<20:52, 10.94it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   8%| | 1224/14932 [01:51<20:52, 10.94it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -12284,8 +12249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1227/14932 [01:54<21:21, 10.70it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   8%| | 1227/14932 [01:54<21:21, 10.70it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   8%| | 1225/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   8%| | 1225/14932 [01:51<20:52, 10.95it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -12293,8 +12258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1228/14932 [01:54<21:20, 10.70it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   8%| | 1228/14932 [01:54<21:20, 10.70it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:   8%| | 1226/14932 [01:51<20:51, 10.95it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:   8%| | 1226/14932 [01:51<20:51, 10.95it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -12302,8 +12267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1229/14932 [01:54<21:20, 10.70it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:   8%| | 1229/14932 [01:54<21:20, 10.70it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:   8%| | 1227/14932 [01:52<20:51, 10.95it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:   8%| | 1227/14932 [01:52<20:51, 10.95it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -12311,8 +12276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1230/14932 [01:54<21:20, 10.70it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:   8%| | 1230/14932 [01:54<21:21, 10.70it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:   8%| | 1228/14932 [01:52<20:51, 10.95it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:   8%| | 1228/14932 [01:52<20:51, 10.95it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -12320,8 +12285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1231/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:   8%| | 1231/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:   8%| | 1229/14932 [01:52<20:50, 10.95it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   8%| | 1229/14932 [01:52<20:50, 10.95it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -12329,8 +12294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1232/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:   8%| | 1232/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:   8%| | 1230/14932 [01:52<20:50, 10.96it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:   8%| | 1230/14932 [01:52<20:50, 10.96it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -12338,8 +12303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1233/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:   8%| | 1233/14932 [01:55<21:20, 10.70it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:   8%| | 1231/14932 [01:52<20:50, 10.96it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   8%| | 1231/14932 [01:52<20:50, 10.96it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -12347,8 +12312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1234/14932 [01:55<21:19, 10.70it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:   8%| | 1234/14932 [01:55<21:19, 10.70it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:   8%| | 1232/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:   8%| | 1232/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -12356,8 +12321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1235/14932 [01:55<21:19, 10.71it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:   8%| | 1235/14932 [01:55<21:19, 10.71it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   8%| | 1233/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:   8%| | 1233/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -12365,8 +12330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1236/14932 [01:55<21:19, 10.71it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   8%| | 1236/14932 [01:55<21:19, 10.71it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:   8%| | 1234/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:   8%| | 1234/14932 [01:52<20:49, 10.96it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -12374,8 +12339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1237/14932 [01:55<21:18, 10.71it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:   8%| | 1237/14932 [01:55<21:18, 10.71it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:   8%| | 1235/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   8%| | 1235/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -12383,8 +12348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1238/14932 [01:55<21:18, 10.71it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:   8%| | 1238/14932 [01:55<21:18, 10.71it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:   8%| | 1236/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:   8%| | 1236/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -12392,8 +12357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1239/14932 [01:55<21:17, 10.71it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:   8%| | 1239/14932 [01:55<21:17, 10.71it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:   8%| | 1237/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:   8%| | 1237/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -12401,8 +12366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1240/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:   8%| | 1240/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   8%| | 1238/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:   8%| | 1238/14932 [01:52<20:48, 10.97it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -12410,8 +12375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1241/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:   8%| | 1241/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:   8%| | 1239/14932 [01:52<20:47, 10.97it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   8%| | 1239/14932 [01:52<20:47, 10.97it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -12419,8 +12384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1242/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:   8%| | 1242/14932 [01:55<21:17, 10.72it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:   8%| | 1240/14932 [01:52<20:47, 10.98it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:   8%| | 1240/14932 [01:52<20:47, 10.98it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -12428,8 +12393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1243/14932 [01:55<21:16, 10.72it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:   8%| | 1243/14932 [01:55<21:16, 10.72it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:   8%| | 1241/14932 [01:53<20:47, 10.98it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:   8%| | 1241/14932 [01:53<20:47, 10.98it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -12437,8 +12402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1244/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:   8%| | 1244/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   8%| | 1242/14932 [01:53<20:46, 10.98it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   8%| | 1242/14932 [01:53<20:46, 10.98it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -12446,8 +12411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1245/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   8%| | 1245/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:   8%| | 1243/14932 [01:53<20:46, 10.98it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:   8%| | 1243/14932 [01:53<20:46, 10.98it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -12455,8 +12420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1246/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:   8%| | 1246/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:   8%| | 1244/14932 [01:53<20:49, 10.96it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:   8%| | 1244/14932 [01:53<20:49, 10.96it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -12464,8 +12429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1247/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:   8%| | 1247/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:   8%| | 1245/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:   8%| | 1245/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -12473,8 +12438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1248/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:   8%| | 1248/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:   8%| | 1246/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:   8%| | 1246/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -12482,8 +12447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1249/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:   8%| | 1249/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:   8%| | 1247/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:   8%| | 1247/14932 [01:53<20:48, 10.96it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -12491,8 +12456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1250/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:   8%| | 1250/14932 [01:56<21:16, 10.72it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:   8%| | 1248/14932 [01:53<20:49, 10.95it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:   8%| | 1248/14932 [01:53<20:49, 10.95it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -12500,8 +12465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1251/14932 [01:56<21:15, 10.72it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:   8%| | 1251/14932 [01:56<21:15, 10.72it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:   8%| | 1249/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   8%| | 1249/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -12509,8 +12474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1252/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:   8%| | 1252/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:   8%| | 1250/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:   8%| | 1250/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -12518,8 +12483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1253/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:   8%| | 1253/14932 [01:56<21:15, 10.73it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:   8%| | 1251/14932 [01:54<20:49, 10.95it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:   8%| | 1251/14932 [01:54<20:49, 10.95it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -12527,8 +12492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1254/14932 [01:56<21:14, 10.73it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:   8%| | 1254/14932 [01:56<21:14, 10.73it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:   8%| | 1252/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:   8%| | 1252/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -12536,8 +12501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1255/14932 [01:56<21:14, 10.73it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:   8%| | 1255/14932 [01:56<21:14, 10.73it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:   8%| | 1253/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   8%| | 1253/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -12545,8 +12510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1256/14932 [01:57<21:14, 10.73it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:   8%| | 1256/14932 [01:57<21:14, 10.73it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:   8%| | 1254/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:   8%| | 1254/14932 [01:54<20:48, 10.96it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -12554,8 +12519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1257/14932 [01:57<21:13, 10.73it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:   8%| | 1257/14932 [01:57<21:13, 10.73it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:   8%| | 1255/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:   8%| | 1255/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -12563,8 +12528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1258/14932 [01:57<21:13, 10.74it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:   8%| | 1258/14932 [01:57<21:13, 10.74it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:   8%| | 1256/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:   8%| | 1256/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -12572,8 +12537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1259/14932 [01:57<21:13, 10.74it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:   8%| | 1259/14932 [01:57<21:13, 10.74it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:   8%| | 1257/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:   8%| | 1257/14932 [01:54<20:47, 10.96it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -12581,8 +12546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1260/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:   8%| | 1260/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:   8%| | 1258/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:   8%| | 1258/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -12590,8 +12555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1261/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:   8%| | 1261/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:   8%| | 1259/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:   8%| | 1259/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -12599,8 +12564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1262/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:   8%| | 1262/14932 [01:57<21:12, 10.74it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:   8%| | 1260/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:   8%| | 1260/14932 [01:54<20:46, 10.97it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -12608,8 +12573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1263/14932 [01:57<21:12, 10.75it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:   8%| | 1263/14932 [01:57<21:12, 10.75it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:   8%| | 1261/14932 [01:54<20:45, 10.97it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:   8%| | 1261/14932 [01:54<20:45, 10.97it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -12617,8 +12582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1264/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:   8%| | 1264/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   8%| | 1262/14932 [01:54<20:45, 10.97it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   8%| | 1262/14932 [01:54<20:45, 10.97it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -12626,8 +12591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1265/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   8%| | 1265/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:   8%| | 1263/14932 [01:55<20:45, 10.98it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:   8%| | 1263/14932 [01:55<20:45, 10.98it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -12635,8 +12600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1266/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:   8%| | 1266/14932 [01:57<21:11, 10.75it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:   8%| | 1264/14932 [01:55<20:45, 10.98it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   8%| | 1264/14932 [01:55<20:45, 10.98it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -12644,8 +12609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1267/14932 [01:57<21:10, 10.75it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:   8%| | 1267/14932 [01:57<21:10, 10.75it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   8%| | 1265/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:   8%| | 1265/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -12653,8 +12618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1268/14932 [01:57<21:10, 10.75it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   8%| | 1268/14932 [01:57<21:10, 10.75it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:   8%| | 1266/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   8%| | 1266/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -12662,8 +12627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   8%| | 1269/14932 [01:57<21:10, 10.76it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:   8%| | 1269/14932 [01:57<21:10, 10.76it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:   8%| | 1267/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   8%| | 1267/14932 [01:55<20:44, 10.98it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -12671,8 +12636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1270/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:   9%| | 1270/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:   8%| | 1268/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:   8%| | 1268/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -12680,8 +12645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1271/14932 [01:58<21:10, 10.75it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:   9%| | 1271/14932 [01:58<21:10, 10.75it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   8%| | 1269/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   8%| | 1269/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -12689,8 +12654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1272/14932 [01:58<21:10, 10.75it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   9%| | 1272/14932 [01:58<21:10, 10.75it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:   9%| | 1270/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:   9%| | 1270/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -12698,8 +12663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1273/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:   9%| | 1273/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:   9%| | 1271/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:   9%| | 1271/14932 [01:55<20:43, 10.99it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -12707,8 +12672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1274/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:   9%| | 1274/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:   9%| | 1272/14932 [01:55<20:42, 10.99it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:   9%| | 1272/14932 [01:55<20:42, 10.99it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -12716,8 +12681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1275/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:   9%| | 1275/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   9%| | 1273/14932 [01:55<20:42, 10.99it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:   9%| | 1273/14932 [01:55<20:42, 10.99it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -12725,8 +12690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1276/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   9%| | 1276/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:   9%| | 1274/14932 [01:55<20:42, 11.00it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:   9%| | 1274/14932 [01:55<20:42, 11.00it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -12734,8 +12699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1277/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:   9%| | 1277/14932 [01:58<21:09, 10.76it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   9%| | 1275/14932 [01:55<20:41, 11.00it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:   9%| | 1275/14932 [01:55<20:41, 11.00it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -12743,8 +12708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1278/14932 [01:58<21:08, 10.76it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   9%| | 1278/14932 [01:58<21:08, 10.76it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:   9%| | 1276/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   9%| | 1276/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -12752,8 +12717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1279/14932 [01:58<21:08, 10.76it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:   9%| | 1279/14932 [01:58<21:08, 10.76it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   9%| | 1277/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:   9%| | 1277/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -12761,8 +12726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1280/14932 [01:59<21:09, 10.75it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   9%| | 1280/14932 [01:59<21:09, 10.75it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:   9%| | 1278/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:   9%| | 1278/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -12770,8 +12735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1281/14932 [01:59<21:09, 10.76it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:   9%| | 1281/14932 [01:59<21:09, 10.76it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:   9%| | 1279/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   9%| | 1279/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=1.40"
      ]
     },
     {
@@ -12779,8 +12744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1282/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:   9%| | 1282/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:   9%| | 1280/14932 [01:56<20:41, 10.99it/s, v_num=ui8w, train/loss=1.40\r",
+      "Epoch 0:   9%| | 1280/14932 [01:56<20:41, 10.99it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -12788,8 +12753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1283/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:   9%| | 1283/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:   9%| | 1281/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   9%| | 1281/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -12797,8 +12762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1284/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:   9%| | 1284/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:   9%| | 1282/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:   9%| | 1282/14932 [01:56<20:41, 11.00it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -12806,8 +12771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1285/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:   9%| | 1285/14932 [01:59<21:08, 10.76it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:   9%| | 1283/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   9%| | 1283/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -12815,8 +12780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1286/14932 [01:59<21:07, 10.76it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:   9%| | 1286/14932 [01:59<21:07, 10.76it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:   9%| | 1284/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:   9%| | 1284/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -12824,8 +12789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1287/14932 [01:59<21:07, 10.77it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:   9%| | 1287/14932 [01:59<21:07, 10.77it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:   9%| | 1285/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:   9%| | 1285/14932 [01:56<20:40, 11.00it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -12833,8 +12798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1288/14932 [01:59<21:07, 10.77it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:   9%| | 1288/14932 [01:59<21:07, 10.77it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:   9%| | 1286/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   9%| | 1286/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -12842,8 +12807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1289/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:   9%| | 1289/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:   9%| | 1287/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:   9%| | 1287/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -12851,8 +12816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1290/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:   9%| | 1290/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:   9%| | 1288/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:   9%| | 1288/14932 [01:56<20:39, 11.01it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -12860,8 +12825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1291/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:   9%| | 1291/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:   9%| | 1289/14932 [01:57<20:39, 11.01it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:   9%| | 1289/14932 [01:57<20:39, 11.01it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -12869,8 +12834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1292/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:   9%| | 1292/14932 [01:59<21:06, 10.77it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:   9%| | 1290/14932 [01:57<20:38, 11.01it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:   9%| | 1290/14932 [01:57<20:38, 11.01it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -12878,8 +12843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1293/14932 [01:59<21:05, 10.78it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:   9%| | 1293/14932 [01:59<21:05, 10.78it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:   9%| | 1291/14932 [01:57<20:38, 11.01it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   9%| | 1291/14932 [01:57<20:38, 11.01it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -12887,8 +12852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1294/14932 [02:00<21:05, 10.78it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:   9%| | 1294/14932 [02:00<21:05, 10.78it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   9%| | 1292/14932 [01:57<20:38, 11.02it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:   9%| | 1292/14932 [01:57<20:38, 11.02it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -12896,8 +12861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1295/14932 [02:00<21:05, 10.78it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   9%| | 1295/14932 [02:00<21:05, 10.78it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   9%| | 1293/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:   9%| | 1293/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -12905,8 +12870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1296/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   9%| | 1296/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:   9%| | 1294/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:   9%| | 1294/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -12914,8 +12879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1297/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:   9%| | 1297/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   9%| | 1295/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:   9%| | 1295/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -12923,8 +12888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1298/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   9%| | 1298/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:   9%| | 1296/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:   9%| | 1296/14932 [01:57<20:37, 11.02it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -12932,8 +12897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1299/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:   9%| | 1299/14932 [02:00<21:04, 10.78it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:   9%| | 1297/14932 [01:57<20:36, 11.02it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:   9%| | 1297/14932 [01:57<20:36, 11.02it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -12941,8 +12906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1300/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:   9%| | 1300/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:   9%| | 1298/14932 [01:57<20:36, 11.03it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:   9%| | 1298/14932 [01:57<20:36, 11.03it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -12950,8 +12915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1301/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:   9%| | 1301/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:   9%| | 1299/14932 [01:57<20:36, 11.03it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:   9%| | 1299/14932 [01:57<20:36, 11.03it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -12959,8 +12924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1302/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:   9%| | 1302/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:   9%| | 1300/14932 [01:57<20:35, 11.03it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   9%| | 1300/14932 [01:57<20:35, 11.03it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -12968,8 +12933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1303/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:   9%| | 1303/14932 [02:00<21:03, 10.79it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:   9%| | 1301/14932 [01:57<20:35, 11.03it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:   9%| | 1301/14932 [01:57<20:35, 11.03it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -12977,8 +12942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1304/14932 [02:00<21:02, 10.79it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:   9%| | 1304/14932 [02:00<21:02, 10.79it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   9%| | 1302/14932 [01:58<20:35, 11.03it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   9%| | 1302/14932 [01:58<20:35, 11.03it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -12986,8 +12951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1305/14932 [02:00<21:02, 10.79it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   9%| | 1305/14932 [02:00<21:02, 10.79it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:   9%| | 1303/14932 [01:58<20:35, 11.04it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   9%| | 1303/14932 [01:58<20:35, 11.03it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -12995,8 +12960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1306/14932 [02:00<21:02, 10.80it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:   9%| | 1306/14932 [02:00<21:02, 10.80it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   9%| | 1304/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:   9%| | 1304/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -13004,7 +12969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1307/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:   9%| | 1305/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:   9%| | 1305/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -13012,7 +12978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1307/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:   9%| | 1306/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:   9%| | 1306/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -13020,8 +12987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1308/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:   9%| | 1308/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:   9%| | 1307/14932 [01:58<20:33, 11.04it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   9%| | 1307/14932 [01:58<20:33, 11.04it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -13029,8 +12996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1309/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:   9%| | 1309/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:   9%| | 1308/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:   9%| | 1308/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -13038,8 +13005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1310/14932 [02:01<21:00, 10.80it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:   9%| | 1310/14932 [02:01<21:00, 10.80it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:   9%| | 1309/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:   9%| | 1309/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=0.89"
      ]
     },
     {
@@ -13047,8 +13014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1311/14932 [02:01<21:00, 10.81it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:   9%| | 1311/14932 [02:01<21:00, 10.81it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:   9%| | 1310/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=0.89\r",
+      "Epoch 0:   9%| | 1310/14932 [01:58<20:34, 11.03it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -13056,8 +13023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1312/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:   9%| | 1312/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:   9%| | 1311/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:   9%| | 1311/14932 [01:58<20:34, 11.04it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -13065,8 +13032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1313/14932 [02:01<21:01, 10.79it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:   9%| | 1313/14932 [02:01<21:01, 10.79it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:   9%| | 1312/14932 [01:59<20:35, 11.02it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:   9%| | 1312/14932 [01:59<20:35, 11.02it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -13074,8 +13041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1314/14932 [02:01<21:01, 10.79it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:   9%| | 1314/14932 [02:01<21:01, 10.79it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   9%| | 1313/14932 [01:59<20:35, 11.02it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:   9%| | 1313/14932 [01:59<20:35, 11.02it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -13083,7 +13050,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1315/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   9%| | 1314/14932 [01:59<20:35, 11.03it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -13091,7 +13058,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1315/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:   9%| | 1314/14932 [01:59<20:35, 11.03it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -13099,8 +13066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1316/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:   9%| | 1316/14932 [02:01<21:01, 10.80it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:   9%| | 1315/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:   9%| | 1315/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -13108,8 +13075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1317/14932 [02:01<21:00, 10.80it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:   9%| | 1317/14932 [02:01<21:00, 10.80it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:   9%| | 1316/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:   9%| | 1316/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -13117,8 +13084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1318/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:   9%| | 1318/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:   9%| | 1317/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:   9%| | 1317/14932 [01:59<20:34, 11.03it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -13126,8 +13093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1319/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:   9%| | 1319/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:   9%| | 1318/14932 [01:59<20:33, 11.03it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:   9%| | 1318/14932 [01:59<20:33, 11.03it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -13135,8 +13102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1320/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:   9%| | 1320/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:   9%| | 1319/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:   9%| | 1319/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -13144,8 +13111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1321/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:   9%| | 1321/14932 [02:02<21:00, 10.80it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:   9%| | 1320/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:   9%| | 1320/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -13153,8 +13120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1322/14932 [02:02<20:59, 10.80it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:   9%| | 1322/14932 [02:02<20:59, 10.80it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:   9%| | 1321/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:   9%| | 1321/14932 [01:59<20:33, 11.04it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -13162,8 +13129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1323/14932 [02:02<20:59, 10.80it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:   9%| | 1323/14932 [02:02<20:59, 10.80it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:   9%| | 1322/14932 [01:59<20:32, 11.04it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:   9%| | 1322/14932 [01:59<20:32, 11.04it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -13171,8 +13138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1324/14932 [02:02<20:59, 10.81it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:   9%| | 1324/14932 [02:02<20:59, 10.81it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:   9%| | 1323/14932 [01:59<20:32, 11.04it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   9%| | 1323/14932 [01:59<20:32, 11.04it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -13180,8 +13147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1325/14932 [02:02<20:59, 10.81it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:   9%| | 1325/14932 [02:02<20:59, 10.81it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:   9%| | 1324/14932 [01:59<20:32, 11.05it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:   9%| | 1324/14932 [01:59<20:32, 11.05it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -13189,8 +13156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1326/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:   9%| | 1326/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:   9%| | 1325/14932 [01:59<20:31, 11.05it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:   9%| | 1325/14932 [01:59<20:31, 11.05it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -13198,8 +13165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1327/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:   9%| | 1327/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   9%| | 1326/14932 [02:00<20:31, 11.05it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:   9%| | 1326/14932 [02:00<20:31, 11.05it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -13207,8 +13174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1328/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   9%| | 1328/14932 [02:02<20:58, 10.81it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:   9%| | 1327/14932 [02:00<20:31, 11.05it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:   9%| | 1327/14932 [02:00<20:31, 11.05it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -13216,8 +13183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1329/14932 [02:02<20:57, 10.81it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:   9%| | 1329/14932 [02:02<20:57, 10.81it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:   9%| | 1328/14932 [02:00<20:30, 11.05it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   9%| | 1328/14932 [02:00<20:30, 11.05it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -13225,8 +13192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1330/14932 [02:02<20:57, 10.82it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:   9%| | 1330/14932 [02:02<20:57, 10.82it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:   9%| | 1329/14932 [02:00<20:30, 11.05it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:   9%| | 1329/14932 [02:00<20:30, 11.05it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -13234,8 +13201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1331/14932 [02:03<20:57, 10.82it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:   9%| | 1331/14932 [02:03<20:57, 10.82it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:   9%| | 1330/14932 [02:00<20:30, 11.06it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:   9%| | 1330/14932 [02:00<20:30, 11.06it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -13243,8 +13210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1332/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:   9%| | 1332/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:   9%| | 1331/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:   9%| | 1331/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -13252,8 +13219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1333/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:   9%| | 1333/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:   9%| | 1332/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:   9%| | 1332/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -13261,8 +13228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1334/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:   9%| | 1334/14932 [02:03<20:56, 10.82it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:   9%| | 1333/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   9%| | 1333/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -13270,8 +13237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1335/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:   9%| | 1335/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   9%| | 1334/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:   9%| | 1334/14932 [02:00<20:29, 11.06it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -13279,8 +13246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1336/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   9%| | 1336/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:   9%| | 1335/14932 [02:00<20:28, 11.06it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:   9%| | 1335/14932 [02:00<20:28, 11.06it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -13288,8 +13255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1337/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:   9%| | 1337/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   9%| | 1336/14932 [02:00<20:28, 11.07it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:   9%| | 1336/14932 [02:00<20:28, 11.07it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -13297,8 +13264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1338/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   9%| | 1338/14932 [02:03<20:55, 10.83it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   9%| | 1337/14932 [02:00<20:28, 11.07it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:   9%| | 1337/14932 [02:00<20:28, 11.07it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -13306,8 +13273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1339/14932 [02:03<20:54, 10.83it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   9%| | 1339/14932 [02:03<20:54, 10.83it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:   9%| | 1338/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:   9%| | 1338/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -13315,8 +13282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1340/14932 [02:03<20:54, 10.83it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:   9%| | 1340/14932 [02:03<20:54, 10.83it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:   9%| | 1339/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:   9%| | 1339/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -13324,8 +13291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1341/14932 [02:03<20:54, 10.84it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:   9%| | 1341/14932 [02:03<20:54, 10.84it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:   9%| | 1340/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:   9%| | 1340/14932 [02:00<20:27, 11.07it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -13333,8 +13300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1342/14932 [02:03<20:54, 10.84it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:   9%| | 1342/14932 [02:03<20:54, 10.84it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:   9%| | 1341/14932 [02:01<20:27, 11.08it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:   9%| | 1341/14932 [02:01<20:27, 11.08it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -13342,8 +13309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1343/14932 [02:03<20:53, 10.84it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:   9%| | 1343/14932 [02:03<20:53, 10.84it/s, v_num=o30c, train/loss=1.69"
+      "Epoch 0:   9%| | 1342/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:   9%| | 1342/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -13351,8 +13318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1344/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=1.69\r",
-      "Epoch 0:   9%| | 1344/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:   9%| | 1343/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:   9%| | 1343/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -13360,8 +13327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1345/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:   9%| | 1345/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:   9%| | 1344/14932 [02:01<20:28, 11.06it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:   9%| | 1344/14932 [02:01<20:28, 11.06it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -13369,8 +13336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1346/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:   9%| | 1346/14932 [02:04<20:54, 10.83it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:   9%| | 1345/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:   9%| | 1345/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -13378,8 +13345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1347/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:   9%| | 1347/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:   9%| | 1346/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:   9%| | 1346/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -13387,8 +13354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1348/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:   9%| | 1348/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:   9%| | 1347/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:   9%| | 1347/14932 [02:01<20:27, 11.07it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -13396,8 +13363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1349/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:   9%| | 1349/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:   9%| | 1348/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:   9%| | 1348/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -13405,8 +13372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1350/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:   9%| | 1350/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:   9%| | 1349/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:   9%| | 1349/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -13414,8 +13381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1351/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:   9%| | 1351/14932 [02:04<20:53, 10.84it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   9%| | 1350/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:   9%| | 1350/14932 [02:01<20:26, 11.07it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -13423,8 +13390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1352/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   9%| | 1352/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:   9%| | 1351/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:   9%| | 1351/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -13432,8 +13399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1353/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:   9%| | 1353/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:   9%| | 1352/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:   9%| | 1352/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -13441,8 +13408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1354/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:   9%| | 1354/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:   9%| | 1353/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:   9%| | 1353/14932 [02:02<20:26, 11.07it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -13450,8 +13417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1355/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:   9%| | 1355/14932 [02:04<20:52, 10.84it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:   9%| | 1354/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:   9%| | 1354/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -13459,8 +13426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1356/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:   9%| | 1356/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:   9%| | 1355/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   9%| | 1355/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -13468,8 +13435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1357/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:   9%| | 1357/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:   9%| | 1356/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:   9%| | 1356/14932 [02:02<20:25, 11.08it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -13477,8 +13444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1358/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:   9%| | 1358/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:   9%| | 1357/14932 [02:02<20:24, 11.08it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:   9%| | 1357/14932 [02:02<20:24, 11.08it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -13486,8 +13453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1359/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:   9%| | 1359/14932 [02:05<20:51, 10.85it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:   9%| | 1358/14932 [02:02<20:24, 11.08it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:   9%| | 1358/14932 [02:02<20:24, 11.08it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -13495,8 +13462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1360/14932 [02:05<20:50, 10.85it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:   9%| | 1360/14932 [02:05<20:50, 10.85it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:   9%| | 1359/14932 [02:02<20:24, 11.09it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:   9%| | 1359/14932 [02:02<20:24, 11.09it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -13504,8 +13471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1361/14932 [02:05<20:50, 10.85it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:   9%| | 1361/14932 [02:05<20:50, 10.85it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   9%| | 1360/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:   9%| | 1360/14932 [02:02<20:24, 11.09it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -13513,8 +13480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1362/14932 [02:05<20:50, 10.86it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   9%| | 1362/14932 [02:05<20:50, 10.86it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:   9%| | 1361/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:   9%| | 1361/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -13522,8 +13489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1363/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:   9%| | 1363/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:   9%| | 1362/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:   9%| | 1362/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -13531,8 +13498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1364/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:   9%| | 1364/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:   9%| | 1363/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:   9%| | 1363/14932 [02:02<20:23, 11.09it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -13540,8 +13507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1365/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:   9%| | 1365/14932 [02:05<20:49, 10.86it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:   9%| | 1364/14932 [02:02<20:22, 11.10it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:   9%| | 1364/14932 [02:02<20:22, 11.10it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -13549,8 +13516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1366/14932 [02:05<20:48, 10.86it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:   9%| | 1366/14932 [02:05<20:48, 10.86it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:   9%| | 1365/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:   9%| | 1365/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -13558,8 +13525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1367/14932 [02:05<20:48, 10.86it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:   9%| | 1367/14932 [02:05<20:48, 10.86it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:   9%| | 1366/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:   9%| | 1366/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -13567,8 +13534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1368/14932 [02:05<20:48, 10.87it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:   9%| | 1368/14932 [02:05<20:48, 10.87it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:   9%| | 1367/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:   9%| | 1367/14932 [02:03<20:22, 11.10it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -13576,8 +13543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1369/14932 [02:05<20:48, 10.87it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:   9%| | 1369/14932 [02:05<20:48, 10.87it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:   9%| | 1368/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:   9%| | 1368/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -13585,8 +13552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1370/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:   9%| | 1370/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:   9%| | 1369/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:   9%| | 1369/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -13594,8 +13561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1371/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:   9%| | 1371/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:   9%| | 1370/14932 [02:03<20:21, 11.11it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:   9%| | 1370/14932 [02:03<20:21, 11.11it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -13603,8 +13570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1372/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:   9%| | 1372/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:   9%| | 1371/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:   9%| | 1371/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -13612,8 +13579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1373/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:   9%| | 1373/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   9%| | 1372/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:   9%| | 1372/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -13621,8 +13588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1374/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   9%| | 1374/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:   9%| | 1373/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:   9%| | 1373/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -13630,8 +13597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1375/14932 [02:06<20:46, 10.88it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:   9%| | 1375/14932 [02:06<20:46, 10.88it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:   9%| | 1374/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   9%| | 1374/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -13639,8 +13606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1376/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:   9%| | 1376/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   9%| | 1375/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:   9%| | 1375/14932 [02:03<20:20, 11.11it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -13648,8 +13615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1377/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   9%| | 1377/14932 [02:06<20:47, 10.87it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:   9%| | 1376/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   9%| | 1376/14932 [02:03<20:21, 11.10it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -13657,8 +13624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1378/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:   9%| | 1378/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:   9%| | 1377/14932 [02:04<20:21, 11.10it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:   9%| | 1377/14932 [02:04<20:21, 11.10it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -13666,8 +13633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1379/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:   9%| | 1379/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:   9%| | 1378/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:   9%| | 1378/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -13675,8 +13642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1380/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:   9%| | 1380/14932 [02:06<20:46, 10.87it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:   9%| | 1379/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:   9%| | 1379/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -13684,8 +13651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1381/14932 [02:06<20:46, 10.88it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:   9%| | 1381/14932 [02:06<20:46, 10.88it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:   9%| | 1380/14932 [02:04<20:20, 11.11it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:   9%| | 1380/14932 [02:04<20:20, 11.11it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -13693,8 +13660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1382/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:   9%| | 1382/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:   9%| | 1381/14932 [02:04<20:20, 11.11it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:   9%| | 1381/14932 [02:04<20:20, 11.11it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -13702,8 +13669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1383/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:   9%| | 1383/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:   9%| | 1382/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:   9%| | 1382/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -13711,8 +13678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1384/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:   9%| | 1384/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:   9%| | 1383/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:   9%| | 1383/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -13720,8 +13687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1385/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:   9%| | 1385/14932 [02:07<20:45, 10.88it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:   9%| | 1384/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:   9%| | 1384/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -13729,8 +13696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1386/14932 [02:07<20:44, 10.88it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:   9%| | 1386/14932 [02:07<20:44, 10.88it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:   9%| | 1385/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:   9%| | 1385/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -13738,8 +13705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1387/14932 [02:07<20:44, 10.88it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:   9%| | 1387/14932 [02:07<20:44, 10.88it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:   9%| | 1386/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:   9%| | 1386/14932 [02:04<20:20, 11.10it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -13747,8 +13714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1388/14932 [02:07<20:44, 10.89it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:   9%| | 1388/14932 [02:07<20:44, 10.89it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   9%| | 1387/14932 [02:04<20:19, 11.10it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:   9%| | 1387/14932 [02:04<20:19, 11.10it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -13756,8 +13723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1389/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   9%| | 1389/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:   9%| | 1388/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:   9%| | 1388/14932 [02:04<20:19, 11.11it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -13765,8 +13732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1390/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:   9%| | 1390/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:   9%| | 1389/14932 [02:05<20:19, 11.11it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:   9%| | 1389/14932 [02:05<20:19, 11.11it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -13774,8 +13741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1391/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:   9%| | 1391/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:   9%| | 1390/14932 [02:05<20:19, 11.11it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:   9%| | 1390/14932 [02:05<20:19, 11.11it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -13783,8 +13750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1392/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:   9%| | 1392/14932 [02:07<20:43, 10.89it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   9%| | 1391/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:   9%| | 1391/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -13792,8 +13759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1393/14932 [02:07<20:42, 10.89it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   9%| | 1393/14932 [02:07<20:42, 10.89it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:   9%| | 1392/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:   9%| | 1392/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -13801,8 +13768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1394/14932 [02:07<20:42, 10.90it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:   9%| | 1394/14932 [02:07<20:42, 10.90it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   9%| | 1393/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=1.61\r",
+      "Epoch 0:   9%| | 1393/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -13810,8 +13777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1395/14932 [02:08<20:42, 10.90it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   9%| | 1395/14932 [02:08<20:42, 10.90it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:   9%| | 1394/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:   9%| | 1394/14932 [02:05<20:18, 11.11it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -13819,8 +13786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1396/14932 [02:08<20:42, 10.90it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:   9%| | 1396/14932 [02:08<20:42, 10.90it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:   9%| | 1395/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:   9%| | 1395/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -13828,8 +13795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1397/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:   9%| | 1397/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:   9%| | 1396/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:   9%| | 1396/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -13837,8 +13804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1398/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:   9%| | 1398/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:   9%| | 1397/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:   9%| | 1397/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -13846,8 +13813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1399/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:   9%| | 1399/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:   9%| | 1398/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:   9%| | 1398/14932 [02:05<20:17, 11.12it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -13855,8 +13822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1400/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:   9%| | 1400/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:   9%| | 1399/14932 [02:05<20:16, 11.12it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:   9%| | 1399/14932 [02:05<20:16, 11.12it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -13864,8 +13831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1401/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:   9%| | 1401/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:   9%| | 1400/14932 [02:05<20:16, 11.12it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:   9%| | 1400/14932 [02:05<20:16, 11.12it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -13873,8 +13840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1402/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:   9%| | 1402/14932 [02:08<20:41, 10.90it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:   9%| | 1401/14932 [02:05<20:16, 11.13it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:   9%| | 1401/14932 [02:05<20:16, 11.13it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -13882,8 +13849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1403/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:   9%| | 1403/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:   9%| | 1402/14932 [02:05<20:15, 11.13it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:   9%| | 1402/14932 [02:05<20:15, 11.13it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -13891,8 +13858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1404/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:   9%| | 1404/14932 [02:08<20:40, 10.90it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:   9%| | 1403/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   9%| | 1403/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -13900,8 +13867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1405/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:   9%| | 1405/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:   9%| | 1404/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:   9%| | 1404/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -13909,8 +13876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1406/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:   9%| | 1406/14932 [02:08<20:40, 10.91it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:   9%| | 1405/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:   9%| | 1405/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -13918,8 +13885,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1407/14932 [02:08<20:39, 10.91it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:   9%| | 1407/14932 [02:08<20:39, 10.91it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:   9%| | 1406/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -13927,8 +13893,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1408/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:   9%| | 1408/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:   9%| | 1406/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -13936,8 +13901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1409/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:   9%| | 1409/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:   9%| | 1407/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:   9%| | 1407/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -13945,8 +13910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1410/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:   9%| | 1410/14932 [02:09<20:40, 10.90it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:   9%| | 1408/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:   9%| | 1408/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -13954,8 +13919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1411/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:   9%| | 1411/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:   9%| | 1409/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:   9%| | 1409/14932 [02:06<20:15, 11.13it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -13963,8 +13928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1412/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:   9%| | 1412/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:   9%| | 1410/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:   9%| | 1410/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -13972,8 +13937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1413/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:   9%| | 1413/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:   9%| | 1411/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:   9%| | 1411/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -13981,8 +13946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1414/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:   9%| | 1414/14932 [02:09<20:39, 10.91it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:   9%| | 1412/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:   9%| | 1412/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -13990,8 +13955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1415/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:   9%| | 1415/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:   9%| | 1413/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:   9%| | 1413/14932 [02:06<20:14, 11.13it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -13999,8 +13964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1416/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:   9%| | 1416/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:   9%| | 1414/14932 [02:06<20:13, 11.14it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:   9%| | 1414/14932 [02:06<20:13, 11.14it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -14008,8 +13973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1417/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:   9%| | 1417/14932 [02:09<20:38, 10.91it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:   9%| | 1415/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:   9%| | 1415/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -14017,8 +13982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:   9%| | 1418/14932 [02:09<20:37, 10.92it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:   9%| | 1418/14932 [02:09<20:37, 10.92it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:   9%| | 1416/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:   9%| | 1416/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -14026,8 +13991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1419/14932 [02:09<20:37, 10.92it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  10%| | 1419/14932 [02:09<20:37, 10.92it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:   9%| | 1417/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:   9%| | 1417/14932 [02:07<20:13, 11.14it/s, v_num=ui8w, train/loss=5.03"
      ]
     },
     {
@@ -14035,8 +14000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1420/14932 [02:10<20:37, 10.92it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  10%| | 1420/14932 [02:10<20:37, 10.92it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:   9%| | 1418/14932 [02:07<20:12, 11.14it/s, v_num=ui8w, train/loss=5.03\r",
+      "Epoch 0:   9%| | 1418/14932 [02:07<20:12, 11.14it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -14044,8 +14009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1421/14932 [02:10<20:37, 10.92it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  10%| | 1421/14932 [02:10<20:37, 10.92it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  10%| | 1419/14932 [02:07<20:12, 11.14it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  10%| | 1419/14932 [02:07<20:12, 11.14it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -14053,8 +14018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1422/14932 [02:10<20:36, 10.92it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  10%| | 1422/14932 [02:10<20:36, 10.92it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  10%| | 1420/14932 [02:07<20:12, 11.15it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  10%| | 1420/14932 [02:07<20:12, 11.15it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -14062,8 +14027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1423/14932 [02:10<20:36, 10.92it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  10%| | 1423/14932 [02:10<20:36, 10.92it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  10%| | 1421/14932 [02:07<20:12, 11.15it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  10%| | 1421/14932 [02:07<20:12, 11.15it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -14071,8 +14036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1424/14932 [02:10<20:36, 10.93it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  10%| | 1424/14932 [02:10<20:36, 10.93it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  10%| | 1422/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  10%| | 1422/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -14080,8 +14045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1425/14932 [02:10<20:36, 10.93it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  10%| | 1425/14932 [02:10<20:36, 10.93it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  10%| | 1423/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  10%| | 1423/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -14089,8 +14054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1426/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  10%| | 1426/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  10%| | 1424/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  10%| | 1424/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -14098,8 +14063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1427/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  10%| | 1427/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  10%| | 1425/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  10%| | 1425/14932 [02:07<20:11, 11.15it/s, v_num=ui8w, train/loss=0.96"
      ]
     },
     {
@@ -14107,8 +14072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1428/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  10%| | 1428/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  10%| | 1426/14932 [02:07<20:10, 11.15it/s, v_num=ui8w, train/loss=0.96\r",
+      "Epoch 0:  10%| | 1426/14932 [02:07<20:10, 11.15it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -14116,8 +14081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1429/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  10%| | 1429/14932 [02:10<20:35, 10.93it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  10%| | 1427/14932 [02:07<20:10, 11.16it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  10%| | 1427/14932 [02:07<20:10, 11.16it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -14125,8 +14090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1430/14932 [02:10<20:34, 10.93it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  10%| | 1430/14932 [02:10<20:34, 10.93it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  10%| | 1428/14932 [02:07<20:10, 11.16it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  10%| | 1428/14932 [02:07<20:10, 11.16it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -14134,8 +14099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1431/14932 [02:10<20:34, 10.94it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  10%| | 1431/14932 [02:10<20:34, 10.94it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  10%| | 1429/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  10%| | 1429/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -14143,8 +14108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1432/14932 [02:10<20:34, 10.94it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  10%| | 1432/14932 [02:10<20:34, 10.94it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  10%| | 1430/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  10%| | 1430/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -14152,8 +14117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1433/14932 [02:10<20:33, 10.94it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  10%| | 1433/14932 [02:10<20:33, 10.94it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  10%| | 1431/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  10%| | 1431/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -14161,8 +14126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1434/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  10%| | 1434/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  10%| | 1432/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  10%| | 1432/14932 [02:08<20:09, 11.16it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -14170,8 +14135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1435/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  10%| | 1435/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  10%| | 1433/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  10%| | 1433/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -14179,8 +14144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1436/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  10%| | 1436/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  10%| | 1434/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  10%| | 1434/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -14188,8 +14153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1437/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  10%| | 1437/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  10%| | 1435/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  10%| | 1435/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -14197,8 +14162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1438/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  10%| | 1438/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  10%| | 1436/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  10%| | 1436/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -14206,8 +14171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1439/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  10%| | 1439/14932 [02:11<20:32, 10.95it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  10%| | 1437/14932 [02:08<20:07, 11.17it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  10%| | 1437/14932 [02:08<20:07, 11.17it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -14215,8 +14180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1440/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  10%| | 1440/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  10%| | 1438/14932 [02:08<20:07, 11.17it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  10%| | 1438/14932 [02:08<20:07, 11.17it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -14224,8 +14189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1441/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  10%| | 1441/14932 [02:11<20:33, 10.94it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  10%| | 1439/14932 [02:08<20:07, 11.18it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  10%| | 1439/14932 [02:08<20:07, 11.18it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -14233,8 +14198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1442/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  10%| | 1442/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  10%| | 1440/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  10%| | 1440/14932 [02:08<20:08, 11.17it/s, v_num=ui8w, train/loss=1.17"
      ]
     },
     {
@@ -14242,8 +14207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1443/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  10%| | 1443/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  10%| | 1441/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=1.17\r",
+      "Epoch 0:  10%| | 1441/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -14251,8 +14216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1444/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  10%| | 1444/14932 [02:11<20:32, 10.94it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1442/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  10%| | 1442/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -14260,8 +14225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1445/14932 [02:12<20:32, 10.95it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  10%| | 1445/14932 [02:12<20:32, 10.95it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  10%| | 1443/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  10%| | 1443/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -14269,8 +14234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1446/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  10%| | 1446/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  10%| | 1444/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  10%| | 1444/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -14278,8 +14243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1447/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  10%| | 1447/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  10%| | 1445/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  10%| | 1445/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -14287,8 +14252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1448/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  10%| | 1448/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  10%| | 1446/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  10%| | 1446/14932 [02:09<20:07, 11.17it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -14296,8 +14261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1449/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  10%| | 1449/14932 [02:12<20:31, 10.95it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  10%| | 1447/14932 [02:09<20:06, 11.17it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  10%| | 1447/14932 [02:09<20:06, 11.17it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -14305,8 +14270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1450/14932 [02:12<20:30, 10.95it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  10%| | 1450/14932 [02:12<20:30, 10.95it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  10%| | 1448/14932 [02:09<20:06, 11.17it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  10%| | 1448/14932 [02:09<20:06, 11.17it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -14314,8 +14279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1451/14932 [02:12<20:30, 10.95it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  10%| | 1451/14932 [02:12<20:30, 10.95it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  10%| | 1449/14932 [02:09<20:06, 11.18it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  10%| | 1449/14932 [02:09<20:06, 11.18it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -14323,8 +14288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1452/14932 [02:12<20:30, 10.96it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  10%| | 1452/14932 [02:12<20:30, 10.96it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  10%| | 1450/14932 [02:09<20:06, 11.18it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  10%| | 1450/14932 [02:09<20:06, 11.18it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -14332,8 +14297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1453/14932 [02:12<20:30, 10.96it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  10%| | 1453/14932 [02:12<20:30, 10.96it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  10%| | 1451/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  10%| | 1451/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -14341,8 +14306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1454/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  10%| | 1454/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  10%| | 1452/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  10%| | 1452/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=1.03"
      ]
     },
     {
@@ -14350,8 +14315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1455/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  10%| | 1455/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  10%| | 1453/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=1.03\r",
+      "Epoch 0:  10%| | 1453/14932 [02:09<20:05, 11.18it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -14359,8 +14324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1456/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  10%| | 1456/14932 [02:12<20:29, 10.96it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  10%| | 1454/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  10%| | 1454/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -14368,8 +14333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1457/14932 [02:12<20:28, 10.96it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  10%| | 1457/14932 [02:12<20:28, 10.96it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  10%| | 1455/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  10%| | 1455/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -14377,8 +14342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1458/14932 [02:12<20:28, 10.97it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  10%| | 1458/14932 [02:12<20:28, 10.97it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  10%| | 1456/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  10%| | 1456/14932 [02:10<20:05, 11.18it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -14386,8 +14351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1459/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  10%| | 1459/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  10%| | 1457/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  10%| | 1457/14932 [02:10<20:04, 11.18it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -14395,8 +14360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1460/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  10%| | 1460/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  10%| | 1458/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  10%| | 1458/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -14404,8 +14369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1461/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  10%| | 1461/14932 [02:13<20:28, 10.97it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  10%| | 1459/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  10%| | 1459/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -14413,8 +14378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1462/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  10%| | 1462/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1460/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  10%| | 1460/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -14422,8 +14387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1463/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  10%| | 1463/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  10%| | 1461/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  10%| | 1461/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -14431,8 +14396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1464/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  10%| | 1464/14932 [02:13<20:27, 10.97it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  10%| | 1462/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  10%| | 1462/14932 [02:10<20:04, 11.19it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -14440,8 +14405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1465/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  10%| | 1465/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  10%| | 1463/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  10%| | 1463/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -14449,8 +14414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1466/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  10%| | 1466/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  10%| | 1464/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  10%| | 1464/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -14458,8 +14423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1467/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  10%| | 1467/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  10%| | 1465/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  10%| | 1465/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -14467,8 +14432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1468/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  10%| | 1468/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  10%| | 1466/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  10%| | 1466/14932 [02:10<20:03, 11.19it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -14476,8 +14441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1469/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  10%| | 1469/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  10%| | 1467/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  10%| | 1467/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -14485,8 +14450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1470/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  10%| | 1470/14932 [02:13<20:26, 10.98it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  10%| | 1468/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  10%| | 1468/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -14494,8 +14459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1471/14932 [02:13<20:25, 10.98it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  10%| | 1471/14932 [02:13<20:25, 10.98it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  10%| | 1469/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  10%| | 1469/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -14503,8 +14468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1472/14932 [02:14<20:26, 10.97it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  10%| | 1472/14932 [02:14<20:26, 10.97it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  10%| | 1470/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  10%| | 1470/14932 [02:11<20:02, 11.20it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -14512,8 +14477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1473/14932 [02:14<20:26, 10.97it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  10%| | 1473/14932 [02:14<20:26, 10.97it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  10%| | 1471/14932 [02:11<20:01, 11.20it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  10%| | 1471/14932 [02:11<20:01, 11.20it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -14521,8 +14486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1474/14932 [02:14<20:26, 10.98it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  10%| | 1474/14932 [02:14<20:26, 10.98it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  10%| | 1472/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  10%| | 1472/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -14530,8 +14495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1475/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  10%| | 1475/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  10%| | 1473/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  10%| | 1473/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -14539,8 +14504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1476/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  10%| | 1476/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  10%| | 1474/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  10%| | 1474/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -14548,8 +14513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1477/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  10%| | 1477/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  10%| | 1475/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  10%| | 1475/14932 [02:11<20:03, 11.18it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -14557,8 +14522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1478/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  10%| | 1478/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=1.17"
+      "Epoch 0:  10%| | 1476/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  10%| | 1476/14932 [02:11<20:02, 11.19it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -14566,8 +14531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1479/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=1.17\r",
-      "Epoch 0:  10%| | 1479/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  10%| | 1477/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  10%| | 1477/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -14575,8 +14540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1480/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  10%| | 1480/14932 [02:14<20:25, 10.98it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  10%| | 1478/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  10%| | 1478/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -14584,8 +14549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1481/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  10%| | 1481/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  10%| | 1479/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  10%| | 1479/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -14593,8 +14558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1482/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  10%| | 1482/14932 [02:14<20:24, 10.98it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  10%| | 1480/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  10%| | 1480/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -14602,8 +14567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1483/14932 [02:14<20:24, 10.99it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  10%| | 1483/14932 [02:14<20:24, 10.99it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  10%| | 1481/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  10%| | 1481/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -14611,8 +14576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1484/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  10%| | 1484/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  10%| | 1482/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  10%| | 1482/14932 [02:12<20:02, 11.19it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -14620,8 +14585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1485/14932 [02:15<20:24, 10.98it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  10%| | 1485/14932 [02:15<20:24, 10.98it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  10%| | 1483/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  10%| | 1483/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -14629,8 +14594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1486/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  10%| | 1486/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  10%| | 1484/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  10%| | 1484/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -14638,8 +14603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1487/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  10%| | 1487/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  10%| | 1485/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  10%| | 1485/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -14647,8 +14612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1488/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  10%| | 1488/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  10%| | 1486/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  10%| | 1486/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -14656,8 +14621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1489/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  10%| | 1489/14932 [02:15<20:23, 10.99it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  10%| | 1487/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  10%| | 1487/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -14665,8 +14630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1490/14932 [02:15<20:22, 10.99it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  10%| | 1490/14932 [02:15<20:22, 10.99it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  10%| | 1488/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  10%| | 1488/14932 [02:12<20:01, 11.19it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -14674,8 +14639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1491/14932 [02:15<20:22, 10.99it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  10%| | 1491/14932 [02:15<20:22, 10.99it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  10%| | 1489/14932 [02:13<20:01, 11.19it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  10%| | 1489/14932 [02:13<20:01, 11.19it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -14683,8 +14648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1492/14932 [02:15<20:24, 10.97it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  10%| | 1492/14932 [02:15<20:24, 10.97it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  10%| | 1490/14932 [02:13<20:00, 11.19it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  10%| | 1490/14932 [02:13<20:00, 11.19it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -14692,8 +14657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1493/14932 [02:16<20:24, 10.98it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  10%| | 1493/14932 [02:16<20:24, 10.98it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  10%| | 1491/14932 [02:13<20:00, 11.19it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  10%| | 1491/14932 [02:13<20:00, 11.19it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -14701,8 +14666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1494/14932 [02:16<20:24, 10.98it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  10%| | 1494/14932 [02:16<20:24, 10.98it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  10%| | 1492/14932 [02:13<20:00, 11.20it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  10%| | 1492/14932 [02:13<20:00, 11.20it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -14710,8 +14675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1495/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  10%| | 1495/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  10%| | 1493/14932 [02:13<20:00, 11.20it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  10%| | 1493/14932 [02:13<20:00, 11.20it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -14719,8 +14684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1496/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  10%| | 1496/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  10%| | 1494/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  10%| | 1494/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -14728,8 +14693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1497/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  10%| | 1497/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  10%| | 1495/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  10%| | 1495/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -14737,8 +14702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1498/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  10%| | 1498/14932 [02:16<20:23, 10.98it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  10%| | 1496/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  10%| | 1496/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -14746,8 +14711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1499/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  10%| | 1499/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  10%| | 1497/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  10%| | 1497/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -14755,8 +14720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1500/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  10%| | 1500/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=1.26"
+      "Epoch 0:  10%| | 1498/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  10%| | 1498/14932 [02:13<19:59, 11.20it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -14764,8 +14729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1501/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=1.26\r",
-      "Epoch 0:  10%| | 1501/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  10%| | 1499/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  10%| | 1499/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -14773,8 +14738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1502/14932 [02:16<20:21, 10.99it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  10%| | 1502/14932 [02:16<20:21, 10.99it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  10%| | 1500/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  10%| | 1500/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -14782,8 +14747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1503/14932 [02:16<20:21, 10.99it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  10%| | 1503/14932 [02:16<20:21, 10.99it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  10%| | 1501/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  10%| | 1501/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -14791,8 +14756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1504/14932 [02:16<20:22, 10.98it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  10%| | 1504/14932 [02:16<20:22, 10.98it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  10%| | 1502/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  10%| | 1502/14932 [02:13<19:58, 11.21it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -14800,8 +14765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1505/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  10%| | 1505/14932 [02:16<20:22, 10.99it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  10%| | 1503/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  10%| | 1503/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -14809,8 +14774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1506/14932 [02:17<20:22, 10.98it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  10%| | 1506/14932 [02:17<20:22, 10.98it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  10%| | 1504/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  10%| | 1504/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -14818,8 +14783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1507/14932 [02:17<20:22, 10.98it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  10%| | 1507/14932 [02:17<20:22, 10.98it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  10%| | 1505/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  10%| | 1505/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -14827,8 +14792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1508/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  10%| | 1508/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  10%| | 1506/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  10%| | 1506/14932 [02:14<19:58, 11.20it/s, v_num=ui8w, train/loss=1.40"
      ]
     },
     {
@@ -14836,8 +14801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1509/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  10%| | 1509/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  10%| | 1507/14932 [02:14<19:58, 11.21it/s, v_num=ui8w, train/loss=1.40\r",
+      "Epoch 0:  10%| | 1507/14932 [02:14<19:58, 11.21it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -14845,8 +14810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1510/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  10%| | 1510/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  10%| | 1508/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  10%| | 1508/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -14854,8 +14819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1511/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  10%| | 1511/14932 [02:17<20:21, 10.99it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  10%| | 1509/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  10%| | 1509/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -14863,8 +14828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1512/14932 [02:17<20:20, 10.99it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  10%| | 1512/14932 [02:17<20:20, 10.99it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1510/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  10%| | 1510/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -14872,8 +14837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1513/14932 [02:17<20:20, 10.99it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  10%| | 1513/14932 [02:17<20:20, 10.99it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  10%| | 1511/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  10%| | 1511/14932 [02:14<19:57, 11.21it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -14881,8 +14846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1514/14932 [02:17<20:20, 11.00it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  10%| | 1514/14932 [02:17<20:20, 11.00it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  10%| | 1512/14932 [02:14<19:56, 11.21it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  10%| | 1512/14932 [02:14<19:56, 11.21it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -14890,8 +14855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1515/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  10%| | 1515/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  10%| | 1513/14932 [02:14<19:56, 11.22it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  10%| | 1513/14932 [02:14<19:56, 11.22it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -14899,8 +14864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1516/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  10%| | 1516/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  10%| | 1514/14932 [02:15<19:56, 11.21it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  10%| | 1514/14932 [02:15<19:56, 11.21it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -14908,8 +14873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1517/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  10%| | 1517/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  10%| | 1515/14932 [02:15<19:56, 11.21it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  10%| | 1515/14932 [02:15<19:56, 11.21it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -14917,8 +14882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1518/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  10%| | 1518/14932 [02:17<20:19, 11.00it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  10%| | 1516/14932 [02:15<19:56, 11.22it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  10%| | 1516/14932 [02:15<19:56, 11.22it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -14926,8 +14891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1519/14932 [02:18<20:18, 11.00it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  10%| | 1519/14932 [02:18<20:18, 11.00it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  10%| | 1517/14932 [02:15<19:56, 11.22it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  10%| | 1517/14932 [02:15<19:56, 11.22it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -14935,8 +14900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1520/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  10%| | 1520/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  10%| | 1518/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  10%| | 1518/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -14944,8 +14909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1521/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  10%| | 1521/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  10%| | 1519/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  10%| | 1519/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -14953,8 +14918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1522/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  10%| | 1522/14932 [02:18<20:18, 11.01it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  10%| | 1520/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  10%| | 1520/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -14962,8 +14927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1523/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  10%| | 1523/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  10%| | 1521/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  10%| | 1521/14932 [02:15<19:55, 11.22it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -14971,8 +14936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1524/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  10%| | 1524/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  10%| | 1522/14932 [02:15<19:54, 11.22it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  10%| | 1522/14932 [02:15<19:54, 11.22it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -14980,8 +14945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1525/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  10%| | 1525/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  10%| | 1523/14932 [02:15<19:54, 11.23it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  10%| | 1523/14932 [02:15<19:54, 11.23it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -14989,8 +14954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1526/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  10%| | 1526/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  10%| | 1524/14932 [02:15<19:54, 11.23it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  10%| | 1524/14932 [02:15<19:54, 11.23it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -14998,8 +14963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1527/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  10%| | 1527/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1525/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  10%| | 1525/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=1.33"
      ]
     },
     {
@@ -15007,7 +14972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1528/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1526/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=1.33\r",
+      "Epoch 0:  10%| | 1526/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -15015,7 +14981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1528/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  10%| | 1527/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  10%| | 1527/14932 [02:15<19:53, 11.23it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -15023,8 +14990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1529/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  10%| | 1529/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  10%| | 1528/14932 [02:16<19:53, 11.24it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  10%| | 1528/14932 [02:16<19:53, 11.24it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -15032,8 +14999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1530/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  10%| | 1530/14932 [02:18<20:17, 11.01it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  10%| | 1529/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  10%| | 1529/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -15041,8 +15008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1531/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  10%| | 1531/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  10%| | 1530/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  10%| | 1530/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -15050,8 +15017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1532/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  10%| | 1532/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  10%| | 1531/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  10%| | 1531/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -15059,8 +15026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1533/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  10%| | 1533/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  10%| | 1532/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  10%| | 1532/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -15068,8 +15035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1534/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  10%| | 1534/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  10%| | 1533/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  10%| | 1533/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -15077,8 +15044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1535/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  10%| | 1535/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  10%| | 1534/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  10%| | 1534/14932 [02:16<19:52, 11.24it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -15086,8 +15053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1536/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  10%| | 1536/14932 [02:19<20:17, 11.01it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  10%| | 1535/14932 [02:16<19:52, 11.23it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  10%| | 1535/14932 [02:16<19:52, 11.23it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -15095,8 +15062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1537/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  10%| | 1537/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  10%| | 1536/14932 [02:16<19:53, 11.22it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  10%| | 1536/14932 [02:16<19:53, 11.22it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -15104,8 +15071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1538/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  10%| | 1538/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  10%| | 1537/14932 [02:16<19:53, 11.22it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  10%| | 1537/14932 [02:16<19:53, 11.22it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -15113,8 +15080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1539/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  10%| | 1539/14932 [02:19<20:16, 11.01it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  10%| | 1538/14932 [02:17<19:53, 11.23it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  10%| | 1538/14932 [02:17<19:53, 11.23it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -15122,8 +15089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1540/14932 [02:19<20:15, 11.01it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  10%| | 1540/14932 [02:19<20:15, 11.01it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  10%| | 1539/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  10%| | 1539/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -15131,8 +15098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1541/14932 [02:19<20:15, 11.02it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  10%| | 1541/14932 [02:19<20:15, 11.02it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  10%| | 1540/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  10%| | 1540/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -15140,8 +15107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1542/14932 [02:19<20:15, 11.02it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  10%| | 1542/14932 [02:19<20:15, 11.02it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  10%| | 1541/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  10%| | 1541/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -15149,8 +15116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1543/14932 [02:20<20:15, 11.02it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  10%| | 1543/14932 [02:20<20:15, 11.02it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  10%| | 1542/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  10%| | 1542/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -15158,8 +15125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1544/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  10%| | 1544/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  10%| | 1543/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  10%| | 1543/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -15167,8 +15134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1545/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  10%| | 1545/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  10%| | 1544/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  10%| | 1544/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -15176,8 +15143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1546/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  10%| | 1546/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  10%| | 1545/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  10%| | 1545/14932 [02:17<19:52, 11.23it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -15185,8 +15152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1547/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  10%| | 1547/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  10%| | 1546/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  10%| | 1546/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -15194,8 +15161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1548/14932 [02:20<20:13, 11.03it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  10%| | 1548/14932 [02:20<20:13, 11.03it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  10%| | 1547/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  10%| | 1547/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -15203,8 +15170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1549/14932 [02:20<20:13, 11.03it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  10%| | 1549/14932 [02:20<20:13, 11.03it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  10%| | 1548/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  10%| | 1548/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -15212,8 +15179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1550/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  10%| | 1550/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  10%| | 1549/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  10%| | 1549/14932 [02:17<19:51, 11.23it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -15221,8 +15188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1551/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  10%| | 1551/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  10%| | 1550/14932 [02:17<19:51, 11.24it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  10%| | 1550/14932 [02:17<19:51, 11.24it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -15230,8 +15197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1552/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  10%| | 1552/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  10%| | 1551/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  10%| | 1551/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -15239,8 +15206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1553/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  10%| | 1553/14932 [02:20<20:14, 11.02it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  10%| | 1552/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  10%| | 1552/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -15248,8 +15215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1554/14932 [02:21<20:14, 11.02it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  10%| | 1554/14932 [02:21<20:14, 11.02it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  10%| | 1553/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  10%| | 1553/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -15257,8 +15224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1555/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  10%| | 1555/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  10%| | 1554/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  10%| | 1554/14932 [02:18<19:50, 11.24it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -15266,8 +15233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1556/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  10%| | 1556/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  10%| | 1555/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  10%| | 1555/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -15275,8 +15242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1557/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  10%| | 1557/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  10%| | 1556/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  10%| | 1556/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -15284,8 +15251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1558/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  10%| | 1558/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  10%| | 1557/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  10%| | 1557/14932 [02:18<19:49, 11.24it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -15293,8 +15260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1559/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  10%| | 1559/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  10%| | 1558/14932 [02:18<19:49, 11.25it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  10%| | 1558/14932 [02:18<19:49, 11.25it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -15302,8 +15269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1560/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  10%| | 1560/14932 [02:21<20:14, 11.01it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  10%| | 1559/14932 [02:18<19:49, 11.25it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  10%| | 1559/14932 [02:18<19:49, 11.25it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -15311,8 +15278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1561/14932 [02:21<20:13, 11.01it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  10%| | 1561/14932 [02:21<20:13, 11.01it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  10%| | 1560/14932 [02:18<19:48, 11.25it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  10%| | 1560/14932 [02:18<19:48, 11.25it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -15320,8 +15287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1562/14932 [02:21<20:13, 11.02it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  10%| | 1562/14932 [02:21<20:13, 11.02it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  10%| | 1561/14932 [02:18<19:50, 11.23it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  10%| | 1561/14932 [02:18<19:50, 11.23it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -15329,8 +15296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1563/14932 [02:22<20:15, 11.00it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  10%| | 1563/14932 [02:22<20:15, 11.00it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  10%| | 1562/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  10%| | 1562/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -15338,8 +15305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1564/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  10%| | 1564/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  10%| | 1563/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  10%| | 1563/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -15347,8 +15314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1565/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  10%| | 1565/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  10%| | 1564/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  10%| | 1564/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -15356,8 +15323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1566/14932 [02:22<20:14, 11.01it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  10%| | 1566/14932 [02:22<20:14, 11.01it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  10%| | 1565/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  10%| | 1565/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -15365,8 +15332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  10%| | 1567/14932 [02:22<20:14, 11.01it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  10%| | 1567/14932 [02:22<20:14, 11.01it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  10%| | 1566/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  10%| | 1566/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -15374,8 +15341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1568/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  11%| | 1568/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  10%| | 1567/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  10%| | 1567/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -15383,8 +15350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1569/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  11%| | 1569/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  11%| | 1568/14932 [02:19<19:49, 11.23it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  11%| | 1568/14932 [02:19<19:49, 11.23it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -15392,8 +15359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1570/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  11%| | 1570/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  11%| | 1569/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  11%| | 1569/14932 [02:19<19:49, 11.24it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -15401,8 +15368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1571/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  11%| | 1571/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  11%| | 1570/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  11%| | 1570/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -15410,8 +15377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1572/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  11%| | 1572/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  11%| | 1571/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  11%| | 1571/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -15419,8 +15386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1573/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  11%| | 1573/14932 [02:22<20:14, 11.00it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  11%| | 1572/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  11%| | 1572/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -15428,8 +15395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1574/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  11%| | 1574/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  11%| | 1573/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  11%| | 1573/14932 [02:19<19:48, 11.24it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -15437,8 +15404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1575/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  11%| | 1575/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  11%| | 1574/14932 [02:19<19:47, 11.24it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  11%| | 1574/14932 [02:19<19:47, 11.24it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -15446,8 +15413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1576/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  11%| | 1576/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  11%| | 1575/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  11%| | 1575/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -15455,8 +15422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1577/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  11%| | 1577/14932 [02:23<20:14, 11.00it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  11%| | 1576/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  11%| | 1576/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -15464,8 +15431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1578/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  11%| | 1578/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  11%| | 1577/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  11%| | 1577/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -15473,8 +15440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1579/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  11%| | 1579/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  11%| | 1578/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  11%| | 1578/14932 [02:20<19:47, 11.25it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -15482,8 +15449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1580/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  11%| | 1580/14932 [02:23<20:13, 11.00it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  11%| | 1579/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  11%| | 1579/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -15491,8 +15458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1581/14932 [02:23<20:13, 11.01it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  11%| | 1581/14932 [02:23<20:13, 11.01it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  11%| | 1580/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  11%| | 1580/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -15500,8 +15467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1582/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  11%| | 1582/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  11%| | 1581/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  11%| | 1581/14932 [02:20<19:46, 11.25it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -15509,8 +15476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1583/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  11%| | 1583/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  11%| | 1582/14932 [02:20<19:46, 11.26it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  11%| | 1582/14932 [02:20<19:46, 11.26it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -15518,8 +15485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1584/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  11%| | 1584/14932 [02:23<20:12, 11.01it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  11%| | 1583/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  11%| | 1583/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -15527,8 +15494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1585/14932 [02:24<20:13, 11.00it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  11%| | 1585/14932 [02:24<20:13, 11.00it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  11%| | 1584/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  11%| | 1584/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -15536,8 +15503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1586/14932 [02:24<20:12, 11.00it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  11%| | 1586/14932 [02:24<20:12, 11.00it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  11%| | 1585/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  11%| | 1585/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -15545,8 +15512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1587/14932 [02:24<20:12, 11.00it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  11%| | 1587/14932 [02:24<20:12, 11.00it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  11%| | 1586/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  11%| | 1586/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -15554,8 +15521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1588/14932 [02:24<20:12, 11.01it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  11%| | 1588/14932 [02:24<20:12, 11.01it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  11%| | 1587/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  11%| | 1587/14932 [02:20<19:45, 11.26it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -15563,7 +15530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1589/14932 [02:24<20:12, 11.01it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  11%| | 1588/14932 [02:21<19:44, 11.26it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  11%| | 1588/14932 [02:21<19:44, 11.26it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -15571,7 +15539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1589/14932 [02:24<20:12, 11.01it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  11%| | 1589/14932 [02:21<19:44, 11.26it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  11%| | 1589/14932 [02:21<19:44, 11.26it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -15579,8 +15548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1590/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  11%| | 1590/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  11%| | 1590/14932 [02:21<19:44, 11.27it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  11%| | 1590/14932 [02:21<19:44, 11.27it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -15588,8 +15557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1591/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  11%| | 1591/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  11%| | 1591/14932 [02:21<19:44, 11.27it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  11%| | 1591/14932 [02:21<19:44, 11.27it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -15597,8 +15566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1592/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  11%| | 1592/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  11%| | 1592/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  11%| | 1592/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -15606,8 +15575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1593/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  11%| | 1593/14932 [02:24<20:11, 11.01it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  11%| | 1593/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  11%| | 1593/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -15615,8 +15584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1594/14932 [02:24<20:10, 11.01it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  11%| | 1594/14932 [02:24<20:10, 11.01it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  11%| | 1594/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  11%| | 1594/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -15624,8 +15593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1595/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  11%| | 1595/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  11%| | 1595/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  11%| | 1595/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -15633,8 +15602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1596/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  11%| | 1596/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  11%| | 1596/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  11%| | 1596/14932 [02:21<19:43, 11.27it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -15642,8 +15611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1597/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  11%| | 1597/14932 [02:24<20:10, 11.02it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  11%| | 1597/14932 [02:21<19:42, 11.27it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  11%| | 1597/14932 [02:21<19:42, 11.27it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -15651,8 +15620,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1598/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  11%| | 1598/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  11%| | 1598/14932 [02:21<19:42, 11.27it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -15660,8 +15628,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1599/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  11%| | 1599/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  11%| | 1598/14932 [02:21<19:42, 11.27it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -15669,8 +15636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1600/14932 [02:25<20:10, 11.01it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  11%| | 1600/14932 [02:25<20:10, 11.01it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  11%| | 1599/14932 [02:21<19:42, 11.28it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  11%| | 1599/14932 [02:21<19:42, 11.28it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -15678,8 +15645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1601/14932 [02:25<20:10, 11.01it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  11%| | 1601/14932 [02:25<20:10, 11.01it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  11%| | 1600/14932 [02:22<19:43, 11.27it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  11%| | 1600/14932 [02:22<19:43, 11.27it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -15687,8 +15654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1602/14932 [02:25<20:10, 11.02it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  11%| | 1602/14932 [02:25<20:10, 11.02it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  11%| | 1601/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  11%| | 1601/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -15696,8 +15663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1603/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  11%| | 1603/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  11%| | 1602/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  11%| | 1602/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -15705,8 +15672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1604/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  11%| | 1604/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  11%| | 1603/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  11%| | 1603/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -15714,8 +15681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1605/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  11%| | 1605/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  11%| | 1604/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  11%| | 1604/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -15723,8 +15690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1606/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  11%| | 1606/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  11%| | 1605/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  11%| | 1605/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -15732,8 +15699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1607/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  11%| | 1607/14932 [02:25<20:09, 11.02it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  11%| | 1606/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  11%| | 1606/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -15741,8 +15708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1608/14932 [02:25<20:08, 11.02it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  11%| | 1608/14932 [02:25<20:08, 11.02it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  11%| | 1607/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  11%| | 1607/14932 [02:22<19:42, 11.27it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -15750,7 +15717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1609/14932 [02:25<20:08, 11.02it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  11%| | 1608/14932 [02:22<19:41, 11.27it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  11%| | 1608/14932 [02:22<19:41, 11.27it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -15758,7 +15726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1609/14932 [02:25<20:08, 11.02it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  11%| | 1609/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  11%| | 1609/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -15766,8 +15735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1610/14932 [02:26<20:08, 11.02it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  11%| | 1610/14932 [02:26<20:08, 11.02it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  11%| | 1610/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  11%| | 1610/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -15775,8 +15744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1611/14932 [02:26<20:08, 11.03it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  11%| | 1611/14932 [02:26<20:08, 11.03it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  11%| | 1611/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  11%| | 1611/14932 [02:22<19:41, 11.28it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -15784,8 +15753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1612/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  11%| | 1612/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  11%| | 1612/14932 [02:22<19:40, 11.28it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  11%| | 1612/14932 [02:22<19:40, 11.28it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -15793,8 +15762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1613/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  11%| | 1613/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  11%| | 1613/14932 [02:22<19:40, 11.28it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  11%| | 1613/14932 [02:22<19:40, 11.28it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -15802,8 +15771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1614/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  11%| | 1614/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  11%| | 1614/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  11%| | 1614/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -15811,8 +15780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1615/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  11%| | 1615/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  11%| | 1615/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  11%| | 1615/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -15820,8 +15789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1616/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  11%| | 1616/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  11%| | 1616/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  11%| | 1616/14932 [02:23<19:40, 11.28it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -15829,8 +15798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1617/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  11%| | 1617/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  11%| | 1617/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  11%| | 1617/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -15838,8 +15807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1618/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  11%| | 1618/14932 [02:26<20:07, 11.03it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  11%| | 1618/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  11%| | 1618/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -15847,8 +15816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1619/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  11%| | 1619/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  11%| | 1619/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  11%| | 1619/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -15856,8 +15825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1620/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  11%| | 1620/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  11%| | 1620/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  11%| | 1620/14932 [02:23<19:39, 11.29it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -15865,8 +15834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1621/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  11%| | 1621/14932 [02:26<20:06, 11.03it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  11%| | 1621/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  11%| | 1621/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -15874,8 +15843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1622/14932 [02:27<20:06, 11.03it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  11%| | 1622/14932 [02:27<20:06, 11.03it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  11%| | 1622/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  11%| | 1622/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -15883,8 +15852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1623/14932 [02:27<20:06, 11.04it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  11%| | 1623/14932 [02:27<20:06, 11.03it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  11%| | 1623/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  11%| | 1623/14932 [02:23<19:38, 11.29it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -15892,8 +15861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1624/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  11%| | 1624/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  11%| | 1624/14932 [02:23<19:38, 11.30it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  11%| | 1624/14932 [02:23<19:38, 11.30it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -15901,8 +15870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1625/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  11%| | 1625/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  11%| | 1625/14932 [02:23<19:38, 11.30it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  11%| | 1625/14932 [02:23<19:38, 11.30it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -15910,8 +15879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1626/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  11%| | 1626/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  11%| | 1626/14932 [02:23<19:37, 11.30it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  11%| | 1626/14932 [02:23<19:37, 11.30it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -15919,8 +15888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1627/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  11%| | 1627/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  11%| | 1627/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  11%| | 1627/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -15928,8 +15897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1628/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  11%| | 1628/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  11%| | 1628/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  11%| | 1628/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -15937,8 +15906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1629/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  11%| | 1629/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  11%| | 1629/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  11%| | 1629/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -15946,8 +15915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1630/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  11%| | 1630/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  11%| | 1630/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  11%| | 1630/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -15955,8 +15924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1631/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  11%| | 1631/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  11%| | 1631/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  11%| | 1631/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -15964,8 +15933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1632/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  11%| | 1632/14932 [02:27<20:05, 11.04it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  11%| | 1632/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  11%| | 1632/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -15973,8 +15942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1633/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  11%| | 1633/14932 [02:27<20:04, 11.04it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  11%| | 1633/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  11%| | 1633/14932 [02:24<19:37, 11.30it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -15982,8 +15951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1634/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  11%| | 1634/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  11%| | 1634/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  11%| | 1634/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -15991,8 +15960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1635/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  11%| | 1635/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  11%| | 1635/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  11%| | 1635/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -16000,8 +15969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1636/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  11%| | 1636/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  11%| | 1636/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  11%| | 1636/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -16009,8 +15978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1637/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  11%| | 1637/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  11%| | 1637/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  11%| | 1637/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -16018,8 +15987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1638/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  11%| | 1638/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  11%| | 1638/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  11%| | 1638/14932 [02:24<19:36, 11.30it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -16027,8 +15996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1639/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  11%| | 1639/14932 [02:28<20:04, 11.04it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  11%| | 1639/14932 [02:24<19:35, 11.31it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  11%| | 1639/14932 [02:24<19:35, 11.31it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -16036,8 +16005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1640/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  11%| | 1640/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  11%| | 1640/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  11%| | 1640/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -16045,8 +16014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1641/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  11%| | 1641/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  11%| | 1641/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  11%| | 1641/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -16054,8 +16023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1642/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  11%| | 1642/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  11%| | 1642/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  11%| | 1642/14932 [02:25<19:35, 11.31it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -16063,8 +16032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1643/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  11%| | 1643/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  11%| | 1643/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  11%| | 1643/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -16072,8 +16041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1644/14932 [02:28<20:02, 11.05it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  11%| | 1644/14932 [02:28<20:02, 11.05it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  11%| | 1644/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  11%| | 1644/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -16081,8 +16050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1645/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  11%| | 1645/14932 [02:28<20:03, 11.04it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  11%| | 1645/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  11%| | 1645/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -16090,8 +16059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1646/14932 [02:29<20:03, 11.04it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  11%| | 1646/14932 [02:29<20:03, 11.04it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  11%| | 1646/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  11%| | 1646/14932 [02:25<19:34, 11.31it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -16099,8 +16068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1647/14932 [02:29<20:02, 11.04it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  11%| | 1647/14932 [02:29<20:02, 11.04it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  11%| | 1647/14932 [02:25<19:34, 11.32it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  11%| | 1647/14932 [02:25<19:34, 11.32it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -16108,8 +16077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1648/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  11%| | 1648/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  11%| | 1648/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  11%| | 1648/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -16117,8 +16086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1649/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  11%| | 1649/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  11%| | 1649/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  11%| | 1649/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -16126,8 +16095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1650/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  11%| | 1650/14932 [02:29<20:02, 11.05it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  11%| | 1650/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  11%| | 1650/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -16135,8 +16104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1651/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  11%| | 1651/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  11%| | 1651/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  11%| | 1651/14932 [02:25<19:33, 11.32it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -16144,8 +16113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1652/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  11%| | 1652/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  11%| | 1652/14932 [02:25<19:32, 11.32it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  11%| | 1652/14932 [02:25<19:32, 11.32it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -16153,8 +16122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1653/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  11%| | 1653/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  11%| | 1653/14932 [02:25<19:32, 11.32it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  11%| | 1653/14932 [02:25<19:32, 11.32it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -16162,8 +16131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1654/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  11%| | 1654/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  11%| | 1654/14932 [02:26<19:32, 11.33it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  11%| | 1654/14932 [02:26<19:32, 11.33it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -16171,8 +16140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1655/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  11%| | 1655/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  11%| | 1655/14932 [02:26<19:32, 11.33it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  11%| | 1655/14932 [02:26<19:32, 11.33it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -16180,8 +16149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1656/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  11%| | 1656/14932 [02:29<20:01, 11.05it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  11%| | 1656/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  11%| | 1656/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -16189,8 +16158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1657/14932 [02:29<20:00, 11.05it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  11%| | 1657/14932 [02:29<20:00, 11.05it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  11%| | 1657/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  11%| | 1657/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -16198,8 +16167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1658/14932 [02:29<20:00, 11.06it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  11%| | 1658/14932 [02:29<20:00, 11.06it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  11%| | 1658/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  11%| | 1658/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -16207,8 +16176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1659/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  11%| | 1659/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  11%| | 1659/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  11%| | 1659/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -16216,8 +16185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1660/14932 [02:30<20:00, 11.05it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  11%| | 1660/14932 [02:30<20:00, 11.05it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  11%| | 1660/14932 [02:26<19:30, 11.33it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  11%| | 1660/14932 [02:26<19:30, 11.33it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -16225,8 +16194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1661/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  11%| | 1661/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  11%| | 1661/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  11%| | 1661/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -16234,8 +16203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1662/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  11%| | 1662/14932 [02:30<20:00, 11.06it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  11%| | 1662/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  11%| | 1662/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -16243,8 +16212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1663/14932 [02:30<19:59, 11.06it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  11%| | 1663/14932 [02:30<19:59, 11.06it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  11%| | 1663/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  11%| | 1663/14932 [02:26<19:30, 11.34it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -16252,8 +16221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1664/14932 [02:30<20:02, 11.03it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  11%| | 1664/14932 [02:30<20:02, 11.03it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  11%| | 1664/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  11%| | 1664/14932 [02:26<19:31, 11.33it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -16261,8 +16230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1665/14932 [02:30<20:02, 11.03it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  11%| | 1665/14932 [02:30<20:02, 11.03it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  11%| | 1665/14932 [02:26<19:30, 11.33it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  11%| | 1665/14932 [02:26<19:30, 11.33it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -16270,8 +16239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1666/14932 [02:30<20:02, 11.04it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  11%| | 1666/14932 [02:30<20:02, 11.04it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  11%| | 1666/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  11%| | 1666/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -16279,8 +16248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1667/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  11%| | 1667/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  11%| | 1667/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  11%| | 1667/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -16288,8 +16257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1668/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  11%| | 1668/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  11%| | 1668/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  11%| | 1668/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -16297,8 +16266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1669/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  11%| | 1669/14932 [02:31<20:01, 11.04it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  11%| | 1669/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  11%| | 1669/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -16306,8 +16275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1670/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  11%| | 1670/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  11%| | 1670/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  11%| | 1670/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -16315,8 +16284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1671/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  11%| | 1671/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  11%| | 1671/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  11%| | 1671/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -16324,8 +16293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1672/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  11%| | 1672/14932 [02:31<20:00, 11.04it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  11%| | 1672/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  11%| | 1672/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=1.33"
      ]
     },
     {
@@ -16333,8 +16302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1673/14932 [02:31<20:00, 11.05it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  11%| | 1673/14932 [02:31<20:00, 11.05it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  11%| | 1673/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=1.33\r",
+      "Epoch 0:  11%| | 1673/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -16342,8 +16311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1674/14932 [02:31<20:00, 11.05it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  11%| | 1674/14932 [02:31<20:00, 11.05it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  11%| | 1674/14932 [02:27<19:29, 11.33it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  11%| | 1674/14932 [02:27<19:29, 11.33it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -16351,8 +16320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1675/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  11%| | 1675/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  11%| | 1675/14932 [02:27<19:29, 11.34it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  11%| | 1675/14932 [02:27<19:29, 11.34it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -16360,8 +16329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1676/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  11%| | 1676/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  11%| | 1676/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  11%| | 1676/14932 [02:27<19:30, 11.33it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -16369,8 +16338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1677/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  11%| | 1677/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  11%| | 1677/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  11%| | 1677/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -16378,8 +16347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1678/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  11%| | 1678/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  11%| | 1678/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  11%| | 1678/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -16387,8 +16356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1679/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  11%| | 1679/14932 [02:31<19:59, 11.05it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  11%| | 1679/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  11%| | 1679/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -16396,8 +16365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1680/14932 [02:31<19:58, 11.05it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  11%| | 1680/14932 [02:31<19:58, 11.05it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  11%| | 1680/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  11%| | 1680/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -16405,8 +16374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1681/14932 [02:32<19:59, 11.05it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  11%| | 1681/14932 [02:32<19:59, 11.05it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  11%| | 1681/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  11%| | 1681/14932 [02:28<19:29, 11.33it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -16414,8 +16383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1682/14932 [02:32<19:58, 11.05it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  11%| | 1682/14932 [02:32<19:58, 11.05it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  11%| | 1682/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  11%| | 1682/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -16423,8 +16392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1683/14932 [02:32<19:58, 11.05it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  11%| | 1683/14932 [02:32<19:58, 11.05it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  11%| | 1683/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  11%| | 1683/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -16432,8 +16401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1684/14932 [02:32<19:58, 11.06it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  11%| | 1684/14932 [02:32<19:58, 11.06it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  11%| | 1684/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  11%| | 1684/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -16441,8 +16410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1685/14932 [02:32<19:58, 11.06it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  11%| | 1685/14932 [02:32<19:58, 11.06it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  11%| | 1685/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  11%| | 1685/14932 [02:28<19:28, 11.34it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -16450,8 +16419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1686/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  11%| | 1686/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  11%| | 1686/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  11%| | 1686/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -16459,8 +16428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1687/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  11%| | 1687/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  11%| | 1687/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  11%| | 1687/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -16468,8 +16437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1688/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  11%| | 1688/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  11%| | 1688/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  11%| | 1688/14932 [02:28<19:27, 11.34it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -16477,8 +16446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1689/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  11%| | 1689/14932 [02:32<19:57, 11.06it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  11%| | 1689/14932 [02:28<19:27, 11.35it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  11%| | 1689/14932 [02:28<19:27, 11.35it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -16486,8 +16455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1690/14932 [02:32<19:56, 11.06it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  11%| | 1690/14932 [02:32<19:56, 11.06it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  11%| | 1690/14932 [02:28<19:27, 11.35it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  11%| | 1690/14932 [02:28<19:27, 11.35it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -16495,8 +16464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1691/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  11%| | 1691/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  11%| | 1691/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  11%| | 1691/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -16504,8 +16473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1692/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  11%| | 1692/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  11%| | 1692/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  11%| | 1692/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -16513,8 +16482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1693/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  11%| | 1693/14932 [02:32<19:56, 11.07it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  11%| | 1693/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  11%| | 1693/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -16522,8 +16491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1694/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  11%| | 1694/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  11%| | 1694/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  11%| | 1694/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -16531,8 +16500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1695/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  11%| | 1695/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  11%| | 1695/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  11%| | 1695/14932 [02:29<19:26, 11.35it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -16540,8 +16509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1696/14932 [02:33<19:56, 11.06it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  11%| | 1696/14932 [02:33<19:56, 11.06it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  11%| | 1696/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  11%| | 1696/14932 [02:29<19:27, 11.34it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -16549,8 +16518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1697/14932 [02:33<19:56, 11.06it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  11%| | 1697/14932 [02:33<19:56, 11.06it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  11%| | 1697/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  11%| | 1697/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -16558,8 +16527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1698/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  11%| | 1698/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  11%| | 1698/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  11%| | 1698/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -16567,8 +16536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1699/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  11%| | 1699/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  11%| | 1699/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  11%| | 1699/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -16576,8 +16545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1700/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  11%| | 1700/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  11%| | 1700/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  11%| | 1700/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -16585,8 +16554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1701/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  11%| | 1701/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  11%| | 1701/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  11%| | 1701/14932 [02:29<19:26, 11.34it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -16594,8 +16563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1702/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  11%| | 1702/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  11%| | 1702/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  11%| | 1702/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -16603,8 +16572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1703/14932 [02:33<19:55, 11.06it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  11%| | 1703/14932 [02:33<19:55, 11.06it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  11%| | 1703/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  11%| | 1703/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -16612,8 +16581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1704/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  11%| | 1704/14932 [02:33<19:55, 11.07it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  11%| | 1704/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  11%| | 1704/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -16621,8 +16590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1705/14932 [02:34<19:55, 11.07it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  11%| | 1705/14932 [02:34<19:55, 11.07it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  11%| | 1705/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  11%| | 1705/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -16630,8 +16599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1706/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  11%| | 1706/14932 [02:34<19:55, 11.07it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  11%| | 1706/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  11%| | 1706/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -16639,8 +16608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1707/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  11%| | 1707/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  11%| | 1707/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  11%| | 1707/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -16648,8 +16617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1708/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  11%| | 1708/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  11%| | 1708/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  11%| | 1708/14932 [02:30<19:25, 11.35it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -16657,8 +16626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1709/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  11%| | 1709/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  11%| | 1709/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  11%| | 1709/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=4.78"
      ]
     },
     {
@@ -16666,8 +16635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1710/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  11%| | 1710/14932 [02:34<19:54, 11.07it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  11%| | 1710/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=4.78\r",
+      "Epoch 0:  11%| | 1710/14932 [02:30<19:26, 11.34it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -16675,8 +16644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1711/14932 [02:34<19:53, 11.07it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  11%| | 1711/14932 [02:34<19:53, 11.07it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  11%| | 1711/14932 [02:30<19:25, 11.34it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  11%| | 1711/14932 [02:30<19:25, 11.34it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -16684,8 +16653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1712/14932 [02:34<19:53, 11.07it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  11%| | 1712/14932 [02:34<19:53, 11.07it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  11%| | 1712/14932 [02:30<19:25, 11.34it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  11%| | 1712/14932 [02:30<19:25, 11.34it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -16693,8 +16662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1713/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  11%| | 1713/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  11%| | 1713/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  11%| | 1713/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -16702,8 +16671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1714/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  11%| | 1714/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  11%| | 1714/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  11%| | 1714/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -16711,8 +16680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1715/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  11%| | 1715/14932 [02:34<19:53, 11.08it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  11%| | 1715/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  11%| | 1715/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -16720,8 +16689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1716/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  11%| | 1716/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  11%| | 1716/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  11%| | 1716/14932 [02:31<19:25, 11.34it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -16729,8 +16698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  11%| | 1717/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  11%| | 1717/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  11%| | 1717/14932 [02:31<19:26, 11.33it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  11%| | 1717/14932 [02:31<19:26, 11.33it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -16738,8 +16707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1718/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  12%| | 1718/14932 [02:35<19:56, 11.05it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  12%| | 1718/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  12%| | 1718/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -16747,8 +16716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1719/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  12%| | 1719/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  12%| | 1719/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  12%| | 1719/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -16756,8 +16725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1720/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  12%| | 1720/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  12%| | 1720/14932 [02:31<19:26, 11.33it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  12%| | 1720/14932 [02:31<19:26, 11.33it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -16765,8 +16734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1721/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  12%| | 1721/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  12%| | 1721/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  12%| | 1721/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -16774,8 +16743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1722/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  12%| | 1722/14932 [02:35<19:55, 11.05it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  12%| | 1722/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  12%| | 1722/14932 [02:31<19:25, 11.33it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -16783,8 +16752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1723/14932 [02:35<19:54, 11.05it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  12%| | 1723/14932 [02:35<19:54, 11.05it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  12%| | 1723/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  12%| | 1723/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -16792,8 +16761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1724/14932 [02:36<19:55, 11.05it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  12%| | 1724/14932 [02:36<19:55, 11.05it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  12%| | 1724/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  12%| | 1724/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -16801,8 +16770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1725/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  12%| | 1725/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  12%| | 1725/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  12%| | 1725/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=1.15"
      ]
     },
     {
@@ -16810,8 +16779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1726/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  12%| | 1726/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  12%| | 1726/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=1.15\r",
+      "Epoch 0:  12%| | 1726/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -16819,8 +16788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1727/14932 [02:36<19:54, 11.06it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  12%| | 1727/14932 [02:36<19:54, 11.06it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  12%| | 1727/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  12%| | 1727/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -16828,8 +16797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1728/14932 [02:36<19:55, 11.05it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  12%| | 1728/14932 [02:36<19:55, 11.05it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  12%| | 1728/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  12%| | 1728/14932 [02:32<19:25, 11.32it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -16837,8 +16806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1729/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  12%| | 1729/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  12%| | 1729/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  12%| | 1729/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -16846,8 +16815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1730/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  12%| | 1730/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  12%| | 1730/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  12%| | 1730/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -16855,8 +16824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1731/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  12%| | 1731/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  12%| | 1731/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  12%| | 1731/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -16864,8 +16833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1732/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  12%| | 1732/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  12%| | 1732/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  12%| | 1732/14932 [02:32<19:25, 11.33it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -16873,8 +16842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1733/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  12%| | 1733/14932 [02:36<19:54, 11.05it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  12%| | 1733/14932 [02:32<19:24, 11.33it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  12%| | 1733/14932 [02:32<19:24, 11.33it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -16882,8 +16851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1734/14932 [02:36<19:53, 11.06it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  12%| | 1734/14932 [02:36<19:53, 11.06it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  12%| | 1734/14932 [02:33<19:24, 11.33it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  12%| | 1734/14932 [02:33<19:24, 11.33it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -16891,8 +16860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1735/14932 [02:36<19:53, 11.06it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  12%| | 1735/14932 [02:36<19:53, 11.06it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  12%| | 1735/14932 [02:33<19:24, 11.33it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  12%| | 1735/14932 [02:33<19:24, 11.33it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -16900,8 +16869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1736/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  12%| | 1736/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  12%| | 1736/14932 [02:33<19:24, 11.34it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  12%| | 1736/14932 [02:33<19:24, 11.34it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -16909,8 +16878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1737/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  12%| | 1737/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  12%| | 1737/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  12%| | 1737/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -16918,8 +16887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1738/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  12%| | 1738/14932 [02:37<19:53, 11.05it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  12%| | 1738/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  12%| | 1738/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -16927,8 +16896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1739/14932 [02:37<19:53, 11.06it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  12%| | 1739/14932 [02:37<19:53, 11.06it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  12%| | 1739/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  12%| | 1739/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -16936,8 +16905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1740/14932 [02:37<19:53, 11.06it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  12%| | 1740/14932 [02:37<19:53, 11.06it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  12%| | 1740/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  12%| | 1740/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -16945,8 +16914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1741/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  12%| | 1741/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  12%| | 1741/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  12%| | 1741/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -16954,8 +16923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1742/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  12%| | 1742/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  12%| | 1742/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  12%| | 1742/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -16963,8 +16932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1743/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  12%| | 1743/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  12%| | 1743/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  12%| | 1743/14932 [02:33<19:23, 11.34it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -16972,8 +16941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1744/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  12%| | 1744/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  12%| | 1744/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  12%| | 1744/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -16981,8 +16950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1745/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  12%| | 1745/14932 [02:37<19:52, 11.06it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  12%| | 1745/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  12%| | 1745/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -16990,8 +16959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1746/14932 [02:37<19:51, 11.06it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  12%| | 1746/14932 [02:37<19:51, 11.06it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  12%| | 1746/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  12%| | 1746/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -16999,8 +16968,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1747/14932 [02:37<19:51, 11.06it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  12%| | 1747/14932 [02:37<19:51, 11.06it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  12%| | 1747/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -17008,8 +16976,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1748/14932 [02:37<19:51, 11.07it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  12%| | 1748/14932 [02:37<19:51, 11.07it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  12%| | 1747/14932 [02:33<19:22, 11.34it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -17017,8 +16984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1749/14932 [02:38<19:51, 11.07it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  12%| | 1749/14932 [02:38<19:51, 11.07it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  12%| | 1748/14932 [02:34<19:22, 11.35it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  12%| | 1748/14932 [02:34<19:22, 11.35it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -17026,8 +16993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1750/14932 [02:38<19:51, 11.07it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  12%| | 1750/14932 [02:38<19:51, 11.07it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  12%| | 1749/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  12%| | 1749/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -17035,8 +17002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1751/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  12%| | 1751/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  12%| | 1750/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  12%| | 1750/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -17044,8 +17011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1752/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  12%| | 1752/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  12%| | 1751/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  12%| | 1751/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -17053,8 +17020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1753/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  12%| | 1753/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  12%| | 1752/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  12%| | 1752/14932 [02:34<19:21, 11.35it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -17062,8 +17029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1754/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  12%| | 1754/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  12%| | 1753/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  12%| | 1753/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -17071,8 +17038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1755/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  12%| | 1755/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  12%| | 1754/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  12%| | 1754/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -17080,8 +17047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1756/14932 [02:38<19:49, 11.07it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  12%| | 1756/14932 [02:38<19:49, 11.07it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  12%| | 1755/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  12%| | 1755/14932 [02:34<19:20, 11.35it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -17089,8 +17056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1757/14932 [02:38<19:49, 11.08it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  12%| | 1757/14932 [02:38<19:49, 11.08it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  12%| | 1756/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  12%| | 1756/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -17098,8 +17065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1758/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  12%| | 1758/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  12%| | 1757/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  12%| | 1757/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -17107,8 +17074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1759/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  12%| | 1759/14932 [02:38<19:50, 11.07it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  12%| | 1758/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  12%| | 1758/14932 [02:34<19:20, 11.36it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -17116,8 +17083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1760/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  12%| | 1760/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  12%| | 1759/14932 [02:34<19:19, 11.36it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  12%| | 1759/14932 [02:34<19:19, 11.36it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -17125,8 +17092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1761/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  12%| | 1761/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  12%| | 1760/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  12%| | 1760/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -17134,8 +17101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1762/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  12%| | 1762/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  12%| | 1761/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  12%| | 1761/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -17143,8 +17110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1763/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  12%| | 1763/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  12%| | 1762/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  12%| | 1762/14932 [02:35<19:20, 11.35it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -17152,8 +17119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1764/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  12%| | 1764/14932 [02:39<19:50, 11.06it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  12%| | 1763/14932 [02:35<19:19, 11.35it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  12%| | 1763/14932 [02:35<19:19, 11.35it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -17161,8 +17128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1765/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  12%| | 1765/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  12%| | 1764/14932 [02:35<19:19, 11.35it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  12%| | 1764/14932 [02:35<19:19, 11.35it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -17170,8 +17137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1766/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  12%| | 1766/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  12%| | 1765/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  12%| | 1765/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -17179,8 +17146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1767/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  12%| | 1767/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  12%| | 1766/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  12%| | 1766/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -17188,8 +17155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1768/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  12%| | 1768/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  12%| | 1767/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  12%| | 1767/14932 [02:35<19:19, 11.36it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -17197,8 +17164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1769/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  12%| | 1769/14932 [02:39<19:49, 11.07it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:  12%| | 1768/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  12%| | 1768/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -17206,8 +17173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1770/14932 [02:39<19:48, 11.07it/s, v_num=o30c, train/loss=4.94\r",
-      "Epoch 0:  12%| | 1770/14932 [02:39<19:48, 11.07it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  12%| | 1769/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  12%| | 1769/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -17215,8 +17182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1771/14932 [02:39<19:48, 11.07it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  12%| | 1771/14932 [02:39<19:48, 11.07it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  12%| | 1770/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  12%| | 1770/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -17224,8 +17191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1772/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  12%| | 1772/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  12%| | 1771/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  12%| | 1771/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -17233,8 +17200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1773/14932 [02:40<19:48, 11.08it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  12%| | 1773/14932 [02:40<19:48, 11.08it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  12%| | 1772/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  12%| | 1772/14932 [02:35<19:18, 11.36it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -17242,8 +17209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1774/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  12%| | 1774/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  12%| | 1773/14932 [02:35<19:17, 11.37it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  12%| | 1773/14932 [02:35<19:17, 11.37it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -17251,8 +17218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1775/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  12%| | 1775/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  12%| | 1774/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  12%| | 1774/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -17260,8 +17227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1776/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  12%| | 1776/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=5.91"
+      "Epoch 0:  12%| | 1775/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  12%| | 1775/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -17269,8 +17236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1777/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=5.91\r",
-      "Epoch 0:  12%| | 1777/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  12%| | 1776/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  12%| | 1776/14932 [02:36<19:17, 11.37it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -17278,8 +17245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1778/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  12%| | 1778/14932 [02:40<19:48, 11.07it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  12%| | 1777/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  12%| | 1777/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -17287,8 +17254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1779/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  12%| | 1779/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  12%| | 1778/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  12%| | 1778/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -17296,7 +17263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1780/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  12%| | 1779/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  12%| | 1779/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -17304,7 +17272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1780/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  12%| | 1780/14932 [02:36<19:17, 11.36it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  12%| | 1780/14932 [02:36<19:17, 11.36it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -17312,8 +17281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1781/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  12%| | 1781/14932 [02:40<19:47, 11.07it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  12%| | 1781/14932 [02:36<19:17, 11.36it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  12%| | 1781/14932 [02:36<19:17, 11.36it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -17321,8 +17290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1782/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  12%| | 1782/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  12%| | 1782/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  12%| | 1782/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -17330,8 +17299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1783/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  12%| | 1783/14932 [02:40<19:47, 11.08it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  12%| | 1783/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  12%| | 1783/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -17339,8 +17308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1784/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  12%| | 1784/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  12%| | 1784/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  12%| | 1784/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -17348,8 +17317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1785/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  12%| | 1785/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  12%| | 1785/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  12%| | 1785/14932 [02:36<19:16, 11.37it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -17357,8 +17326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1786/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  12%| | 1786/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  12%| | 1786/14932 [02:37<19:16, 11.37it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  12%| | 1786/14932 [02:37<19:16, 11.37it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -17366,8 +17335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1787/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  12%| | 1787/14932 [02:41<19:46, 11.08it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  12%| | 1787/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  12%| | 1787/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -17375,8 +17344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1788/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  12%| | 1788/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  12%| | 1788/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  12%| | 1788/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -17384,8 +17353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1789/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  12%| | 1789/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  12%| | 1789/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  12%| | 1789/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -17393,8 +17362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1790/14932 [02:41<19:45, 11.09it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  12%| | 1790/14932 [02:41<19:45, 11.09it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  12%| | 1790/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  12%| | 1790/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=1.33"
      ]
     },
     {
@@ -17402,8 +17371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1791/14932 [02:41<19:45, 11.09it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  12%| | 1791/14932 [02:41<19:45, 11.09it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  12%| | 1791/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=1.33\r",
+      "Epoch 0:  12%| | 1791/14932 [02:37<19:15, 11.38it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -17411,8 +17380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1792/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  12%| | 1792/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  12%| | 1792/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  12%| | 1792/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -17420,8 +17389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1793/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  12%| | 1793/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  12%| | 1793/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  12%| | 1793/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -17429,8 +17398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1794/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  12%| | 1794/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  12%| | 1794/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  12%| | 1794/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -17438,8 +17407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1795/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  12%| | 1795/14932 [02:41<19:45, 11.08it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  12%| | 1795/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  12%| | 1795/14932 [02:37<19:15, 11.37it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -17447,8 +17416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1796/14932 [02:42<19:45, 11.08it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  12%| | 1796/14932 [02:42<19:45, 11.08it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  12%| | 1796/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  12%| | 1796/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -17456,8 +17425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1797/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  12%| | 1797/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  12%| | 1797/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  12%| | 1797/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -17465,8 +17434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1798/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  12%| | 1798/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  12%| | 1798/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  12%| | 1798/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -17474,8 +17443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1799/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  12%| | 1799/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  12%| | 1799/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  12%| | 1799/14932 [02:38<19:15, 11.37it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -17483,8 +17452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1800/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  12%| | 1800/14932 [02:42<19:44, 11.09it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  12%| | 1800/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  12%| | 1800/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -17492,8 +17461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1801/14932 [02:42<19:43, 11.09it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  12%| | 1801/14932 [02:42<19:43, 11.09it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  12%| | 1801/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  12%| | 1801/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -17501,8 +17470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1802/14932 [02:42<19:43, 11.09it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  12%| | 1802/14932 [02:42<19:43, 11.09it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  12%| | 1802/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  12%| | 1802/14932 [02:38<19:14, 11.37it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -17510,8 +17479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1803/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  12%| | 1803/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  12%| | 1803/14932 [02:38<19:14, 11.38it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  12%| | 1803/14932 [02:38<19:14, 11.38it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -17519,8 +17488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1804/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  12%| | 1804/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  12%| | 1804/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  12%| | 1804/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -17528,8 +17497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1805/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  12%| | 1805/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  12%| | 1805/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  12%| | 1805/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -17537,8 +17506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1806/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  12%| | 1806/14932 [02:43<19:50, 11.03it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  12%| | 1806/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  12%| | 1806/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -17546,8 +17515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1807/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  12%| | 1807/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  12%| | 1807/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  12%| | 1807/14932 [02:38<19:13, 11.38it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -17555,8 +17524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1808/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  12%| | 1808/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  12%| | 1808/14932 [02:38<19:12, 11.38it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  12%| | 1808/14932 [02:38<19:12, 11.38it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -17564,8 +17533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1809/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  12%| | 1809/14932 [02:43<19:49, 11.03it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  12%| | 1809/14932 [02:38<19:12, 11.38it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  12%| | 1809/14932 [02:38<19:12, 11.38it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -17573,8 +17542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1810/14932 [02:44<19:49, 11.03it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  12%| | 1810/14932 [02:44<19:49, 11.03it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  12%| | 1810/14932 [02:38<19:12, 11.39it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  12%| | 1810/14932 [02:38<19:12, 11.39it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -17582,8 +17551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1811/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  12%| | 1811/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=5.69"
+      "Epoch 0:  12%| | 1811/14932 [02:39<19:12, 11.39it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  12%| | 1811/14932 [02:39<19:12, 11.39it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -17591,8 +17560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1812/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=5.69\r",
-      "Epoch 0:  12%| | 1812/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  12%| | 1812/14932 [02:39<19:12, 11.39it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  12%| | 1812/14932 [02:39<19:12, 11.39it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -17600,8 +17569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1813/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  12%| | 1813/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  12%| | 1813/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  12%| | 1813/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -17609,8 +17578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1814/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  12%| | 1814/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  12%| | 1814/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  12%| | 1814/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -17618,8 +17587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1815/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  12%| | 1815/14932 [02:44<19:48, 11.04it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  12%| | 1815/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  12%| | 1815/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -17627,8 +17596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1816/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  12%| | 1816/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  12%| | 1816/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  12%| | 1816/14932 [02:39<19:11, 11.39it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -17636,8 +17605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1817/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  12%| | 1817/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  12%| | 1817/14932 [02:39<19:10, 11.39it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  12%| | 1817/14932 [02:39<19:10, 11.39it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -17645,8 +17614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1818/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  12%| | 1818/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  12%| | 1818/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  12%| | 1818/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -17654,8 +17623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1819/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  12%| | 1819/14932 [02:44<19:47, 11.04it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  12%| | 1819/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  12%| | 1819/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -17663,8 +17632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1820/14932 [02:44<19:47, 11.05it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  12%| | 1820/14932 [02:44<19:47, 11.05it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  12%| | 1820/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  12%| | 1820/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -17672,8 +17641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1821/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  12%| | 1821/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  12%| | 1821/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  12%| | 1821/14932 [02:39<19:10, 11.40it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -17681,8 +17650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1822/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  12%| | 1822/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  12%| | 1822/14932 [02:39<19:09, 11.40it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  12%| | 1822/14932 [02:39<19:09, 11.40it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -17690,8 +17659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1823/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  12%| | 1823/14932 [02:44<19:46, 11.05it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  12%| | 1823/14932 [02:39<19:09, 11.40it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  12%| | 1823/14932 [02:39<19:09, 11.40it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -17699,8 +17668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1824/14932 [02:45<19:47, 11.04it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  12%| | 1824/14932 [02:45<19:47, 11.04it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  12%| | 1824/14932 [02:40<19:11, 11.39it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  12%| | 1824/14932 [02:40<19:11, 11.39it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -17708,8 +17677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1825/14932 [02:45<19:46, 11.04it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  12%| | 1825/14932 [02:45<19:46, 11.04it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  12%| | 1825/14932 [02:40<19:11, 11.38it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  12%| | 1825/14932 [02:40<19:11, 11.38it/s, v_num=ui8w, train/loss=5.09"
      ]
     },
     {
@@ -17717,8 +17686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1826/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  12%| | 1826/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  12%| | 1826/14932 [02:40<19:11, 11.39it/s, v_num=ui8w, train/loss=5.09\r",
+      "Epoch 0:  12%| | 1826/14932 [02:40<19:11, 11.39it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -17726,8 +17695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1827/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  12%| | 1827/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  12%| | 1827/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  12%| | 1827/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -17735,8 +17704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1828/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  12%| | 1828/14932 [02:45<19:46, 11.05it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  12%| | 1828/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  12%| | 1828/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -17744,8 +17713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1829/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  12%| | 1829/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  12%| | 1829/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  12%| | 1829/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -17753,8 +17722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1830/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  12%| | 1830/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  12%| | 1830/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  12%| | 1830/14932 [02:40<19:10, 11.39it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -17762,8 +17731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1831/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  12%| | 1831/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  12%| | 1831/14932 [02:40<19:09, 11.39it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  12%| | 1831/14932 [02:40<19:09, 11.39it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -17771,8 +17740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1832/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  12%| | 1832/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  12%| | 1832/14932 [02:40<19:09, 11.39it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  12%| | 1832/14932 [02:40<19:09, 11.39it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -17780,8 +17749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1833/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  12%| | 1833/14932 [02:45<19:45, 11.05it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  12%| | 1833/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  12%| | 1833/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -17789,8 +17758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1834/14932 [02:45<19:44, 11.05it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  12%| | 1834/14932 [02:45<19:44, 11.05it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  12%| | 1834/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  12%| | 1834/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -17798,8 +17767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1835/14932 [02:45<19:44, 11.06it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  12%| | 1835/14932 [02:45<19:44, 11.06it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  12%| | 1835/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  12%| | 1835/14932 [02:40<19:09, 11.40it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -17807,8 +17776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1836/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  12%| | 1836/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  12%| | 1836/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  12%| | 1836/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -17816,8 +17785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1837/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  12%| | 1837/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  12%| | 1837/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  12%| | 1837/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -17825,8 +17794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1838/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  12%| | 1838/14932 [02:46<19:44, 11.06it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  12%| | 1838/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  12%| | 1838/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -17834,8 +17803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1839/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  12%| | 1839/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  12%| | 1839/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  12%| | 1839/14932 [02:41<19:08, 11.40it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -17843,8 +17812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1840/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  12%| | 1840/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  12%| | 1840/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  12%| | 1840/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -17852,8 +17821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1841/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  12%| | 1841/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  12%| | 1841/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  12%| | 1841/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -17861,8 +17830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1842/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  12%| | 1842/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  12%| | 1842/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  12%| | 1842/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -17870,8 +17839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1843/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  12%| | 1843/14932 [02:46<19:43, 11.06it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  12%| | 1843/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  12%| | 1843/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -17879,8 +17848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1844/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  12%| | 1844/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  12%| | 1844/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  12%| | 1844/14932 [02:41<19:07, 11.41it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -17888,7 +17857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1845/14932 [02:46<19:42, 11.07it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  12%| | 1845/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  12%| | 1845/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -17896,7 +17866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1845/14932 [02:46<19:42, 11.07it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  12%| | 1846/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  12%| | 1846/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -17904,8 +17875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1846/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  12%| | 1846/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  12%| | 1847/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  12%| | 1847/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -17913,8 +17884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1847/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  12%| | 1847/14932 [02:46<19:42, 11.06it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  12%| | 1848/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  12%| | 1848/14932 [02:41<19:06, 11.41it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -17922,8 +17893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1848/14932 [02:47<19:42, 11.06it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  12%| | 1848/14932 [02:47<19:42, 11.06it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  12%| | 1849/14932 [02:41<19:06, 11.42it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  12%| | 1849/14932 [02:41<19:06, 11.42it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -17931,8 +17902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1849/14932 [02:47<19:42, 11.07it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  12%| | 1849/14932 [02:47<19:42, 11.07it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  12%| | 1850/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  12%| | 1850/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -17940,8 +17911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1850/14932 [02:47<19:42, 11.07it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  12%| | 1850/14932 [02:47<19:42, 11.07it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  12%| | 1851/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  12%| | 1851/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -17949,8 +17920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1851/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  12%| | 1851/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  12%| | 1852/14932 [02:42<19:06, 11.41it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  12%| | 1852/14932 [02:42<19:06, 11.41it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -17958,8 +17929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1852/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  12%| | 1852/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  12%| | 1853/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  12%| | 1853/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -17967,8 +17938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1853/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  12%| | 1853/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  12%| | 1854/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  12%| | 1854/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -17976,8 +17947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1854/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  12%| | 1854/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  12%| | 1855/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  12%| | 1855/14932 [02:42<19:05, 11.42it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -17985,8 +17956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1855/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  12%| | 1855/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  12%| | 1856/14932 [02:42<19:06, 11.41it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  12%| | 1856/14932 [02:42<19:06, 11.41it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -17994,8 +17965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1856/14932 [02:47<19:41, 11.06it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  12%| | 1856/14932 [02:47<19:41, 11.06it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  12%| | 1857/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  12%| | 1857/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -18003,8 +17974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1857/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  12%| | 1857/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  12%| | 1858/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  12%| | 1858/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -18012,8 +17983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1858/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  12%| | 1858/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  12%| | 1859/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  12%| | 1859/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -18021,8 +17992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1859/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  12%| | 1859/14932 [02:47<19:41, 11.07it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  12%| | 1860/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  12%| | 1860/14932 [02:42<19:05, 11.41it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -18030,8 +18001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1860/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  12%| | 1860/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  12%| | 1861/14932 [02:43<19:05, 11.41it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  12%| | 1861/14932 [02:43<19:05, 11.41it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -18039,8 +18010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1861/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  12%| | 1861/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  12%| | 1862/14932 [02:43<19:05, 11.41it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  12%| | 1862/14932 [02:43<19:05, 11.41it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -18048,8 +18019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1862/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  12%| | 1862/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  12%| | 1863/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  12%| | 1863/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -18057,8 +18028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1863/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  12%| | 1863/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  12%| | 1864/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  12%| | 1864/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -18066,8 +18037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1864/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  12%| | 1864/14932 [02:48<19:40, 11.07it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  12%| | 1865/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  12%| | 1865/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -18075,8 +18046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1865/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  12%| | 1865/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  12%| | 1866/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  12%| | 1866/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -18084,8 +18055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  12%| | 1866/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  12%| | 1866/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  13%|▏| 1867/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  13%|▏| 1867/14932 [02:43<19:04, 11.42it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -18093,8 +18064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1867/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  13%|▏| 1867/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  13%|▏| 1868/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  13%|▏| 1868/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -18102,8 +18073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1868/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  13%|▏| 1868/14932 [02:48<19:39, 11.08it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  13%|▏| 1869/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  13%|▏| 1869/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -18111,8 +18082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1869/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  13%|▏| 1869/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  13%|▏| 1870/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  13%|▏| 1870/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -18120,8 +18091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1870/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  13%|▏| 1870/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  13%|▏| 1871/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  13%|▏| 1871/14932 [02:43<19:03, 11.42it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -18129,8 +18100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1871/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  13%|▏| 1871/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  13%|▏| 1872/14932 [02:43<19:03, 11.43it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  13%|▏| 1872/14932 [02:43<19:03, 11.43it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -18138,8 +18109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1872/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  13%|▏| 1872/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  13%|▏| 1873/14932 [02:43<19:02, 11.43it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  13%|▏| 1873/14932 [02:43<19:02, 11.43it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -18147,8 +18118,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1873/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  13%|▏| 1873/14932 [02:48<19:38, 11.08it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  13%|▏| 1874/14932 [02:43<19:02, 11.43it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -18156,8 +18126,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1874/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  13%|▏| 1874/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  13%|▏| 1874/14932 [02:43<19:02, 11.43it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -18165,8 +18134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1875/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  13%|▏| 1875/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  13%|▏| 1875/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  13%|▏| 1875/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -18174,8 +18143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1876/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  13%|▏| 1876/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  13%|▏| 1876/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  13%|▏| 1876/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -18183,8 +18152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1877/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  13%|▏| 1877/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  13%|▏| 1877/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  13%|▏| 1877/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -18192,8 +18161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1878/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  13%|▏| 1878/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  13%|▏| 1878/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  13%|▏| 1878/14932 [02:44<19:02, 11.43it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -18201,8 +18170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1879/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  13%|▏| 1879/14932 [02:49<19:38, 11.08it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  13%|▏| 1879/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  13%|▏| 1879/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -18210,8 +18179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1880/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  13%|▏| 1880/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  13%|▏| 1880/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  13%|▏| 1880/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -18219,8 +18188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1881/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  13%|▏| 1881/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  13%|▏| 1881/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  13%|▏| 1881/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -18228,8 +18197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1882/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  13%|▏| 1882/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  13%|▏| 1882/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  13%|▏| 1882/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -18237,8 +18206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1883/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  13%|▏| 1883/14932 [02:49<19:37, 11.08it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  13%|▏| 1883/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  13%|▏| 1883/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -18246,8 +18215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1884/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  13%|▏| 1884/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  13%|▏| 1884/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  13%|▏| 1884/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -18255,8 +18224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1885/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  13%|▏| 1885/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  13%|▏| 1885/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  13%|▏| 1885/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -18264,8 +18233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1886/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  13%|▏| 1886/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  13%|▏| 1886/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  13%|▏| 1886/14932 [02:44<19:01, 11.43it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -18273,8 +18242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1887/14932 [02:50<19:36, 11.09it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  13%|▏| 1887/14932 [02:50<19:36, 11.09it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  13%|▏| 1887/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  13%|▏| 1887/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -18282,8 +18251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1888/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  13%|▏| 1888/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  13%|▏| 1888/14932 [02:45<19:01, 11.42it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  13%|▏| 1888/14932 [02:45<19:01, 11.42it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -18291,8 +18260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1889/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  13%|▏| 1889/14932 [02:50<19:37, 11.08it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  13%|▏| 1889/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  13%|▏| 1889/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -18300,8 +18269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1890/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  13%|▏| 1890/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  13%|▏| 1890/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  13%|▏| 1890/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -18309,8 +18278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1891/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  13%|▏| 1891/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  13%|▏| 1891/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  13%|▏| 1891/14932 [02:45<19:01, 11.43it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -18318,8 +18287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1892/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  13%|▏| 1892/14932 [02:50<19:36, 11.08it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  13%|▏| 1892/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  13%|▏| 1892/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -18327,8 +18296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1893/14932 [02:50<19:36, 11.09it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  13%|▏| 1893/14932 [02:50<19:36, 11.09it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  13%|▏| 1893/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  13%|▏| 1893/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -18336,8 +18305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1894/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  13%|▏| 1894/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  13%|▏| 1894/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  13%|▏| 1894/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -18345,8 +18314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1895/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  13%|▏| 1895/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  13%|▏| 1895/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  13%|▏| 1895/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -18354,8 +18323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1896/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  13%|▏| 1896/14932 [02:50<19:35, 11.09it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  13%|▏| 1896/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  13%|▏| 1896/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -18363,7 +18332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1897/14932 [02:51<19:35, 11.09it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  13%|▏| 1897/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  13%|▏| 1897/14932 [02:45<19:00, 11.43it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -18371,7 +18341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1897/14932 [02:51<19:35, 11.09it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  13%|▏| 1898/14932 [02:45<18:59, 11.44it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  13%|▏| 1898/14932 [02:45<18:59, 11.43it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -18379,8 +18350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1898/14932 [02:51<19:34, 11.09it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  13%|▏| 1898/14932 [02:51<19:34, 11.09it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  13%|▏| 1899/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  13%|▏| 1899/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -18388,8 +18359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1899/14932 [02:51<19:34, 11.09it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  13%|▏| 1899/14932 [02:51<19:34, 11.09it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  13%|▏| 1900/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  13%|▏| 1900/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -18397,8 +18368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1900/14932 [02:51<19:34, 11.10it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  13%|▏| 1900/14932 [02:51<19:34, 11.10it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  13%|▏| 1901/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  13%|▏| 1901/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -18406,8 +18377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1901/14932 [02:51<19:34, 11.10it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  13%|▏| 1901/14932 [02:51<19:34, 11.10it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  13%|▏| 1902/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  13%|▏| 1902/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -18415,8 +18386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1902/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  13%|▏| 1902/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  13%|▏| 1903/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  13%|▏| 1903/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -18424,8 +18395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1903/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  13%|▏| 1903/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  13%|▏| 1904/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  13%|▏| 1904/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -18433,8 +18404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1904/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  13%|▏| 1904/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  13%|▏| 1905/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  13%|▏| 1905/14932 [02:46<18:59, 11.44it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -18442,8 +18413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1905/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  13%|▏| 1905/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  13%|▏| 1906/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  13%|▏| 1906/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -18451,8 +18422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1906/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  13%|▏| 1906/14932 [02:51<19:33, 11.10it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  13%|▏| 1907/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  13%|▏| 1907/14932 [02:46<18:59, 11.43it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -18460,8 +18431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1907/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  13%|▏| 1907/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=1.04"
+      "Epoch 0:  13%|▏| 1908/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  13%|▏| 1908/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -18469,8 +18440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1908/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=1.04\r",
-      "Epoch 0:  13%|▏| 1908/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  13%|▏| 1909/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  13%|▏| 1909/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -18478,8 +18449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1909/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  13%|▏| 1909/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  13%|▏| 1910/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  13%|▏| 1910/14932 [02:46<18:58, 11.44it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -18487,8 +18458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1910/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  13%|▏| 1910/14932 [02:51<19:32, 11.11it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  13%|▏| 1911/14932 [02:47<18:58, 11.44it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  13%|▏| 1911/14932 [02:47<18:58, 11.44it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -18496,8 +18467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1911/14932 [02:51<19:31, 11.11it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  13%|▏| 1911/14932 [02:51<19:31, 11.11it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  13%|▏| 1912/14932 [02:47<18:58, 11.44it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  13%|▏| 1912/14932 [02:47<18:58, 11.44it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -18505,8 +18476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1912/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  13%|▏| 1912/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  13%|▏| 1913/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  13%|▏| 1913/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -18514,8 +18485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1913/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  13%|▏| 1913/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  13%|▏| 1914/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  13%|▏| 1914/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -18523,8 +18494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1914/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  13%|▏| 1914/14932 [02:52<19:31, 11.11it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  13%|▏| 1915/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  13%|▏| 1915/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -18532,8 +18503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1915/14932 [02:52<19:31, 11.12it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  13%|▏| 1915/14932 [02:52<19:31, 11.12it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  13%|▏| 1916/14932 [02:47<18:57, 11.45it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  13%|▏| 1916/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -18541,8 +18512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1916/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  13%|▏| 1916/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  13%|▏| 1917/14932 [02:47<18:57, 11.45it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  13%|▏| 1917/14932 [02:47<18:57, 11.45it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -18550,8 +18521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1917/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  13%|▏| 1917/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  13%|▏| 1918/14932 [02:47<18:56, 11.45it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  13%|▏| 1918/14932 [02:47<18:56, 11.45it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -18559,8 +18530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1918/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  13%|▏| 1918/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  13%|▏| 1919/14932 [02:47<18:56, 11.45it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  13%|▏| 1919/14932 [02:47<18:56, 11.45it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -18568,8 +18539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1919/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  13%|▏| 1919/14932 [02:52<19:30, 11.12it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  13%|▏| 1920/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  13%|▏| 1920/14932 [02:47<18:57, 11.44it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -18577,8 +18548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1920/14932 [02:52<19:30, 11.11it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  13%|▏| 1920/14932 [02:52<19:30, 11.11it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  13%|▏| 1921/14932 [02:47<18:56, 11.44it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  13%|▏| 1921/14932 [02:47<18:56, 11.44it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -18586,8 +18557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1921/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  13%|▏| 1921/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  13%|▏| 1922/14932 [02:47<18:56, 11.44it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  13%|▏| 1922/14932 [02:47<18:56, 11.44it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -18595,8 +18566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1922/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  13%|▏| 1922/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  13%|▏| 1923/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  13%|▏| 1923/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -18604,8 +18575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1923/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  13%|▏| 1923/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  13%|▏| 1924/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  13%|▏| 1924/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -18613,8 +18584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1924/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  13%|▏| 1924/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  13%|▏| 1925/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  13%|▏| 1925/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -18622,8 +18593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1925/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  13%|▏| 1925/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  13%|▏| 1926/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  13%|▏| 1926/14932 [02:48<18:56, 11.45it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -18631,8 +18602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1926/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  13%|▏| 1926/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  13%|▏| 1927/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  13%|▏| 1927/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -18640,8 +18611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1927/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  13%|▏| 1927/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  13%|▏| 1928/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  13%|▏| 1928/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -18649,8 +18620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1928/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  13%|▏| 1928/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  13%|▏| 1929/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  13%|▏| 1929/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -18658,8 +18629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1929/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  13%|▏| 1929/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  13%|▏| 1930/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  13%|▏| 1930/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -18667,8 +18638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1930/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  13%|▏| 1930/14932 [02:53<19:31, 11.10it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  13%|▏| 1931/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  13%|▏| 1931/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -18676,8 +18647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1931/14932 [02:53<19:30, 11.10it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  13%|▏| 1931/14932 [02:53<19:30, 11.10it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  13%|▏| 1932/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  13%|▏| 1932/14932 [02:48<18:55, 11.45it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -18685,8 +18656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1932/14932 [02:53<19:30, 11.10it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  13%|▏| 1932/14932 [02:53<19:30, 11.10it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  13%|▏| 1933/14932 [02:48<18:54, 11.45it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  13%|▏| 1933/14932 [02:48<18:54, 11.45it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -18694,8 +18665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1933/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  13%|▏| 1933/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  13%|▏| 1934/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  13%|▏| 1934/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -18703,8 +18674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1934/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  13%|▏| 1934/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  13%|▏| 1935/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  13%|▏| 1935/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -18712,8 +18683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1935/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  13%|▏| 1935/14932 [02:54<19:30, 11.11it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  13%|▏| 1936/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  13%|▏| 1936/14932 [02:48<18:54, 11.46it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -18721,8 +18692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1936/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  13%|▏| 1936/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  13%|▏| 1937/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  13%|▏| 1937/14932 [02:49<18:54, 11.46it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -18730,8 +18701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1937/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  13%|▏| 1937/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  13%|▏| 1938/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  13%|▏| 1938/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -18739,8 +18710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1938/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  13%|▏| 1938/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  13%|▏| 1939/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  13%|▏| 1939/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -18748,8 +18719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1939/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  13%|▏| 1939/14932 [02:54<19:29, 11.11it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  13%|▏| 1940/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  13%|▏| 1940/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -18757,8 +18728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1940/14932 [02:54<19:28, 11.11it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  13%|▏| 1940/14932 [02:54<19:28, 11.11it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  13%|▏| 1941/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  13%|▏| 1941/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -18766,8 +18737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1941/14932 [02:54<19:28, 11.11it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  13%|▏| 1941/14932 [02:54<19:28, 11.11it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  13%|▏| 1942/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  13%|▏| 1942/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -18775,8 +18746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1942/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  13%|▏| 1942/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  13%|▏| 1943/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  13%|▏| 1943/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -18784,8 +18755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1943/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  13%|▏| 1943/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  13%|▏| 1944/14932 [02:49<18:52, 11.47it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  13%|▏| 1944/14932 [02:49<18:52, 11.47it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -18793,8 +18764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1944/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  13%|▏| 1944/14932 [02:54<19:28, 11.12it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  13%|▏| 1945/14932 [02:49<18:52, 11.47it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  13%|▏| 1945/14932 [02:49<18:52, 11.47it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -18802,8 +18773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1945/14932 [02:54<19:27, 11.12it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  13%|▏| 1945/14932 [02:54<19:27, 11.12it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  13%|▏| 1946/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  13%|▏| 1946/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -18811,8 +18782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1946/14932 [02:54<19:27, 11.12it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  13%|▏| 1946/14932 [02:54<19:27, 11.12it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  13%|▏| 1947/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  13%|▏| 1947/14932 [02:49<18:53, 11.46it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -18820,8 +18791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1947/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  13%|▏| 1947/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  13%|▏| 1948/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  13%|▏| 1948/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -18829,8 +18800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1948/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  13%|▏| 1948/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  13%|▏| 1949/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  13%|▏| 1949/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -18838,8 +18809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1949/14932 [02:55<19:29, 11.11it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  13%|▏| 1949/14932 [02:55<19:29, 11.11it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  13%|▏| 1950/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  13%|▏| 1950/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -18847,8 +18818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1950/14932 [02:55<19:28, 11.11it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  13%|▏| 1950/14932 [02:55<19:28, 11.11it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  13%|▏| 1951/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  13%|▏| 1951/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -18856,8 +18827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1951/14932 [02:55<19:28, 11.11it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  13%|▏| 1951/14932 [02:55<19:28, 11.11it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  13%|▏| 1952/14932 [02:50<18:53, 11.45it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  13%|▏| 1952/14932 [02:50<18:53, 11.45it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -18865,8 +18836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1952/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  13%|▏| 1952/14932 [02:55<19:29, 11.10it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  13%|▏| 1953/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  13%|▏| 1953/14932 [02:50<18:53, 11.46it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -18874,8 +18845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1953/14932 [02:55<19:28, 11.10it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  13%|▏| 1953/14932 [02:55<19:28, 11.10it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  13%|▏| 1954/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  13%|▏| 1954/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -18883,8 +18854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1954/14932 [02:55<19:28, 11.10it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  13%|▏| 1954/14932 [02:55<19:28, 11.10it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  13%|▏| 1955/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  13%|▏| 1955/14932 [02:50<18:52, 11.46it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -18892,8 +18863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1955/14932 [02:56<19:28, 11.10it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  13%|▏| 1955/14932 [02:56<19:28, 11.10it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  13%|▏| 1956/14932 [02:50<18:53, 11.45it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  13%|▏| 1956/14932 [02:50<18:53, 11.45it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -18901,8 +18872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1956/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  13%|▏| 1956/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  13%|▏| 1957/14932 [02:50<18:52, 11.45it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  13%|▏| 1957/14932 [02:50<18:52, 11.45it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -18910,8 +18881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1957/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  13%|▏| 1957/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  13%|▏| 1958/14932 [02:50<18:52, 11.45it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  13%|▏| 1958/14932 [02:50<18:52, 11.45it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -18919,8 +18890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1958/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  13%|▏| 1958/14932 [02:56<19:28, 11.11it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  13%|▏| 1959/14932 [02:51<18:52, 11.45it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  13%|▏| 1959/14932 [02:51<18:52, 11.45it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -18928,8 +18899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1959/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  13%|▏| 1959/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  13%|▏| 1960/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:  13%|▏| 1960/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -18937,8 +18908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1960/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  13%|▏| 1960/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  13%|▏| 1961/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  13%|▏| 1961/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -18946,8 +18917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1961/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  13%|▏| 1961/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  13%|▏| 1962/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  13%|▏| 1962/14932 [02:51<18:52, 11.46it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -18955,8 +18926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1962/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  13%|▏| 1962/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  13%|▏| 1963/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  13%|▏| 1963/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -18964,8 +18935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1963/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  13%|▏| 1963/14932 [02:56<19:27, 11.11it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  13%|▏| 1964/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  13%|▏| 1964/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -18973,8 +18944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1964/14932 [02:56<19:26, 11.11it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  13%|▏| 1964/14932 [02:56<19:26, 11.11it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  13%|▏| 1965/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  13%|▏| 1965/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -18982,8 +18953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1965/14932 [02:56<19:26, 11.11it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  13%|▏| 1965/14932 [02:56<19:26, 11.11it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  13%|▏| 1966/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  13%|▏| 1966/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -18991,8 +18962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1966/14932 [02:56<19:26, 11.12it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  13%|▏| 1966/14932 [02:56<19:26, 11.12it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  13%|▏| 1967/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  13%|▏| 1967/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=5.84"
      ]
     },
     {
@@ -19000,8 +18971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1967/14932 [02:56<19:26, 11.12it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  13%|▏| 1967/14932 [02:56<19:26, 11.12it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  13%|▏| 1968/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=5.84\r",
+      "Epoch 0:  13%|▏| 1968/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -19009,8 +18980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1968/14932 [02:57<19:26, 11.12it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  13%|▏| 1968/14932 [02:57<19:26, 11.12it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  13%|▏| 1969/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  13%|▏| 1969/14932 [02:51<18:51, 11.46it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -19018,8 +18989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1969/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  13%|▏| 1969/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  13%|▏| 1970/14932 [02:51<18:50, 11.46it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  13%|▏| 1970/14932 [02:51<18:50, 11.46it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -19027,8 +18998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1970/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  13%|▏| 1970/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  13%|▏| 1971/14932 [02:51<18:50, 11.46it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  13%|▏| 1971/14932 [02:51<18:50, 11.46it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -19036,8 +19007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1971/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  13%|▏| 1971/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  13%|▏| 1972/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  13%|▏| 1972/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -19045,8 +19016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1972/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  13%|▏| 1972/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  13%|▏| 1973/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  13%|▏| 1973/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -19054,8 +19025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1973/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  13%|▏| 1973/14932 [02:57<19:25, 11.12it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  13%|▏| 1974/14932 [02:52<18:50, 11.47it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  13%|▏| 1974/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -19063,8 +19034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1974/14932 [02:57<19:24, 11.12it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  13%|▏| 1974/14932 [02:57<19:24, 11.12it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  13%|▏| 1975/14932 [02:52<18:50, 11.47it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  13%|▏| 1975/14932 [02:52<18:50, 11.47it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -19072,8 +19043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1975/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  13%|▏| 1975/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  13%|▏| 1976/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  13%|▏| 1976/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -19081,8 +19052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1976/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  13%|▏| 1976/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  13%|▏| 1977/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  13%|▏| 1977/14932 [02:52<18:50, 11.46it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -19090,8 +19061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1977/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  13%|▏| 1977/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  13%|▏| 1978/14932 [02:52<18:49, 11.46it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  13%|▏| 1978/14932 [02:52<18:49, 11.46it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -19099,8 +19070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1978/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  13%|▏| 1978/14932 [02:57<19:24, 11.13it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  13%|▏| 1979/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  13%|▏| 1979/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -19108,8 +19079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1979/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  13%|▏| 1979/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  13%|▏| 1980/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  13%|▏| 1980/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -19117,8 +19088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1980/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  13%|▏| 1980/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  13%|▏| 1981/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  13%|▏| 1981/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -19126,8 +19097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1981/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  13%|▏| 1981/14932 [02:57<19:23, 11.13it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  13%|▏| 1982/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  13%|▏| 1982/14932 [02:52<18:49, 11.47it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -19135,8 +19106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1982/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  13%|▏| 1982/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  13%|▏| 1983/14932 [02:52<18:48, 11.47it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  13%|▏| 1983/14932 [02:52<18:48, 11.47it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -19144,8 +19115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1983/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  13%|▏| 1983/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  13%|▏| 1984/14932 [02:53<18:49, 11.46it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  13%|▏| 1984/14932 [02:53<18:49, 11.46it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -19153,8 +19124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1984/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  13%|▏| 1984/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  13%|▏| 1985/14932 [02:53<18:49, 11.46it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  13%|▏| 1985/14932 [02:53<18:49, 11.46it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -19162,8 +19133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1985/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  13%|▏| 1985/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  13%|▏| 1986/14932 [02:53<18:49, 11.47it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  13%|▏| 1986/14932 [02:53<18:49, 11.47it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -19171,8 +19142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1986/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  13%|▏| 1986/14932 [02:58<19:23, 11.13it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  13%|▏| 1987/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  13%|▏| 1987/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -19180,8 +19151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1987/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  13%|▏| 1987/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  13%|▏| 1988/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  13%|▏| 1988/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -19189,8 +19160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1988/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  13%|▏| 1988/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  13%|▏| 1989/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  13%|▏| 1989/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -19198,8 +19169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1989/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  13%|▏| 1989/14932 [02:58<19:22, 11.13it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  13%|▏| 1990/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  13%|▏| 1990/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -19207,8 +19178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1990/14932 [02:58<19:22, 11.14it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  13%|▏| 1990/14932 [02:58<19:22, 11.14it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  13%|▏| 1991/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  13%|▏| 1991/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -19216,8 +19187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1991/14932 [02:58<19:22, 11.14it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  13%|▏| 1991/14932 [02:58<19:22, 11.14it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  13%|▏| 1992/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  13%|▏| 1992/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -19225,8 +19196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1992/14932 [02:58<19:21, 11.14it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  13%|▏| 1992/14932 [02:58<19:21, 11.14it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  13%|▏| 1993/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  13%|▏| 1993/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -19234,8 +19205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1993/14932 [02:58<19:21, 11.14it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  13%|▏| 1993/14932 [02:58<19:21, 11.14it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  13%|▏| 1994/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  13%|▏| 1994/14932 [02:53<18:48, 11.47it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -19243,8 +19214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1994/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  13%|▏| 1994/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  13%|▏| 1995/14932 [02:53<18:47, 11.47it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  13%|▏| 1995/14932 [02:53<18:47, 11.47it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -19252,8 +19223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1995/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  13%|▏| 1995/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  13%|▏| 1996/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  13%|▏| 1996/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -19261,8 +19232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1996/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  13%|▏| 1996/14932 [02:59<19:21, 11.14it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  13%|▏| 1997/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  13%|▏| 1997/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -19270,8 +19241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1997/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  13%|▏| 1997/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  13%|▏| 1998/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  13%|▏| 1998/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -19279,8 +19250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1998/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  13%|▏| 1998/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  13%|▏| 1999/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  13%|▏| 1999/14932 [02:54<18:47, 11.47it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -19288,8 +19259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 1999/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  13%|▏| 1999/14932 [02:59<19:20, 11.14it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  13%|▏| 2000/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  13%|▏| 2000/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -19297,8 +19268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2000/14932 [02:59<19:20, 11.15it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  13%|▏| 2000/14932 [02:59<19:20, 11.15it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  13%|▏| 2001/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  13%|▏| 2001/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -19306,8 +19277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2001/14932 [02:59<19:20, 11.15it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  13%|▏| 2001/14932 [02:59<19:20, 11.15it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  13%|▏| 2002/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  13%|▏| 2002/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -19315,8 +19286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2002/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  13%|▏| 2002/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  13%|▏| 2003/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  13%|▏| 2003/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -19324,8 +19295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2003/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  13%|▏| 2003/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  13%|▏| 2004/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  13%|▏| 2004/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -19333,8 +19304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2004/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  13%|▏| 2004/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  13%|▏| 2005/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  13%|▏| 2005/14932 [02:54<18:46, 11.48it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -19342,8 +19313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2005/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  13%|▏| 2005/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  13%|▏| 2006/14932 [02:54<18:45, 11.48it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  13%|▏| 2006/14932 [02:54<18:45, 11.48it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -19351,8 +19322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2006/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  13%|▏| 2006/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  13%|▏| 2007/14932 [02:54<18:46, 11.47it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  13%|▏| 2007/14932 [02:54<18:46, 11.47it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -19360,8 +19331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2007/14932 [02:59<19:18, 11.15it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  13%|▏| 2007/14932 [02:59<19:19, 11.15it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  13%|▏| 2008/14932 [02:54<18:46, 11.47it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  13%|▏| 2008/14932 [02:54<18:46, 11.47it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -19369,8 +19340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2008/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  13%|▏| 2008/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  13%|▏| 2009/14932 [02:55<18:46, 11.48it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  13%|▏| 2009/14932 [02:55<18:46, 11.48it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -19378,8 +19349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2009/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  13%|▏| 2009/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  13%|▏| 2010/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  13%|▏| 2010/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -19387,8 +19358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2010/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  13%|▏| 2010/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  13%|▏| 2011/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  13%|▏| 2011/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -19396,8 +19367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2011/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  13%|▏| 2011/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  13%|▏| 2012/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  13%|▏| 2012/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -19405,8 +19376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2012/14932 [03:00<19:17, 11.16it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  13%|▏| 2012/14932 [03:00<19:17, 11.16it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  13%|▏| 2013/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  13%|▏| 2013/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -19414,8 +19385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2013/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  13%|▏| 2013/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  13%|▏| 2014/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  13%|▏| 2014/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -19423,8 +19394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2014/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  13%|▏| 2014/14932 [03:00<19:18, 11.16it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  13%|▏| 2015/14932 [02:55<18:44, 11.48it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  13%|▏| 2015/14932 [02:55<18:44, 11.48it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -19432,8 +19403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  13%|▏| 2015/14932 [03:00<19:17, 11.16it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  13%|▏| 2015/14932 [03:00<19:17, 11.16it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  14%|▏| 2016/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  14%|▏| 2016/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -19441,8 +19412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2016/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  14%|▏| 2016/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  14%|▏| 2017/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  14%|▏| 2017/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -19450,8 +19421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2017/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  14%|▏| 2017/14932 [03:00<19:18, 11.15it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  14%|▏| 2018/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  14%|▏| 2018/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -19459,8 +19430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2018/14932 [03:01<19:18, 11.15it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  14%|▏| 2018/14932 [03:01<19:18, 11.15it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  14%|▏| 2019/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  14%|▏| 2019/14932 [02:55<18:45, 11.48it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -19468,8 +19439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2019/14932 [03:01<19:18, 11.15it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  14%|▏| 2019/14932 [03:01<19:18, 11.15it/s, v_num=o30c, train/loss=1.56"
+      "Epoch 0:  14%|▏| 2020/14932 [02:55<18:44, 11.48it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  14%|▏| 2020/14932 [02:55<18:44, 11.48it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -19477,8 +19448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2020/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=1.56\r",
-      "Epoch 0:  14%|▏| 2020/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  14%|▏| 2021/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  14%|▏| 2021/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -19486,8 +19457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2021/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  14%|▏| 2021/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  14%|▏| 2022/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  14%|▏| 2022/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -19495,8 +19466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2022/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  14%|▏| 2022/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  14%|▏| 2023/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  14%|▏| 2023/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -19504,8 +19475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2023/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  14%|▏| 2023/14932 [03:01<19:17, 11.15it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  14%|▏| 2024/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  14%|▏| 2024/14932 [02:56<18:44, 11.48it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -19513,8 +19484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2024/14932 [03:01<19:17, 11.16it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  14%|▏| 2024/14932 [03:01<19:17, 11.16it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  14%|▏| 2025/14932 [02:56<18:43, 11.48it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  14%|▏| 2025/14932 [02:56<18:43, 11.48it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -19522,8 +19493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2025/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  14%|▏| 2025/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  14%|▏| 2026/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  14%|▏| 2026/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -19531,8 +19502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2026/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  14%|▏| 2026/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  14%|▏| 2027/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  14%|▏| 2027/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -19540,8 +19511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2027/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  14%|▏| 2027/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  14%|▏| 2028/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  14%|▏| 2028/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -19549,8 +19520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2028/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  14%|▏| 2028/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  14%|▏| 2029/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  14%|▏| 2029/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -19558,8 +19529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2029/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  14%|▏| 2029/14932 [03:01<19:16, 11.16it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  14%|▏| 2030/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  14%|▏| 2030/14932 [02:56<18:43, 11.49it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -19567,8 +19538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2030/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  14%|▏| 2030/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  14%|▏| 2031/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  14%|▏| 2031/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -19576,8 +19547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2031/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  14%|▏| 2031/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  14%|▏| 2032/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  14%|▏| 2032/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -19585,8 +19556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2032/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  14%|▏| 2032/14932 [03:01<19:15, 11.16it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  14%|▏| 2033/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  14%|▏| 2033/14932 [02:56<18:42, 11.49it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -19594,8 +19565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2033/14932 [03:02<19:16, 11.16it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  14%|▏| 2033/14932 [03:02<19:16, 11.16it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  14%|▏| 2034/14932 [02:57<18:42, 11.49it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  14%|▏| 2034/14932 [02:57<18:42, 11.49it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -19603,8 +19574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2034/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  14%|▏| 2034/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  14%|▏| 2035/14932 [02:57<18:42, 11.49it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  14%|▏| 2035/14932 [02:57<18:42, 11.49it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -19612,8 +19583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2035/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  14%|▏| 2035/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  14%|▏| 2036/14932 [02:57<18:41, 11.49it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  14%|▏| 2036/14932 [02:57<18:41, 11.49it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -19621,8 +19592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2036/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  14%|▏| 2036/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  14%|▏| 2037/14932 [02:57<18:41, 11.49it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  14%|▏| 2037/14932 [02:57<18:41, 11.49it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -19630,8 +19601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2037/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  14%|▏| 2037/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  14%|▏| 2038/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  14%|▏| 2038/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -19639,8 +19610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2038/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  14%|▏| 2038/14932 [03:02<19:15, 11.16it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  14%|▏| 2039/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  14%|▏| 2039/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -19648,8 +19619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2039/14932 [03:02<19:16, 11.15it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  14%|▏| 2039/14932 [03:02<19:16, 11.15it/s, v_num=o30c, train/loss=5.16"
+      "Epoch 0:  14%|▏| 2040/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  14%|▏| 2040/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -19657,8 +19628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2040/14932 [03:02<19:16, 11.15it/s, v_num=o30c, train/loss=5.16\r",
-      "Epoch 0:  14%|▏| 2040/14932 [03:02<19:16, 11.15it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  14%|▏| 2041/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  14%|▏| 2041/14932 [02:57<18:41, 11.50it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -19666,8 +19637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2041/14932 [03:03<19:16, 11.15it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  14%|▏| 2041/14932 [03:03<19:16, 11.15it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  14%|▏| 2042/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  14%|▏| 2042/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -19675,8 +19646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2042/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  14%|▏| 2042/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  14%|▏| 2043/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  14%|▏| 2043/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -19684,8 +19655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2043/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  14%|▏| 2043/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  14%|▏| 2044/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  14%|▏| 2044/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -19693,8 +19664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2044/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  14%|▏| 2044/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  14%|▏| 2045/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  14%|▏| 2045/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -19702,8 +19673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2045/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  14%|▏| 2045/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  14%|▏| 2046/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  14%|▏| 2046/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -19711,8 +19682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2046/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  14%|▏| 2046/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  14%|▏| 2047/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  14%|▏| 2047/14932 [02:57<18:40, 11.50it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -19720,8 +19691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2047/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  14%|▏| 2047/14932 [03:03<19:15, 11.15it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  14%|▏| 2048/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  14%|▏| 2048/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -19729,8 +19700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2048/14932 [03:03<19:16, 11.14it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  14%|▏| 2048/14932 [03:03<19:16, 11.14it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  14%|▏| 2049/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  14%|▏| 2049/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -19738,8 +19709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2049/14932 [03:03<19:16, 11.14it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  14%|▏| 2049/14932 [03:03<19:16, 11.14it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  14%|▏| 2050/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  14%|▏| 2050/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -19747,8 +19718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2050/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  14%|▏| 2050/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  14%|▏| 2051/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  14%|▏| 2051/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -19756,8 +19727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2051/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  14%|▏| 2051/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  14%|▏| 2052/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  14%|▏| 2052/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -19765,8 +19736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2052/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  14%|▏| 2052/14932 [03:04<19:16, 11.14it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  14%|▏| 2053/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  14%|▏| 2053/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -19774,8 +19745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2053/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  14%|▏| 2053/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  14%|▏| 2054/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  14%|▏| 2054/14932 [02:58<18:40, 11.50it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -19783,8 +19754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2054/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  14%|▏| 2054/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  14%|▏| 2055/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  14%|▏| 2055/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -19792,8 +19763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2055/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  14%|▏| 2055/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  14%|▏| 2056/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  14%|▏| 2056/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -19801,8 +19772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2056/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  14%|▏| 2056/14932 [03:04<19:15, 11.14it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  14%|▏| 2057/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  14%|▏| 2057/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -19810,8 +19781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2057/14932 [03:04<19:15, 11.15it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  14%|▏| 2057/14932 [03:04<19:15, 11.15it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2058/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  14%|▏| 2058/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -19819,8 +19790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2058/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2058/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  14%|▏| 2059/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  14%|▏| 2059/14932 [02:58<18:39, 11.50it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -19828,8 +19799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2059/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  14%|▏| 2059/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  14%|▏| 2060/14932 [02:59<18:39, 11.50it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  14%|▏| 2060/14932 [02:59<18:39, 11.50it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -19837,8 +19808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2060/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  14%|▏| 2060/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  14%|▏| 2061/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  14%|▏| 2061/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -19846,8 +19817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2061/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  14%|▏| 2061/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  14%|▏| 2062/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  14%|▏| 2062/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -19855,8 +19826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2062/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  14%|▏| 2062/14932 [03:04<19:14, 11.15it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  14%|▏| 2063/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  14%|▏| 2063/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -19864,8 +19835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2063/14932 [03:04<19:13, 11.15it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  14%|▏| 2063/14932 [03:04<19:13, 11.15it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  14%|▏| 2064/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  14%|▏| 2064/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -19873,8 +19844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2064/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  14%|▏| 2064/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  14%|▏| 2065/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  14%|▏| 2065/14932 [02:59<18:38, 11.51it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -19882,8 +19853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2065/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  14%|▏| 2065/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  14%|▏| 2066/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  14%|▏| 2066/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -19891,8 +19862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2066/14932 [03:05<19:14, 11.15it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  14%|▏| 2066/14932 [03:05<19:14, 11.15it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2067/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  14%|▏| 2067/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -19900,8 +19871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2067/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2067/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  14%|▏| 2068/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  14%|▏| 2068/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -19909,8 +19880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2068/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  14%|▏| 2068/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  14%|▏| 2069/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  14%|▏| 2069/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -19918,8 +19889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2069/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  14%|▏| 2069/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  14%|▏| 2070/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  14%|▏| 2070/14932 [02:59<18:38, 11.50it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -19927,8 +19898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2070/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  14%|▏| 2070/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  14%|▏| 2071/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  14%|▏| 2071/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -19936,8 +19907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2071/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  14%|▏| 2071/14932 [03:05<19:13, 11.15it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  14%|▏| 2072/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  14%|▏| 2072/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -19945,8 +19916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2072/14932 [03:05<19:12, 11.15it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  14%|▏| 2072/14932 [03:05<19:12, 11.15it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  14%|▏| 2073/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  14%|▏| 2073/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -19954,8 +19925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2073/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  14%|▏| 2073/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2074/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  14%|▏| 2074/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -19963,8 +19934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2074/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2074/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  14%|▏| 2075/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  14%|▏| 2075/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -19972,8 +19943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2075/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  14%|▏| 2075/14932 [03:05<19:12, 11.16it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  14%|▏| 2076/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  14%|▏| 2076/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -19981,8 +19952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2076/14932 [03:06<19:12, 11.16it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  14%|▏| 2076/14932 [03:06<19:12, 11.16it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  14%|▏| 2077/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  14%|▏| 2077/14932 [03:00<18:37, 11.51it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -19990,8 +19961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2077/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  14%|▏| 2077/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  14%|▏| 2078/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  14%|▏| 2078/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -19999,8 +19970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2078/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  14%|▏| 2078/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  14%|▏| 2079/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  14%|▏| 2079/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -20008,8 +19979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2079/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  14%|▏| 2079/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  14%|▏| 2080/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  14%|▏| 2080/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -20017,8 +19988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2080/14932 [03:06<19:12, 11.15it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  14%|▏| 2080/14932 [03:06<19:12, 11.15it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  14%|▏| 2081/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  14%|▏| 2081/14932 [03:00<18:37, 11.50it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -20026,8 +19997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2081/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  14%|▏| 2081/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  14%|▏| 2082/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  14%|▏| 2082/14932 [03:00<18:36, 11.51it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -20035,8 +20006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2082/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  14%|▏| 2082/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  14%|▏| 2083/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  14%|▏| 2083/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -20044,8 +20015,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2083/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  14%|▏| 2083/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  14%|▏| 2084/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -20053,8 +20023,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2084/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  14%|▏| 2084/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  14%|▏| 2084/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -20062,8 +20031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2085/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  14%|▏| 2085/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  14%|▏| 2085/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  14%|▏| 2085/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -20071,8 +20040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2086/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  14%|▏| 2086/14932 [03:06<19:11, 11.16it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  14%|▏| 2086/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  14%|▏| 2086/14932 [03:01<18:36, 11.51it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -20080,8 +20049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2087/14932 [03:06<19:10, 11.16it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  14%|▏| 2087/14932 [03:06<19:10, 11.16it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  14%|▏| 2087/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  14%|▏| 2087/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -20089,8 +20058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2088/14932 [03:07<19:11, 11.16it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  14%|▏| 2088/14932 [03:07<19:11, 11.16it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  14%|▏| 2088/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  14%|▏| 2088/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -20098,8 +20067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2089/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  14%|▏| 2089/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  14%|▏| 2089/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  14%|▏| 2089/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -20107,8 +20076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2090/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  14%|▏| 2090/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  14%|▏| 2090/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  14%|▏| 2090/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -20116,8 +20085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2091/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  14%|▏| 2091/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  14%|▏| 2091/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  14%|▏| 2091/14932 [03:01<18:35, 11.51it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -20125,8 +20094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2092/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  14%|▏| 2092/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  14%|▏| 2092/14932 [03:01<18:35, 11.52it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  14%|▏| 2092/14932 [03:01<18:35, 11.52it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -20134,8 +20103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2093/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  14%|▏| 2093/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  14%|▏| 2093/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  14%|▏| 2093/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -20143,8 +20112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2094/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  14%|▏| 2094/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  14%|▏| 2094/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  14%|▏| 2094/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -20152,8 +20121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2095/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  14%|▏| 2095/14932 [03:07<19:10, 11.16it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  14%|▏| 2095/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  14%|▏| 2095/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -20161,8 +20130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2096/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  14%|▏| 2096/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  14%|▏| 2096/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  14%|▏| 2096/14932 [03:01<18:34, 11.52it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -20170,7 +20139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2097/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  14%|▏| 2097/14932 [03:02<18:34, 11.52it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  14%|▏| 2097/14932 [03:02<18:34, 11.52it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -20178,7 +20148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2097/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  14%|▏| 2098/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  14%|▏| 2098/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -20186,8 +20157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2098/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  14%|▏| 2098/14932 [03:07<19:09, 11.16it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  14%|▏| 2099/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  14%|▏| 2099/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -20195,8 +20166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2099/14932 [03:07<19:09, 11.17it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  14%|▏| 2099/14932 [03:07<19:09, 11.17it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  14%|▏| 2100/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  14%|▏| 2100/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -20204,8 +20175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2100/14932 [03:08<19:09, 11.17it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  14%|▏| 2100/14932 [03:08<19:09, 11.17it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  14%|▏| 2101/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  14%|▏| 2101/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -20213,8 +20184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2101/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  14%|▏| 2101/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  14%|▏| 2102/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  14%|▏| 2102/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -20222,8 +20193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2102/14932 [03:08<19:09, 11.16it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  14%|▏| 2102/14932 [03:08<19:09, 11.16it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  14%|▏| 2103/14932 [03:02<18:33, 11.53it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  14%|▏| 2103/14932 [03:02<18:33, 11.52it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -20231,8 +20202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2103/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  14%|▏| 2103/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  14%|▏| 2104/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  14%|▏| 2104/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -20240,8 +20211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2104/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  14%|▏| 2104/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  14%|▏| 2105/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  14%|▏| 2105/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -20249,8 +20220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2105/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  14%|▏| 2105/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  14%|▏| 2106/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  14%|▏| 2106/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -20258,8 +20229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2106/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  14%|▏| 2106/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  14%|▏| 2107/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  14%|▏| 2107/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -20267,8 +20238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2107/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  14%|▏| 2107/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  14%|▏| 2108/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  14%|▏| 2108/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -20276,8 +20247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2108/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  14%|▏| 2108/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  14%|▏| 2109/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  14%|▏| 2109/14932 [03:02<18:32, 11.53it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -20285,8 +20256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2109/14932 [03:08<19:07, 11.17it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  14%|▏| 2109/14932 [03:08<19:07, 11.17it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  14%|▏| 2110/14932 [03:03<18:37, 11.47it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  14%|▏| 2110/14932 [03:03<18:37, 11.47it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -20294,8 +20265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2110/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  14%|▏| 2110/14932 [03:08<19:08, 11.17it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  14%|▏| 2111/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  14%|▏| 2111/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -20303,8 +20274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2111/14932 [03:08<19:07, 11.17it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  14%|▏| 2111/14932 [03:08<19:07, 11.17it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  14%|▏| 2112/14932 [03:04<18:38, 11.46it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  14%|▏| 2112/14932 [03:04<18:38, 11.46it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -20312,8 +20283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2112/14932 [03:09<19:08, 11.16it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  14%|▏| 2112/14932 [03:09<19:08, 11.16it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  14%|▏| 2113/14932 [03:04<18:38, 11.47it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  14%|▏| 2113/14932 [03:04<18:38, 11.46it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -20321,8 +20292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2113/14932 [03:09<19:08, 11.17it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  14%|▏| 2113/14932 [03:09<19:08, 11.17it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  14%|▏| 2114/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  14%|▏| 2114/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -20330,8 +20301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2114/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  14%|▏| 2114/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  14%|▏| 2115/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  14%|▏| 2115/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -20339,8 +20310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2115/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  14%|▏| 2115/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2116/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  14%|▏| 2116/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -20348,8 +20319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2116/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2116/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  14%|▏| 2117/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  14%|▏| 2117/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -20357,8 +20328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2117/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  14%|▏| 2117/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  14%|▏| 2118/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  14%|▏| 2118/14932 [03:04<18:37, 11.47it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -20366,8 +20337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2118/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  14%|▏| 2118/14932 [03:09<19:07, 11.17it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  14%|▏| 2119/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  14%|▏| 2119/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -20375,8 +20346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2119/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  14%|▏| 2119/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  14%|▏| 2120/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  14%|▏| 2120/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -20384,8 +20355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2120/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  14%|▏| 2120/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=1.25"
+      "Epoch 0:  14%|▏| 2121/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  14%|▏| 2121/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -20393,8 +20364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2121/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=1.25\r",
-      "Epoch 0:  14%|▏| 2121/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  14%|▏| 2122/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  14%|▏| 2122/14932 [03:04<18:36, 11.47it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -20402,8 +20373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2122/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  14%|▏| 2122/14932 [03:09<19:06, 11.17it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  14%|▏| 2123/14932 [03:05<18:36, 11.48it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  14%|▏| 2123/14932 [03:05<18:36, 11.48it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -20411,8 +20382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2123/14932 [03:09<19:06, 11.18it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  14%|▏| 2123/14932 [03:09<19:06, 11.18it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  14%|▏| 2124/14932 [03:05<18:36, 11.48it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  14%|▏| 2124/14932 [03:05<18:36, 11.48it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -20420,8 +20391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2124/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  14%|▏| 2124/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  14%|▏| 2125/14932 [03:05<18:36, 11.47it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  14%|▏| 2125/14932 [03:05<18:36, 11.47it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -20429,8 +20400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2125/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  14%|▏| 2125/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  14%|▏| 2126/14932 [03:05<18:36, 11.47it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  14%|▏| 2126/14932 [03:05<18:36, 11.47it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -20438,8 +20409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2126/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  14%|▏| 2126/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  14%|▏| 2127/14932 [03:05<18:35, 11.47it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  14%|▏| 2127/14932 [03:05<18:35, 11.47it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -20447,8 +20418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2127/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  14%|▏| 2127/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  14%|▏| 2128/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  14%|▏| 2128/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -20456,8 +20427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2128/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  14%|▏| 2128/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  14%|▏| 2129/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  14%|▏| 2129/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -20465,8 +20436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2129/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  14%|▏| 2129/14932 [03:10<19:05, 11.18it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  14%|▏| 2130/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  14%|▏| 2130/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -20474,8 +20445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2130/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  14%|▏| 2130/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  14%|▏| 2131/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  14%|▏| 2131/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -20483,8 +20454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2131/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  14%|▏| 2131/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  14%|▏| 2132/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  14%|▏| 2132/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -20492,8 +20463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2132/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  14%|▏| 2132/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  14%|▏| 2133/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  14%|▏| 2133/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -20501,8 +20472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2133/14932 [03:10<19:04, 11.19it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  14%|▏| 2133/14932 [03:10<19:04, 11.19it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  14%|▏| 2134/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  14%|▏| 2134/14932 [03:05<18:35, 11.48it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -20510,8 +20481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2134/14932 [03:10<19:04, 11.19it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  14%|▏| 2134/14932 [03:10<19:04, 11.19it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  14%|▏| 2135/14932 [03:06<18:35, 11.47it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  14%|▏| 2135/14932 [03:06<18:35, 11.47it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -20519,8 +20490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2135/14932 [03:10<19:03, 11.19it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  14%|▏| 2135/14932 [03:10<19:03, 11.19it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  14%|▏| 2136/14932 [03:06<18:35, 11.48it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  14%|▏| 2136/14932 [03:06<18:35, 11.48it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -20528,8 +20499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2136/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  14%|▏| 2136/14932 [03:10<19:04, 11.18it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  14%|▏| 2137/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  14%|▏| 2137/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -20537,8 +20508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2137/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  14%|▏| 2137/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  14%|▏| 2138/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  14%|▏| 2138/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -20546,8 +20517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2138/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  14%|▏| 2138/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  14%|▏| 2139/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  14%|▏| 2139/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -20555,8 +20526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2139/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  14%|▏| 2139/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2140/14932 [03:06<18:34, 11.47it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  14%|▏| 2140/14932 [03:06<18:34, 11.47it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -20564,8 +20535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2140/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2140/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  14%|▏| 2141/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  14%|▏| 2141/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -20573,8 +20544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2141/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  14%|▏| 2141/14932 [03:11<19:03, 11.19it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  14%|▏| 2142/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  14%|▏| 2142/14932 [03:06<18:34, 11.48it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -20582,8 +20553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2142/14932 [03:11<19:02, 11.19it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  14%|▏| 2142/14932 [03:11<19:02, 11.19it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  14%|▏| 2143/14932 [03:06<18:34, 11.47it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  14%|▏| 2143/14932 [03:06<18:34, 11.47it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -20591,8 +20562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2143/14932 [03:11<19:02, 11.19it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  14%|▏| 2143/14932 [03:11<19:02, 11.19it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  14%|▏| 2144/14932 [03:06<18:35, 11.47it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  14%|▏| 2144/14932 [03:06<18:35, 11.47it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -20600,8 +20571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2144/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  14%|▏| 2144/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  14%|▏| 2145/14932 [03:07<18:35, 11.47it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  14%|▏| 2145/14932 [03:07<18:35, 11.47it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -20609,8 +20580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2145/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  14%|▏| 2145/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  14%|▏| 2146/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  14%|▏| 2146/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -20618,8 +20589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2146/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  14%|▏| 2146/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  14%|▏| 2147/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  14%|▏| 2147/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -20627,8 +20598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2147/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  14%|▏| 2147/14932 [03:11<19:03, 11.18it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  14%|▏| 2148/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  14%|▏| 2148/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -20636,8 +20607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2148/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  14%|▏| 2148/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  14%|▏| 2149/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  14%|▏| 2149/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -20645,8 +20616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2149/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  14%|▏| 2149/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  14%|▏| 2150/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  14%|▏| 2150/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -20654,8 +20625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2150/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  14%|▏| 2150/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  14%|▏| 2151/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  14%|▏| 2151/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -20663,8 +20634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2151/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  14%|▏| 2151/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  14%|▏| 2152/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  14%|▏| 2152/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -20672,8 +20643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2152/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  14%|▏| 2152/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  14%|▏| 2153/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  14%|▏| 2153/14932 [03:07<18:34, 11.47it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -20681,8 +20652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2153/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  14%|▏| 2153/14932 [03:12<19:02, 11.19it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  14%|▏| 2154/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  14%|▏| 2154/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -20690,8 +20661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2154/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  14%|▏| 2154/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  14%|▏| 2155/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  14%|▏| 2155/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -20699,8 +20670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2155/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  14%|▏| 2155/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  14%|▏| 2156/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  14%|▏| 2156/14932 [03:07<18:33, 11.47it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -20708,8 +20679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2156/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  14%|▏| 2156/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  14%|▏| 2157/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  14%|▏| 2157/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -20717,8 +20688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2157/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  14%|▏| 2157/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  14%|▏| 2158/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  14%|▏| 2158/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -20726,8 +20697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2158/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  14%|▏| 2158/14932 [03:12<19:01, 11.19it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  14%|▏| 2159/14932 [03:08<18:34, 11.46it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  14%|▏| 2159/14932 [03:08<18:34, 11.46it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -20735,8 +20706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2159/14932 [03:12<19:00, 11.19it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  14%|▏| 2159/14932 [03:12<19:00, 11.19it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  14%|▏| 2160/14932 [03:08<18:34, 11.46it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  14%|▏| 2160/14932 [03:08<18:34, 11.46it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -20744,8 +20715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2160/14932 [03:12<19:00, 11.20it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  14%|▏| 2160/14932 [03:12<19:00, 11.20it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  14%|▏| 2161/14932 [03:08<18:33, 11.46it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  14%|▏| 2161/14932 [03:08<18:33, 11.46it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -20753,8 +20724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2161/14932 [03:13<19:00, 11.20it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  14%|▏| 2161/14932 [03:13<19:00, 11.20it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  14%|▏| 2162/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  14%|▏| 2162/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -20762,8 +20733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2162/14932 [03:13<19:00, 11.20it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  14%|▏| 2162/14932 [03:13<19:00, 11.20it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  14%|▏| 2163/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  14%|▏| 2163/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -20771,8 +20742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2163/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  14%|▏| 2163/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  14%|▏| 2164/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  14%|▏| 2164/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -20780,8 +20751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2164/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  14%|▏| 2164/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  14%|▏| 2165/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  14%|▏| 2165/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -20789,8 +20760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  14%|▏| 2165/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  14%|▏| 2165/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  15%|▏| 2166/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  15%|▏| 2166/14932 [03:08<18:33, 11.47it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -20798,8 +20769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2166/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  15%|▏| 2166/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  15%|▏| 2167/14932 [03:08<18:32, 11.47it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  15%|▏| 2167/14932 [03:08<18:32, 11.47it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -20807,8 +20778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2167/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  15%|▏| 2167/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  15%|▏| 2168/14932 [03:08<18:32, 11.47it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  15%|▏| 2168/14932 [03:08<18:32, 11.47it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -20816,8 +20787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2168/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  15%|▏| 2168/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  15%|▏| 2169/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  15%|▏| 2169/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -20825,8 +20796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2169/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  15%|▏| 2169/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  15%|▏| 2170/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  15%|▏| 2170/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -20834,8 +20805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2170/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  15%|▏| 2170/14932 [03:13<19:00, 11.19it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  15%|▏| 2171/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  15%|▏| 2171/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -20843,8 +20814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2171/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  15%|▏| 2171/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  15%|▏| 2172/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  15%|▏| 2172/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -20852,8 +20823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2172/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  15%|▏| 2172/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  15%|▏| 2173/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  15%|▏| 2173/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -20861,8 +20832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2173/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  15%|▏| 2173/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  15%|▏| 2174/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  15%|▏| 2174/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -20870,8 +20841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2174/14932 [03:14<18:59, 11.19it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  15%|▏| 2174/14932 [03:14<18:59, 11.19it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  15%|▏| 2175/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  15%|▏| 2175/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -20879,8 +20850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2175/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  15%|▏| 2175/14932 [03:14<19:00, 11.19it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  15%|▏| 2176/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  15%|▏| 2176/14932 [03:09<18:32, 11.47it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -20888,8 +20859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2176/14932 [03:14<19:01, 11.18it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  15%|▏| 2176/14932 [03:14<19:01, 11.18it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  15%|▏| 2177/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  15%|▏| 2177/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -20897,8 +20868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2177/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  15%|▏| 2177/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  15%|▏| 2178/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  15%|▏| 2178/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -20906,8 +20877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2178/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  15%|▏| 2178/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  15%|▏| 2179/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  15%|▏| 2179/14932 [03:09<18:31, 11.47it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -20915,8 +20886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2179/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  15%|▏| 2179/14932 [03:14<19:00, 11.18it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  15%|▏| 2180/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  15%|▏| 2180/14932 [03:09<18:31, 11.48it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -20924,8 +20895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2180/14932 [03:15<19:01, 11.17it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  15%|▏| 2180/14932 [03:15<19:01, 11.17it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  15%|▏| 2181/14932 [03:10<18:31, 11.48it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  15%|▏| 2181/14932 [03:10<18:31, 11.48it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -20933,8 +20904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2181/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  15%|▏| 2181/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  15%|▏| 2182/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  15%|▏| 2182/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -20942,8 +20913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2182/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  15%|▏| 2182/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  15%|▏| 2183/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  15%|▏| 2183/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -20951,8 +20922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2183/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  15%|▏| 2183/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  15%|▏| 2184/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  15%|▏| 2184/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -20960,8 +20931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2184/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  15%|▏| 2184/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  15%|▏| 2185/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  15%|▏| 2185/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -20969,8 +20940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2185/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  15%|▏| 2185/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  15%|▏| 2186/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  15%|▏| 2186/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -20978,8 +20949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2186/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  15%|▏| 2186/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  15%|▏| 2187/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  15%|▏| 2187/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -20987,8 +20958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2187/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  15%|▏| 2187/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  15%|▏| 2188/14932 [03:10<18:29, 11.48it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  15%|▏| 2188/14932 [03:10<18:29, 11.48it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -20996,8 +20967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2188/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  15%|▏| 2188/14932 [03:15<19:00, 11.18it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  15%|▏| 2189/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  15%|▏| 2189/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -21005,8 +20976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2189/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  15%|▏| 2189/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  15%|▏| 2190/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  15%|▏| 2190/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -21014,8 +20985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2190/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  15%|▏| 2190/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  15%|▏| 2191/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  15%|▏| 2191/14932 [03:10<18:30, 11.48it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -21023,8 +20994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2191/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  15%|▏| 2191/14932 [03:15<18:59, 11.18it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  15%|▏| 2192/14932 [03:10<18:29, 11.48it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  15%|▏| 2192/14932 [03:10<18:29, 11.48it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -21032,8 +21003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2192/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  15%|▏| 2192/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  15%|▏| 2193/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  15%|▏| 2193/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -21041,8 +21012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2193/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  15%|▏| 2193/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  15%|▏| 2194/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  15%|▏| 2194/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -21050,8 +21021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2194/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  15%|▏| 2194/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  15%|▏| 2195/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  15%|▏| 2195/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -21059,8 +21030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2195/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  15%|▏| 2195/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  15%|▏| 2196/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  15%|▏| 2196/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -21068,8 +21039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2196/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  15%|▏| 2196/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  15%|▏| 2197/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  15%|▏| 2197/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -21077,8 +21048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2197/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  15%|▏| 2197/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  15%|▏| 2198/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  15%|▏| 2198/14932 [03:11<18:29, 11.48it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -21086,8 +21057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2198/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  15%|▏| 2198/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  15%|▏| 2199/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  15%|▏| 2199/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -21095,8 +21066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2199/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  15%|▏| 2199/14932 [03:16<18:59, 11.18it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  15%|▏| 2200/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  15%|▏| 2200/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -21104,8 +21075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2200/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  15%|▏| 2200/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  15%|▏| 2201/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  15%|▏| 2201/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -21113,8 +21084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2201/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  15%|▏| 2201/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  15%|▏| 2202/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  15%|▏| 2202/14932 [03:11<18:28, 11.48it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -21122,8 +21093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2202/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  15%|▏| 2202/14932 [03:16<18:58, 11.18it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  15%|▏| 2203/14932 [03:11<18:28, 11.49it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  15%|▏| 2203/14932 [03:11<18:28, 11.49it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -21131,8 +21102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2203/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  15%|▏| 2203/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  15%|▏| 2204/14932 [03:11<18:28, 11.49it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  15%|▏| 2204/14932 [03:11<18:28, 11.49it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -21140,8 +21111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2204/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  15%|▏| 2204/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  15%|▏| 2205/14932 [03:11<18:27, 11.49it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  15%|▏| 2205/14932 [03:11<18:27, 11.49it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -21149,8 +21120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2205/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  15%|▏| 2205/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  15%|▏| 2206/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  15%|▏| 2206/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -21158,8 +21129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2206/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  15%|▏| 2206/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  15%|▏| 2207/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  15%|▏| 2207/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -21167,8 +21138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2207/14932 [03:17<18:57, 11.19it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  15%|▏| 2207/14932 [03:17<18:57, 11.19it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  15%|▏| 2208/14932 [03:12<18:28, 11.48it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  15%|▏| 2208/14932 [03:12<18:28, 11.48it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -21176,8 +21147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2208/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  15%|▏| 2208/14932 [03:17<18:58, 11.18it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  15%|▏| 2209/14932 [03:12<18:28, 11.48it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  15%|▏| 2209/14932 [03:12<18:28, 11.48it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -21185,8 +21156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2209/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  15%|▏| 2209/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  15%|▏| 2210/14932 [03:12<18:27, 11.48it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  15%|▏| 2210/14932 [03:12<18:27, 11.48it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -21194,8 +21165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2210/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  15%|▏| 2210/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  15%|▏| 2211/14932 [03:12<18:27, 11.48it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  15%|▏| 2211/14932 [03:12<18:27, 11.48it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -21203,8 +21174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2211/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  15%|▏| 2211/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  15%|▏| 2212/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  15%|▏| 2212/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -21212,8 +21183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2212/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  15%|▏| 2212/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  15%|▏| 2213/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  15%|▏| 2213/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -21221,8 +21192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2213/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  15%|▏| 2213/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  15%|▏| 2214/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  15%|▏| 2214/14932 [03:12<18:27, 11.49it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -21230,8 +21201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2214/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  15%|▏| 2214/14932 [03:17<18:57, 11.18it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  15%|▏| 2215/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  15%|▏| 2215/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -21239,8 +21210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2215/14932 [03:18<18:57, 11.18it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  15%|▏| 2215/14932 [03:18<18:57, 11.18it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  15%|▏| 2216/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  15%|▏| 2216/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -21248,8 +21219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2216/14932 [03:18<18:56, 11.18it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  15%|▏| 2216/14932 [03:18<18:56, 11.18it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  15%|▏| 2217/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  15%|▏| 2217/14932 [03:12<18:26, 11.49it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -21257,8 +21228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2217/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  15%|▏| 2217/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  15%|▏| 2218/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  15%|▏| 2218/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -21266,8 +21237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2218/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  15%|▏| 2218/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  15%|▏| 2219/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  15%|▏| 2219/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -21275,8 +21246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2219/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  15%|▏| 2219/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  15%|▏| 2220/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  15%|▏| 2220/14932 [03:13<18:26, 11.49it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -21284,8 +21255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2220/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  15%|▏| 2220/14932 [03:18<18:56, 11.19it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  15%|▏| 2221/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  15%|▏| 2221/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -21293,8 +21264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2221/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  15%|▏| 2221/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  15%|▏| 2222/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  15%|▏| 2222/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -21302,8 +21273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2222/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  15%|▏| 2222/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  15%|▏| 2223/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  15%|▏| 2223/14932 [03:13<18:25, 11.49it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -21311,8 +21282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2223/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  15%|▏| 2223/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  15%|▏| 2224/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  15%|▏| 2224/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -21320,8 +21291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2224/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  15%|▏| 2224/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  15%|▏| 2225/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  15%|▏| 2225/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -21329,8 +21300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2225/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  15%|▏| 2225/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  15%|▏| 2226/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  15%|▏| 2226/14932 [03:13<18:25, 11.50it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -21338,8 +21309,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2226/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  15%|▏| 2226/14932 [03:18<18:55, 11.19it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  15%|▏| 2227/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -21347,8 +21317,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2227/14932 [03:18<18:54, 11.19it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  15%|▏| 2227/14932 [03:18<18:54, 11.19it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  15%|▏| 2227/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -21356,8 +21325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2228/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  15%|▏| 2228/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  15%|▏| 2228/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  15%|▏| 2228/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -21365,8 +21334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2229/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  15%|▏| 2229/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  15%|▏| 2229/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  15%|▏| 2229/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -21374,8 +21343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2230/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  15%|▏| 2230/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  15%|▏| 2230/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  15%|▏| 2230/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -21383,8 +21352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2231/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  15%|▏| 2231/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  15%|▏| 2231/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  15%|▏| 2231/14932 [03:13<18:24, 11.50it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -21392,8 +21361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2232/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  15%|▏| 2232/14932 [03:19<18:54, 11.20it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  15%|▏| 2232/14932 [03:14<18:24, 11.50it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  15%|▏| 2232/14932 [03:14<18:24, 11.50it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -21401,8 +21370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2233/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  15%|▏| 2233/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  15%|▏| 2233/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  15%|▏| 2233/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -21410,8 +21379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2234/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  15%|▏| 2234/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  15%|▏| 2234/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  15%|▏| 2234/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -21419,8 +21388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2235/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  15%|▏| 2235/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  15%|▏| 2235/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  15%|▏| 2235/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -21428,8 +21397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2236/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  15%|▏| 2236/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  15%|▏| 2236/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  15%|▏| 2236/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -21437,8 +21406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2237/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  15%|▏| 2237/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  15%|▏| 2237/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  15%|▏| 2237/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -21446,8 +21415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2238/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  15%|▏| 2238/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  15%|▏| 2238/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  15%|▏| 2238/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -21455,8 +21424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2239/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  15%|▏| 2239/14932 [03:19<18:53, 11.20it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  15%|▏| 2239/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  15%|▏| 2239/14932 [03:14<18:23, 11.51it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -21464,8 +21433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2240/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  15%|▏| 2240/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  15%|▏| 2240/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  15%|▏| 2240/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -21473,8 +21442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2241/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  15%|▏| 2241/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  15%|▏| 2241/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  15%|▏| 2241/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -21482,8 +21451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2242/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  15%|▏| 2242/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  15%|▏| 2242/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  15%|▏| 2242/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -21491,8 +21460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2243/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  15%|▏| 2243/14932 [03:20<18:53, 11.20it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  15%|▏| 2243/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  15%|▏| 2243/14932 [03:14<18:23, 11.50it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -21500,8 +21469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2244/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  15%|▏| 2244/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  15%|▏| 2244/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  15%|▏| 2244/14932 [03:15<18:22, 11.50it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -21509,8 +21478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2245/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  15%|▏| 2245/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  15%|▏| 2245/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  15%|▏| 2245/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -21518,8 +21487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2246/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  15%|▏| 2246/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  15%|▏| 2246/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  15%|▏| 2246/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -21527,8 +21496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2247/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  15%|▏| 2247/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  15%|▏| 2247/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  15%|▏| 2247/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -21536,8 +21505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2248/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  15%|▏| 2248/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  15%|▏| 2248/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  15%|▏| 2248/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -21545,8 +21514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2249/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  15%|▏| 2249/14932 [03:20<18:52, 11.20it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  15%|▏| 2249/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  15%|▏| 2249/14932 [03:15<18:22, 11.51it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -21554,8 +21523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2250/14932 [03:20<18:51, 11.20it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  15%|▏| 2250/14932 [03:20<18:51, 11.20it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  15%|▏| 2250/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  15%|▏| 2250/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -21563,8 +21532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2251/14932 [03:20<18:51, 11.21it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  15%|▏| 2251/14932 [03:20<18:51, 11.21it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  15%|▏| 2251/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  15%|▏| 2251/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -21572,8 +21541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2252/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  15%|▏| 2252/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  15%|▏| 2252/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  15%|▏| 2252/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -21581,8 +21550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2253/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  15%|▏| 2253/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  15%|▏| 2253/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  15%|▏| 2253/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -21590,8 +21559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2254/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  15%|▏| 2254/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  15%|▏| 2254/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  15%|▏| 2254/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -21599,8 +21568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2255/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  15%|▏| 2255/14932 [03:21<18:51, 11.20it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  15%|▏| 2255/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  15%|▏| 2255/14932 [03:15<18:21, 11.51it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -21608,8 +21577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2256/14932 [03:21<18:51, 11.21it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  15%|▏| 2256/14932 [03:21<18:51, 11.21it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  15%|▏| 2256/14932 [03:15<18:20, 11.51it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  15%|▏| 2256/14932 [03:15<18:20, 11.51it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -21617,8 +21586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2257/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  15%|▏| 2257/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  15%|▏| 2257/14932 [03:16<18:20, 11.51it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  15%|▏| 2257/14932 [03:16<18:20, 11.51it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -21626,8 +21595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2258/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  15%|▏| 2258/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  15%|▏| 2258/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  15%|▏| 2258/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -21635,8 +21604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2259/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  15%|▏| 2259/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  15%|▏| 2259/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  15%|▏| 2259/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -21644,8 +21613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2260/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  15%|▏| 2260/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  15%|▏| 2260/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  15%|▏| 2260/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -21653,8 +21622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2261/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  15%|▏| 2261/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  15%|▏| 2261/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  15%|▏| 2261/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -21662,8 +21631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2262/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  15%|▏| 2262/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  15%|▏| 2262/14932 [03:16<18:20, 11.51it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  15%|▏| 2262/14932 [03:16<18:20, 11.51it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -21671,8 +21640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2263/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  15%|▏| 2263/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  15%|▏| 2263/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  15%|▏| 2263/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -21680,8 +21649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2264/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  15%|▏| 2264/14932 [03:21<18:50, 11.21it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  15%|▏| 2264/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  15%|▏| 2264/14932 [03:16<18:20, 11.52it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -21689,8 +21658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2265/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  15%|▏| 2265/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  15%|▏| 2265/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  15%|▏| 2265/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -21698,8 +21667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2266/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  15%|▏| 2266/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  15%|▏| 2266/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  15%|▏| 2266/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -21707,8 +21676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2267/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  15%|▏| 2267/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  15%|▏| 2267/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  15%|▏| 2267/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -21716,8 +21685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2268/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  15%|▏| 2268/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  15%|▏| 2268/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  15%|▏| 2268/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -21725,8 +21694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2269/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  15%|▏| 2269/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  15%|▏| 2269/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  15%|▏| 2269/14932 [03:16<18:19, 11.52it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -21734,8 +21703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2270/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  15%|▏| 2270/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  15%|▏| 2270/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  15%|▏| 2270/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -21743,8 +21712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2271/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  15%|▏| 2271/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  15%|▏| 2271/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  15%|▏| 2271/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -21752,8 +21721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2272/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  15%|▏| 2272/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  15%|▏| 2272/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  15%|▏| 2272/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -21761,8 +21730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2273/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  15%|▏| 2273/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  15%|▏| 2273/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  15%|▏| 2273/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -21770,8 +21739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2274/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  15%|▏| 2274/14932 [03:22<18:49, 11.21it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  15%|▏| 2274/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  15%|▏| 2274/14932 [03:17<18:19, 11.52it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -21779,8 +21748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2275/14932 [03:22<18:48, 11.21it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  15%|▏| 2275/14932 [03:22<18:48, 11.21it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  15%|▏| 2275/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  15%|▏| 2275/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -21788,8 +21757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2276/14932 [03:22<18:48, 11.21it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  15%|▏| 2276/14932 [03:22<18:48, 11.21it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  15%|▏| 2276/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  15%|▏| 2276/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -21797,8 +21766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2277/14932 [03:23<18:48, 11.21it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  15%|▏| 2277/14932 [03:23<18:48, 11.21it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  15%|▏| 2277/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  15%|▏| 2277/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -21806,8 +21775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2278/14932 [03:23<18:48, 11.21it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  15%|▏| 2278/14932 [03:23<18:48, 11.21it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  15%|▏| 2278/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  15%|▏| 2278/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -21815,8 +21784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2279/14932 [03:23<18:48, 11.22it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  15%|▏| 2279/14932 [03:23<18:48, 11.22it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  15%|▏| 2279/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  15%|▏| 2279/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -21824,8 +21793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2280/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  15%|▏| 2280/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  15%|▏| 2280/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  15%|▏| 2280/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.01"
      ]
     },
     {
@@ -21833,8 +21802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2281/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  15%|▏| 2281/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  15%|▏| 2281/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=1.01\r",
+      "Epoch 0:  15%|▏| 2281/14932 [03:17<18:18, 11.52it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -21842,8 +21811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2282/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  15%|▏| 2282/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  15%|▏| 2282/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  15%|▏| 2282/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -21851,8 +21820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2283/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  15%|▏| 2283/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  15%|▏| 2283/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  15%|▏| 2283/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -21860,8 +21829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2284/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  15%|▏| 2284/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  15%|▏| 2284/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  15%|▏| 2284/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -21869,7 +21838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2285/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  15%|▏| 2285/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  15%|▏| 2285/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -21877,7 +21847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2285/14932 [03:23<18:47, 11.22it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  15%|▏| 2286/14932 [03:18<18:17, 11.53it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  15%|▏| 2286/14932 [03:18<18:17, 11.52it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -21885,8 +21856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2286/14932 [03:23<18:46, 11.22it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  15%|▏| 2286/14932 [03:23<18:46, 11.22it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  15%|▏| 2287/14932 [03:18<18:17, 11.53it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  15%|▏| 2287/14932 [03:18<18:17, 11.53it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -21894,8 +21865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2287/14932 [03:23<18:46, 11.22it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  15%|▏| 2287/14932 [03:23<18:46, 11.22it/s, v_num=o30c, train/loss=0.82"
+      "Epoch 0:  15%|▏| 2288/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  15%|▏| 2288/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -21903,8 +21874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2288/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=0.82\r",
-      "Epoch 0:  15%|▏| 2288/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  15%|▏| 2289/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  15%|▏| 2289/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -21912,8 +21883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2289/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  15%|▏| 2289/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  15%|▏| 2290/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  15%|▏| 2290/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -21921,8 +21892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2290/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  15%|▏| 2290/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  15%|▏| 2291/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  15%|▏| 2291/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -21930,8 +21901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2291/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  15%|▏| 2291/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  15%|▏| 2292/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  15%|▏| 2292/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -21939,8 +21910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2292/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  15%|▏| 2292/14932 [03:24<18:47, 11.21it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  15%|▏| 2293/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  15%|▏| 2293/14932 [03:18<18:16, 11.53it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -21948,8 +21919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2293/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  15%|▏| 2293/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  15%|▏| 2294/14932 [03:18<18:15, 11.53it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  15%|▏| 2294/14932 [03:18<18:15, 11.53it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -21957,8 +21928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2294/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  15%|▏| 2294/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  15%|▏| 2295/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  15%|▏| 2295/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -21966,8 +21937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2295/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  15%|▏| 2295/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  15%|▏| 2296/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  15%|▏| 2296/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -21975,8 +21946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2296/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  15%|▏| 2296/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  15%|▏| 2297/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  15%|▏| 2297/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -21984,8 +21955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2297/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  15%|▏| 2297/14932 [03:24<18:46, 11.22it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  15%|▏| 2298/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  15%|▏| 2298/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -21993,8 +21964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2298/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  15%|▏| 2298/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  15%|▏| 2299/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  15%|▏| 2299/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -22002,8 +21973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2299/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  15%|▏| 2299/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  15%|▏| 2300/14932 [03:19<18:15, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  15%|▏| 2300/14932 [03:19<18:15, 11.54it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -22011,8 +21982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2300/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  15%|▏| 2300/14932 [03:24<18:45, 11.22it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  15%|▏| 2301/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  15%|▏| 2301/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -22020,8 +21991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2301/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  15%|▏| 2301/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  15%|▏| 2302/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  15%|▏| 2302/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -22029,8 +22000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2302/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  15%|▏| 2302/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  15%|▏| 2303/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  15%|▏| 2303/14932 [03:19<18:14, 11.54it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -22038,8 +22009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2303/14932 [03:25<18:45, 11.23it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  15%|▏| 2303/14932 [03:25<18:45, 11.23it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  15%|▏| 2304/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  15%|▏| 2304/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -22047,8 +22018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2304/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  15%|▏| 2304/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  15%|▏| 2305/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  15%|▏| 2305/14932 [03:19<18:15, 11.53it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -22056,8 +22027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2305/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  15%|▏| 2305/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  15%|▏| 2306/14932 [03:20<18:15, 11.53it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  15%|▏| 2306/14932 [03:20<18:15, 11.53it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -22065,8 +22036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2306/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  15%|▏| 2306/14932 [03:25<18:45, 11.22it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  15%|▏| 2307/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  15%|▏| 2307/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -22074,8 +22045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2307/14932 [03:25<18:44, 11.22it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  15%|▏| 2307/14932 [03:25<18:44, 11.22it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  15%|▏| 2308/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  15%|▏| 2308/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -22083,8 +22054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2308/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  15%|▏| 2308/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  15%|▏| 2309/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  15%|▏| 2309/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -22092,8 +22063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|��| 2309/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  15%|▏| 2309/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  15%|▏| 2310/14932 [03:20<18:15, 11.52it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  15%|▏| 2310/14932 [03:20<18:15, 11.52it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -22101,8 +22072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2310/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  15%|▏| 2310/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  15%|▏| 2311/14932 [03:20<18:15, 11.53it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  15%|▏| 2311/14932 [03:20<18:15, 11.53it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -22110,8 +22081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2311/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  15%|▏| 2311/14932 [03:25<18:44, 11.23it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  15%|▏| 2312/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  15%|▏| 2312/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -22119,8 +22090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2312/14932 [03:25<18:43, 11.23it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  15%|▏| 2312/14932 [03:25<18:43, 11.23it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  15%|▏| 2313/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  15%|▏| 2313/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -22128,8 +22099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2313/14932 [03:25<18:43, 11.23it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  15%|▏| 2313/14932 [03:25<18:43, 11.23it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  15%|▏| 2314/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  15%|▏| 2314/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -22137,8 +22108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  15%|▏| 2314/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  15%|▏| 2314/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  16%|▏| 2315/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  16%|▏| 2315/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -22146,8 +22117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2315/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  16%|▏| 2315/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  16%|▏| 2316/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  16%|▏| 2316/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -22155,8 +22126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2316/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  16%|▏| 2316/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  16%|▏| 2317/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  16%|▏| 2317/14932 [03:20<18:14, 11.53it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -22164,8 +22135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2317/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  16%|▏| 2317/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  16%|▏| 2318/14932 [03:21<18:14, 11.53it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  16%|▏| 2318/14932 [03:21<18:14, 11.53it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -22173,8 +22144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2318/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  16%|▏| 2318/14932 [03:26<18:43, 11.23it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  16%|▏| 2319/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  16%|▏| 2319/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -22182,8 +22153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2319/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  16%|▏| 2319/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  16%|▏| 2320/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  16%|▏| 2320/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -22191,8 +22162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2320/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  16%|▏| 2320/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  16%|▏| 2321/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  16%|▏| 2321/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -22200,8 +22171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2321/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  16%|▏| 2321/14932 [03:26<18:42, 11.23it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  16%|▏| 2322/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  16%|▏| 2322/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -22209,8 +22180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2322/14932 [03:26<18:42, 11.24it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  16%|▏| 2322/14932 [03:26<18:42, 11.24it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  16%|▏| 2323/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  16%|▏| 2323/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -22218,8 +22189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2323/14932 [03:26<18:42, 11.24it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  16%|▏| 2323/14932 [03:26<18:42, 11.24it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  16%|▏| 2324/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  16%|▏| 2324/14932 [03:21<18:13, 11.53it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -22227,8 +22198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2324/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  16%|▏| 2324/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  16%|▏| 2325/14932 [03:21<18:12, 11.53it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  16%|▏| 2325/14932 [03:21<18:12, 11.53it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -22236,8 +22207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2325/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  16%|▏| 2325/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  16%|▏| 2326/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  16%|▏| 2326/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -22245,8 +22216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2326/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  16%|▏| 2326/14932 [03:26<18:41, 11.24it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  16%|▏| 2327/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  16%|▏| 2327/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -22254,8 +22225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2327/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  16%|▏| 2327/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  16%|▏| 2328/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  16%|▏| 2328/14932 [03:21<18:12, 11.54it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -22263,8 +22234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2328/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  16%|▏| 2328/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  16%|▏| 2329/14932 [03:21<18:12, 11.53it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  16%|▏| 2329/14932 [03:21<18:12, 11.53it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -22272,8 +22243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2329/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  16%|▏| 2329/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  16%|▏| 2330/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  16%|▏| 2330/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -22281,8 +22252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2330/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  16%|▏| 2330/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  16%|▏| 2331/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  16%|▏| 2331/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -22290,8 +22261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2331/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  16%|▏| 2331/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  16%|▏| 2332/14932 [03:22<18:12, 11.54it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  16%|▏| 2332/14932 [03:22<18:12, 11.54it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -22299,8 +22270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2332/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  16%|▏| 2332/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  16%|▏| 2333/14932 [03:22<18:12, 11.54it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  16%|▏| 2333/14932 [03:22<18:12, 11.54it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -22308,8 +22279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2333/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  16%|▏| 2333/14932 [03:27<18:41, 11.23it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  16%|▏| 2334/14932 [03:22<18:11, 11.54it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  16%|▏| 2334/14932 [03:22<18:11, 11.54it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -22317,8 +22288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2334/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  16%|▏| 2334/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  16%|▏| 2335/14932 [03:22<18:11, 11.54it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  16%|▏| 2335/14932 [03:22<18:11, 11.54it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -22326,8 +22297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2335/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  16%|▏| 2335/14932 [03:27<18:41, 11.24it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  16%|▏| 2336/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:  16%|▏| 2336/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -22335,8 +22306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2336/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  16%|▏| 2336/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  16%|▏| 2337/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  16%|▏| 2337/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -22344,8 +22315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2337/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  16%|▏| 2337/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  16%|▏| 2338/14932 [03:22<18:11, 11.53it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  16%|▏| 2338/14932 [03:22<18:11, 11.53it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -22353,8 +22324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2338/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  16%|▏| 2338/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  16%|▏| 2339/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  16%|▏| 2339/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -22362,8 +22333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2339/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  16%|▏| 2339/14932 [03:28<18:41, 11.23it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  16%|▏| 2340/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  16%|▏| 2340/14932 [03:22<18:12, 11.53it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -22371,8 +22342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2340/14932 [03:28<18:40, 11.23it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  16%|▏| 2340/14932 [03:28<18:40, 11.23it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  16%|▏| 2341/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  16%|▏| 2341/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -22380,8 +22351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2341/14932 [03:28<18:40, 11.23it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  16%|▏| 2341/14932 [03:28<18:40, 11.23it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  16%|▏| 2342/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  16%|▏| 2342/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -22389,8 +22360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2342/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  16%|▏| 2342/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  16%|▏| 2343/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  16%|▏| 2343/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=0.99"
      ]
     },
     {
@@ -22398,8 +22369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2343/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  16%|▏| 2343/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  16%|▏| 2344/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=0.99\r",
+      "Epoch 0:  16%|▏| 2344/14932 [03:23<18:12, 11.53it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -22407,8 +22378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2344/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  16%|▏| 2344/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  16%|▏| 2345/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  16%|▏| 2345/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -22416,8 +22387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2345/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  16%|▏| 2345/14932 [03:28<18:40, 11.24it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  16%|▏| 2346/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  16%|▏| 2346/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -22425,8 +22396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2346/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  16%|▏| 2346/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  16%|▏| 2347/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  16%|▏| 2347/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -22434,8 +22405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2347/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  16%|▏| 2347/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  16%|▏| 2348/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  16%|▏| 2348/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -22443,8 +22414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2348/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  16%|▏| 2348/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  16%|▏| 2349/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  16%|▏| 2349/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -22452,8 +22423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2349/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  16%|▏| 2349/14932 [03:28<18:39, 11.24it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  16%|▏| 2350/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  16%|▏| 2350/14932 [03:23<18:11, 11.53it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -22461,8 +22432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2350/14932 [03:29<18:39, 11.24it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  16%|▏| 2350/14932 [03:29<18:39, 11.24it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  16%|▏| 2351/14932 [03:23<18:10, 11.53it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  16%|▏| 2351/14932 [03:23<18:10, 11.53it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -22470,8 +22441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2351/14932 [03:29<18:39, 11.24it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  16%|▏| 2351/14932 [03:29<18:39, 11.24it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  16%|▏| 2352/14932 [03:23<18:10, 11.53it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  16%|▏| 2352/14932 [03:23<18:10, 11.53it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -22479,8 +22450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2352/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  16%|▏| 2352/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  16%|▏| 2353/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  16%|▏| 2353/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -22488,8 +22459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2353/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  16%|▏| 2353/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  16%|▏| 2354/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  16%|▏| 2354/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -22497,8 +22468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2354/14932 [03:29<18:38, 11.25it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  16%|▏| 2354/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  16%|▏| 2355/14932 [03:24<18:10, 11.54it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  16%|▏| 2355/14932 [03:24<18:10, 11.54it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -22506,8 +22477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2355/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  16%|▏| 2355/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  16%|▏| 2356/14932 [03:24<18:10, 11.54it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  16%|▏| 2356/14932 [03:24<18:10, 11.54it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -22515,8 +22486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2356/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  16%|▏| 2356/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  16%|▏| 2357/14932 [03:24<18:09, 11.54it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  16%|▏| 2357/14932 [03:24<18:09, 11.54it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -22524,8 +22495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2357/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  16%|▏| 2357/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  16%|▏| 2358/14932 [03:24<18:09, 11.54it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  16%|▏| 2358/14932 [03:24<18:09, 11.54it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -22533,8 +22504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2358/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  16%|▏| 2358/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  16%|▏| 2359/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  16%|▏| 2359/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -22542,8 +22513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2359/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  16%|▏| 2359/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  16%|▏| 2360/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  16%|▏| 2360/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -22551,8 +22522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2360/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  16%|▏| 2360/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  16%|▏| 2361/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  16%|▏| 2361/14932 [03:24<18:10, 11.53it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -22560,8 +22531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2361/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  16%|▏| 2361/14932 [03:29<18:38, 11.24it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  16%|▏| 2362/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  16%|▏| 2362/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -22569,8 +22540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2362/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  16%|▏| 2362/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  16%|▏| 2363/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  16%|▏| 2363/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -22578,8 +22549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2363/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  16%|▏| 2363/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  16%|▏| 2364/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  16%|▏| 2364/14932 [03:24<18:09, 11.53it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -22587,8 +22558,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2364/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  16%|▏| 2364/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  16%|▏| 2365/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -22596,8 +22566,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2365/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  16%|▏| 2365/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  16%|▏| 2365/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -22605,8 +22574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2366/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  16%|▏| 2366/14932 [03:30<18:37, 11.25it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  16%|▏| 2366/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  16%|▏| 2366/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -22614,8 +22583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2367/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  16%|▏| 2367/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  16%|▏| 2367/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  16%|▏| 2367/14932 [03:25<18:09, 11.54it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -22623,8 +22592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2368/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  16%|▏| 2368/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  16%|▏| 2368/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  16%|▏| 2368/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -22632,8 +22601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2369/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  16%|▏| 2369/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  16%|▏| 2369/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  16%|▏| 2369/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -22641,8 +22610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2370/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  16%|▏| 2370/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  16%|▏| 2370/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  16%|▏| 2370/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -22650,8 +22619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2371/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  16%|▏| 2371/14932 [03:30<18:37, 11.24it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  16%|▏| 2371/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  16%|▏| 2371/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -22659,8 +22628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2372/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  16%|▏| 2372/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  16%|▏| 2372/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  16%|▏| 2372/14932 [03:25<18:09, 11.53it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -22668,8 +22637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2373/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  16%|▏| 2373/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  16%|▏| 2373/14932 [03:25<18:08, 11.53it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  16%|▏| 2373/14932 [03:25<18:08, 11.53it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -22677,8 +22646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2374/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  16%|▏| 2374/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  16%|▏| 2374/14932 [03:25<18:08, 11.53it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  16%|▏| 2374/14932 [03:25<18:08, 11.53it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -22686,8 +22655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2375/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  16%|▏| 2375/14932 [03:31<18:37, 11.24it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  16%|▏| 2375/14932 [03:25<18:08, 11.54it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  16%|▏| 2375/14932 [03:25<18:08, 11.54it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -22695,8 +22664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2376/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  16%|▏| 2376/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  16%|▏| 2376/14932 [03:25<18:08, 11.54it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  16%|▏| 2376/14932 [03:25<18:08, 11.54it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -22704,8 +22673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2377/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  16%|▏| 2377/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  16%|▏| 2377/14932 [03:26<18:08, 11.54it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  16%|▏| 2377/14932 [03:26<18:08, 11.54it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -22713,8 +22682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2378/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  16%|▏| 2378/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  16%|▏| 2378/14932 [03:26<18:08, 11.54it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  16%|▏| 2378/14932 [03:26<18:08, 11.54it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -22722,8 +22691,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2379/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  16%|▏| 2379/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  16%|▏| 2379/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -22731,8 +22699,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2380/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  16%|▏| 2380/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  16%|▏| 2379/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -22740,8 +22707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2381/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  16%|▏| 2381/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  16%|▏| 2380/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  16%|▏| 2380/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -22749,8 +22716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2382/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  16%|▏| 2382/14932 [03:31<18:36, 11.24it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  16%|▏| 2381/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  16%|▏| 2381/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -22758,8 +22725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2383/14932 [03:31<18:35, 11.25it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  16%|▏| 2383/14932 [03:31<18:35, 11.25it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  16%|▏| 2382/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  16%|▏| 2382/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -22767,8 +22734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2384/14932 [03:31<18:35, 11.25it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  16%|▏| 2384/14932 [03:31<18:35, 11.25it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  16%|▏| 2383/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  16%|▏| 2383/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -22776,8 +22743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2385/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  16%|▏| 2385/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  16%|▏| 2384/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  16%|▏| 2384/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -22785,8 +22752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2386/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  16%|▏| 2386/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  16%|▏| 2385/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  16%|▏| 2385/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -22794,8 +22761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2387/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  16%|▏| 2387/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  16%|▏| 2386/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  16%|▏| 2386/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -22803,8 +22770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2388/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  16%|▏| 2388/14932 [03:32<18:35, 11.25it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  16%|▏| 2387/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  16%|▏| 2387/14932 [03:26<18:07, 11.54it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -22812,8 +22779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2389/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  16%|▏| 2389/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  16%|▏| 2388/14932 [03:26<18:06, 11.54it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  16%|▏| 2388/14932 [03:26<18:06, 11.54it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -22821,8 +22788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2390/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  16%|▏| 2390/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  16%|▏| 2389/14932 [03:26<18:06, 11.54it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  16%|▏| 2389/14932 [03:26<18:06, 11.54it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -22830,8 +22797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2391/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  16%|▏| 2391/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  16%|▏| 2390/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  16%|▏| 2390/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -22839,8 +22806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2392/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  16%|▏| 2392/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  16%|▏| 2391/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  16%|▏| 2391/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -22848,8 +22815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2393/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  16%|▏| 2393/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  16%|▏| 2392/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  16%|▏| 2392/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -22857,8 +22824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2394/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  16%|▏| 2394/14932 [03:32<18:34, 11.25it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  16%|▏| 2393/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  16%|▏| 2393/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -22866,8 +22833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2395/14932 [03:32<18:33, 11.25it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  16%|▏| 2395/14932 [03:32<18:33, 11.25it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  16%|▏| 2394/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  16%|▏| 2394/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -22875,8 +22842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2396/14932 [03:32<18:33, 11.26it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  16%|▏| 2396/14932 [03:32<18:33, 11.26it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  16%|▏| 2395/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  16%|▏| 2395/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -22884,8 +22851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2397/14932 [03:32<18:33, 11.26it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  16%|▏| 2397/14932 [03:32<18:33, 11.26it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  16%|▏| 2396/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  16%|▏| 2396/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -22893,8 +22860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2398/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  16%|▏| 2398/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  16%|▏| 2397/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  16%|▏| 2397/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -22902,8 +22869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2399/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  16%|▏| 2399/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  16%|▏| 2398/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  16%|▏| 2398/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -22911,8 +22878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2400/14932 [03:33<18:34, 11.24it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  16%|▏| 2400/14932 [03:33<18:34, 11.24it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  16%|▏| 2399/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  16%|▏| 2399/14932 [03:27<18:05, 11.54it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -22920,8 +22887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2401/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  16%|▏| 2401/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  16%|▏| 2400/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  16%|▏| 2400/14932 [03:27<18:06, 11.54it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -22929,8 +22896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2402/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  16%|▏| 2402/14932 [03:33<18:34, 11.25it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  16%|▏| 2401/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  16%|▏| 2401/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -22938,8 +22905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2403/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  16%|▏| 2403/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  16%|▏| 2402/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  16%|▏| 2402/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -22947,8 +22914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2404/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  16%|▏| 2404/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  16%|▏| 2403/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  16%|▏| 2403/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -22956,8 +22923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2405/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  16%|▏| 2405/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  16%|▏| 2404/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  16%|▏| 2404/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -22965,8 +22932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2406/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  16%|▏| 2406/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  16%|▏| 2405/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  16%|▏| 2405/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -22974,8 +22941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2407/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  16%|▏| 2407/14932 [03:33<18:33, 11.25it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  16%|▏| 2406/14932 [03:28<18:05, 11.53it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  16%|▏| 2406/14932 [03:28<18:05, 11.53it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -22983,8 +22950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2408/14932 [03:34<18:33, 11.25it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  16%|▏| 2408/14932 [03:34<18:33, 11.25it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  16%|▏| 2407/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  16%|▏| 2407/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -22992,8 +22959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2409/14932 [03:34<18:33, 11.25it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  16%|▏| 2409/14932 [03:34<18:33, 11.25it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  16%|▏| 2408/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  16%|▏| 2408/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -23001,8 +22968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2410/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  16%|▏| 2410/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  16%|▏| 2409/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  16%|▏| 2409/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=5.25"
      ]
     },
     {
@@ -23010,8 +22977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2411/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  16%|▏| 2411/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  16%|▏| 2410/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=5.25\r",
+      "Epoch 0:  16%|▏| 2410/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -23019,8 +22986,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2412/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  16%|▏| 2412/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  16%|▏| 2411/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -23028,8 +22994,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2413/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  16%|▏| 2413/14932 [03:34<18:32, 11.25it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  16%|▏| 2411/14932 [03:28<18:05, 11.54it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -23037,8 +23002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2414/14932 [03:34<18:32, 11.26it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  16%|▏| 2414/14932 [03:34<18:32, 11.26it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  16%|▏| 2412/14932 [03:29<18:05, 11.54it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  16%|▏| 2412/14932 [03:29<18:05, 11.54it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -23046,8 +23011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2415/14932 [03:34<18:32, 11.26it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  16%|▏| 2415/14932 [03:34<18:32, 11.26it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  16%|▏| 2413/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  16%|▏| 2413/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -23055,8 +23020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2416/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  16%|▏| 2416/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  16%|▏| 2414/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  16%|▏| 2414/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -23064,8 +23029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2417/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  16%|▏| 2417/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  16%|▏| 2415/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  16%|▏| 2415/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -23073,8 +23038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2418/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  16%|▏| 2418/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  16%|▏| 2416/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  16%|▏| 2416/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -23082,8 +23047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2419/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  16%|▏| 2419/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  16%|▏| 2417/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  16%|▏| 2417/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -23091,8 +23056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2420/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  16%|▏| 2420/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  16%|▏| 2418/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  16%|▏| 2418/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -23100,8 +23065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2421/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  16%|▏| 2421/14932 [03:34<18:31, 11.26it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:  16%|▏| 2419/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  16%|▏| 2419/14932 [03:29<18:04, 11.54it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -23109,8 +23074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2422/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:  16%|▏| 2422/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  16%|▏| 2420/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  16%|▏| 2420/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -23118,8 +23083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2423/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  16%|▏| 2423/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  16%|▏| 2421/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  16%|▏| 2421/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=1.49"
      ]
     },
     {
@@ -23127,8 +23092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2424/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  16%|▏| 2424/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  16%|▏| 2422/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=1.49\r",
+      "Epoch 0:  16%|▏| 2422/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=5.19"
      ]
     },
     {
@@ -23136,8 +23101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2425/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  16%|▏| 2425/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  16%|▏| 2423/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=5.19\r",
+      "Epoch 0:  16%|▏| 2423/14932 [03:29<18:03, 11.54it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -23145,8 +23110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2426/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  16%|▏| 2426/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  16%|▏| 2424/14932 [03:29<18:03, 11.55it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  16%|▏| 2424/14932 [03:29<18:03, 11.55it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -23154,8 +23119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2427/14932 [03:35<18:31, 11.26it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  16%|▏| 2427/14932 [03:35<18:31, 11.26it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  16%|▏| 2425/14932 [03:30<18:03, 11.55it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  16%|▏| 2425/14932 [03:30<18:03, 11.55it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -23163,8 +23128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2428/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  16%|▏| 2428/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  16%|▏| 2426/14932 [03:30<18:03, 11.55it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  16%|▏| 2426/14932 [03:30<18:03, 11.55it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -23172,8 +23137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2429/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  16%|▏| 2429/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  16%|▏| 2427/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  16%|▏| 2427/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -23181,8 +23146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2430/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  16%|▏| 2430/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=5.16"
+      "Epoch 0:  16%|▏| 2428/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  16%|▏| 2428/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -23190,8 +23155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2431/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=5.16\r",
-      "Epoch 0:  16%|▏| 2431/14932 [03:35<18:30, 11.26it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  16%|▏| 2429/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  16%|▏| 2429/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -23199,8 +23164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2432/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  16%|▏| 2432/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  16%|▏| 2430/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  16%|▏| 2430/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -23208,8 +23173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2433/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  16%|▏| 2433/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  16%|▏| 2431/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  16%|▏| 2431/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -23217,8 +23182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2434/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  16%|▏| 2434/14932 [03:36<18:30, 11.25it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  16%|▏| 2432/14932 [03:30<18:02, 11.54it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  16%|▏| 2432/14932 [03:30<18:02, 11.54it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -23226,8 +23191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2435/14932 [03:36<18:30, 11.26it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  16%|▏| 2435/14932 [03:36<18:30, 11.26it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  16%|▏| 2433/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  16%|▏| 2433/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -23235,8 +23200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2436/14932 [03:36<18:30, 11.26it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  16%|▏| 2436/14932 [03:36<18:30, 11.26it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  16%|▏| 2434/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  16%|▏| 2434/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -23244,8 +23209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2437/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  16%|▏| 2437/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  16%|▏| 2435/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  16%|▏| 2435/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -23253,8 +23218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2438/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  16%|▏| 2438/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  16%|▏| 2436/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  16%|▏| 2436/14932 [03:30<18:02, 11.55it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -23262,8 +23227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2439/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  16%|▏| 2439/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  16%|▏| 2437/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  16%|▏| 2437/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -23271,8 +23236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2440/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  16%|▏| 2440/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  16%|▏| 2438/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  16%|▏| 2438/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -23280,8 +23245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2441/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  16%|▏| 2441/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  16%|▏| 2439/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  16%|▏| 2439/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -23289,8 +23254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2442/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  16%|▏| 2442/14932 [03:36<18:29, 11.26it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  16%|▏| 2440/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  16%|▏| 2440/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -23298,7 +23263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2443/14932 [03:36<18:28, 11.26it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  16%|▏| 2441/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  16%|▏| 2441/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -23306,7 +23272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2443/14932 [03:36<18:28, 11.26it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  16%|▏| 2442/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  16%|▏| 2442/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -23314,8 +23281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2444/14932 [03:36<18:28, 11.26it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  16%|▏| 2444/14932 [03:36<18:28, 11.26it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  16%|▏| 2443/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  16%|▏| 2443/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -23323,8 +23290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2445/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  16%|▏| 2445/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  16%|▏| 2444/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  16%|▏| 2444/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -23332,8 +23299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2446/14932 [03:37<18:29, 11.26it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  16%|▏| 2446/14932 [03:37<18:29, 11.26it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  16%|▏| 2445/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  16%|▏| 2445/14932 [03:31<18:01, 11.55it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -23341,8 +23308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2447/14932 [03:37<18:29, 11.26it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  16%|▏| 2447/14932 [03:37<18:29, 11.26it/s, v_num=o30c, train/loss=1.99"
+      "Epoch 0:  16%|▏| 2446/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  16%|▏| 2446/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -23350,8 +23317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2448/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=1.99\r",
-      "Epoch 0:  16%|▏| 2448/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  16%|▏| 2447/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  16%|▏| 2447/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -23359,8 +23326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2449/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  16%|▏| 2449/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  16%|▏| 2448/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  16%|▏| 2448/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -23368,8 +23335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2450/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  16%|▏| 2450/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  16%|▏| 2449/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  16%|▏| 2449/14932 [03:31<18:00, 11.55it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -23377,8 +23344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2451/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  16%|▏| 2451/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  16%|▏| 2450/14932 [03:32<18:00, 11.55it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  16%|▏| 2450/14932 [03:32<18:00, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -23386,8 +23353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2452/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  16%|▏| 2452/14932 [03:37<18:28, 11.26it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  16%|▏| 2451/14932 [03:32<18:00, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  16%|▏| 2451/14932 [03:32<18:00, 11.55it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -23395,8 +23362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2453/14932 [03:38<18:29, 11.25it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  16%|▏| 2453/14932 [03:38<18:29, 11.25it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  16%|▏| 2452/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  16%|▏| 2452/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -23404,8 +23371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2454/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  16%|▏| 2454/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  16%|▏| 2453/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  16%|▏| 2453/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -23413,8 +23380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2455/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  16%|▏| 2455/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  16%|▏| 2454/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  16%|▏| 2454/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -23422,8 +23389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2456/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  16%|▏| 2456/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  16%|▏| 2455/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  16%|▏| 2455/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -23431,8 +23398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2457/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  16%|▏| 2457/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  16%|▏| 2456/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  16%|▏| 2456/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -23440,8 +23407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2458/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  16%|▏| 2458/14932 [03:38<18:28, 11.25it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  16%|▏| 2457/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  16%|▏| 2457/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -23449,8 +23416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2459/14932 [03:38<18:28, 11.26it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  16%|▏| 2459/14932 [03:38<18:28, 11.26it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  16%|▏| 2458/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  16%|▏| 2458/14932 [03:32<17:59, 11.56it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -23458,8 +23425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2460/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  16%|▏| 2460/14932 [03:38<18:28, 11.26it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  16%|▏| 2459/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  16%|▏| 2459/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -23467,8 +23434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2461/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  16%|▏| 2461/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  16%|▏| 2460/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  16%|▏| 2460/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -23476,8 +23443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2462/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  16%|▏| 2462/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  16%|▏| 2461/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  16%|▏| 2461/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -23485,8 +23452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  16%|▏| 2463/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  16%|▏| 2463/14932 [03:38<18:27, 11.26it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  16%|▏| 2462/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  16%|▏| 2462/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -23494,8 +23461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2464/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  17%|▏| 2464/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  16%|▏| 2463/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  16%|▏| 2463/14932 [03:32<17:58, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -23503,8 +23470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2465/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  17%|▏| 2465/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  17%|▏| 2464/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  17%|▏| 2464/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -23512,8 +23479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2466/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  17%|▏| 2466/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  17%|▏| 2465/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  17%|▏| 2465/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -23521,8 +23488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2467/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  17%|▏| 2467/14932 [03:39<18:28, 11.25it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  17%|▏| 2466/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  17%|▏| 2466/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -23530,8 +23497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2468/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  17%|▏| 2468/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  17%|▏| 2467/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  17%|▏| 2467/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -23539,8 +23506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2469/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  17%|▏| 2469/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  17%|▏| 2468/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  17%|▏| 2468/14932 [03:33<17:58, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -23548,8 +23515,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2470/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  17%|▏| 2470/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  17%|▏| 2469/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -23557,8 +23523,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2471/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  17%|▏| 2471/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  17%|▏| 2469/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -23566,8 +23531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2472/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  17%|▏| 2472/14932 [03:39<18:27, 11.25it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  17%|▏| 2470/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  17%|▏| 2470/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -23575,8 +23540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2473/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  17%|▏| 2473/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  17%|▏| 2471/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  17%|▏| 2471/14932 [03:33<17:57, 11.56it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -23584,8 +23549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2474/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  17%|▏| 2474/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  17%|▏| 2472/14932 [03:33<17:57, 11.57it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  17%|▏| 2472/14932 [03:33<17:57, 11.57it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -23593,8 +23558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2475/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  17%|▏| 2475/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  17%|▏| 2473/14932 [03:33<17:57, 11.57it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  17%|▏| 2473/14932 [03:33<17:57, 11.57it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -23602,8 +23567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2476/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  17%|▏| 2476/14932 [03:39<18:26, 11.26it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  17%|▏| 2474/14932 [03:33<17:56, 11.57it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  17%|▏| 2474/14932 [03:33<17:56, 11.57it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -23611,8 +23576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2477/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  17%|▏| 2477/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  17%|▏| 2475/14932 [03:34<17:57, 11.56it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  17%|▏| 2475/14932 [03:34<17:57, 11.56it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -23620,8 +23585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2478/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  17%|▏| 2478/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  17%|▏| 2476/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  17%|▏| 2476/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -23629,8 +23594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2479/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  17%|▏| 2479/14932 [03:40<18:26, 11.26it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  17%|▏| 2477/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  17%|▏| 2477/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -23638,8 +23603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2480/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  17%|▏| 2480/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  17%|▏| 2478/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  17%|▏| 2478/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -23647,8 +23612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2481/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  17%|▏| 2481/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  17%|▏| 2479/14932 [03:34<17:56, 11.56it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  17%|▏| 2479/14932 [03:34<17:56, 11.56it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -23656,8 +23621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2482/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  17%|▏| 2482/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  17%|▏| 2480/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  17%|▏| 2480/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -23665,8 +23630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2483/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  17%|▏| 2483/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  17%|▏| 2481/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  17%|▏| 2481/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -23674,8 +23639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2484/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  17%|▏| 2484/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  17%|▏| 2482/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  17%|▏| 2482/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -23683,8 +23648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2485/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  17%|▏| 2485/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=1.99"
+      "Epoch 0:  17%|▏| 2483/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  17%|▏| 2483/14932 [03:34<17:56, 11.57it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -23692,8 +23657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2486/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=1.99\r",
-      "Epoch 0:  17%|▏| 2486/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  17%|▏| 2484/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  17%|▏| 2484/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -23701,8 +23666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2487/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  17%|▏| 2487/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  17%|▏| 2485/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  17%|▏| 2485/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -23710,8 +23675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2488/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  17%|▏| 2488/14932 [03:40<18:25, 11.26it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  17%|▏| 2486/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  17%|▏| 2486/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -23719,8 +23684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2489/14932 [03:41<18:25, 11.26it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  17%|▏| 2489/14932 [03:41<18:25, 11.26it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  17%|▏| 2487/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  17%|▏| 2487/14932 [03:34<17:55, 11.57it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -23728,8 +23693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2490/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  17%|▏| 2490/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  17%|▏| 2488/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  17%|▏| 2488/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -23737,8 +23702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2491/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  17%|▏| 2491/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  17%|▏| 2489/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  17%|▏| 2489/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -23746,8 +23711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2492/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  17%|▏| 2492/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  17%|▏| 2490/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  17%|▏| 2490/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -23755,8 +23720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2493/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  17%|▏| 2493/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:  17%|▏| 2491/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  17%|▏| 2491/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -23764,8 +23729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2494/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:  17%|▏| 2494/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  17%|▏| 2492/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  17%|▏| 2492/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -23773,8 +23738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2495/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  17%|▏| 2495/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  17%|▏| 2493/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  17%|▏| 2493/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -23782,8 +23747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2496/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  17%|▏| 2496/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  17%|▏| 2494/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  17%|▏| 2494/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -23791,8 +23756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2497/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  17%|▏| 2497/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  17%|▏| 2495/14932 [03:35<17:54, 11.57it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  17%|▏| 2495/14932 [03:35<17:54, 11.57it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -23800,8 +23765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2498/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  17%|▏| 2498/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  17%|▏| 2496/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  17%|▏| 2496/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -23809,8 +23774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2499/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  17%|▏| 2499/14932 [03:41<18:24, 11.26it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  17%|▏| 2497/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  17%|▏| 2497/14932 [03:35<17:55, 11.57it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -23818,8 +23783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2500/14932 [03:41<18:23, 11.26it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  17%|▏| 2500/14932 [03:41<18:23, 11.26it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  17%|▏| 2498/14932 [03:36<17:55, 11.56it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  17%|▏| 2498/14932 [03:36<17:55, 11.56it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -23827,8 +23792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2501/14932 [03:42<18:24, 11.26it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  17%|▏| 2501/14932 [03:42<18:24, 11.26it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  17%|▏| 2499/14932 [03:36<17:55, 11.56it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  17%|▏| 2499/14932 [03:36<17:55, 11.56it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -23836,8 +23801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2502/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  17%|▏| 2502/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  17%|▏| 2500/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  17%|▏| 2500/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -23845,8 +23810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2503/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  17%|▏| 2503/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  17%|▏| 2501/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  17%|▏| 2501/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -23854,8 +23819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2504/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  17%|▏| 2504/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  17%|▏| 2502/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  17%|▏| 2502/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -23863,8 +23828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2505/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  17%|▏| 2505/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  17%|▏| 2503/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  17%|▏| 2503/14932 [03:36<17:54, 11.57it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -23872,8 +23837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2506/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  17%|▏| 2506/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  17%|▏| 2504/14932 [03:37<17:59, 11.51it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  17%|▏| 2504/14932 [03:37<17:59, 11.51it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -23881,8 +23846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2507/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  17%|▏| 2507/14932 [03:42<18:23, 11.26it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  17%|▏| 2505/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  17%|▏| 2505/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -23890,8 +23855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2508/14932 [03:42<18:22, 11.26it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  17%|▏| 2508/14932 [03:42<18:22, 11.26it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  17%|▏| 2506/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  17%|▏| 2506/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -23899,8 +23864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2509/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  17%|▏| 2509/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  17%|▏| 2507/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  17%|▏| 2507/14932 [03:37<18:00, 11.50it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -23908,8 +23873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2510/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  17%|▏| 2510/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  17%|▏| 2508/14932 [03:38<18:00, 11.50it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  17%|▏| 2508/14932 [03:38<18:00, 11.50it/s, v_num=ui8w, train/loss=1.60"
      ]
     },
     {
@@ -23917,8 +23882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2511/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  17%|▏| 2511/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  17%|▏| 2509/14932 [03:38<17:59, 11.50it/s, v_num=ui8w, train/loss=1.60\r",
+      "Epoch 0:  17%|▏| 2509/14932 [03:38<17:59, 11.50it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -23926,8 +23891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2512/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  17%|▏| 2512/14932 [03:42<18:22, 11.27it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  17%|▏| 2510/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  17%|▏| 2510/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -23935,8 +23900,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2513/14932 [03:43<18:22, 11.27it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  17%|▏| 2513/14932 [03:43<18:22, 11.27it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  17%|▏| 2511/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -23944,8 +23908,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2514/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  17%|▏| 2514/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  17%|▏| 2511/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -23953,8 +23916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2515/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  17%|▏| 2515/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  17%|▏| 2512/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  17%|▏| 2512/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -23962,8 +23925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2516/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  17%|▏| 2516/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  17%|▏| 2513/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  17%|▏| 2513/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -23971,8 +23934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2517/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  17%|▏| 2517/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  17%|▏| 2514/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  17%|▏| 2514/14932 [03:38<17:59, 11.51it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -23980,8 +23943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2518/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  17%|▏| 2518/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  17%|▏| 2515/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  17%|▏| 2515/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -23989,8 +23952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2519/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  17%|▏| 2519/14932 [03:43<18:21, 11.27it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  17%|▏| 2516/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  17%|▏| 2516/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -23998,8 +23961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2520/14932 [03:43<18:20, 11.27it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  17%|▏| 2520/14932 [03:43<18:20, 11.27it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  17%|▏| 2517/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  17%|▏| 2517/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -24007,8 +23970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2521/14932 [03:43<18:20, 11.27it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  17%|▏| 2521/14932 [03:43<18:20, 11.27it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  17%|▏| 2518/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  17%|▏| 2518/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -24016,8 +23979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2522/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  17%|▏| 2522/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  17%|▏| 2519/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  17%|▏| 2519/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -24025,8 +23988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2523/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  17%|▏| 2523/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  17%|▏| 2520/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  17%|▏| 2520/14932 [03:38<17:58, 11.51it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -24034,8 +23997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2524/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  17%|▏| 2524/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  17%|▏| 2521/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  17%|▏| 2521/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -24043,8 +24006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2525/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  17%|▏| 2525/14932 [03:43<18:20, 11.28it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  17%|▏| 2522/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  17%|▏| 2522/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -24052,8 +24015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2526/14932 [03:43<18:19, 11.28it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  17%|▏| 2526/14932 [03:43<18:19, 11.28it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  17%|▏| 2523/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  17%|▏| 2523/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -24061,8 +24024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2527/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  17%|▏| 2527/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  17%|▏| 2524/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  17%|▏| 2524/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -24070,8 +24033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2528/14932 [03:44<18:20, 11.27it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  17%|▏| 2528/14932 [03:44<18:20, 11.27it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  17%|▏| 2525/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  17%|▏| 2525/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -24079,8 +24042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2529/14932 [03:44<18:20, 11.27it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  17%|▏| 2529/14932 [03:44<18:20, 11.27it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  17%|▏| 2526/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  17%|▏| 2526/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -24088,8 +24051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2530/14932 [03:44<18:19, 11.27it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  17%|▏| 2530/14932 [03:44<18:19, 11.27it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  17%|▏| 2527/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  17%|▏| 2527/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -24097,8 +24060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2531/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  17%|▏| 2531/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  17%|▏| 2528/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  17%|▏| 2528/14932 [03:39<17:58, 11.51it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -24106,8 +24069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2532/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  17%|▏| 2532/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  17%|▏| 2529/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  17%|▏| 2529/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -24115,8 +24078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2533/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  17%|▏| 2533/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  17%|▏| 2530/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  17%|▏| 2530/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -24124,8 +24087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2534/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  17%|▏| 2534/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  17%|▏| 2531/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  17%|▏| 2531/14932 [03:39<17:57, 11.51it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -24133,8 +24096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2535/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  17%|▏| 2535/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  17%|▏| 2532/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  17%|▏| 2532/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -24142,8 +24105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2536/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  17%|▏| 2536/14932 [03:44<18:19, 11.28it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  17%|▏| 2533/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  17%|▏| 2533/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -24151,8 +24114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2537/14932 [03:44<18:18, 11.28it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  17%|▏| 2537/14932 [03:44<18:18, 11.28it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  17%|▏| 2534/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  17%|▏| 2534/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -24160,8 +24123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2538/14932 [03:44<18:18, 11.28it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  17%|▏| 2538/14932 [03:44<18:18, 11.28it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  17%|▏| 2535/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  17%|▏| 2535/14932 [03:40<17:57, 11.51it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -24169,8 +24132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2539/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  17%|▏| 2539/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  17%|▏| 2536/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  17%|▏| 2536/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -24178,8 +24141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2540/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  17%|▏| 2540/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  17%|▏| 2537/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  17%|▏| 2537/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -24187,8 +24150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2541/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  17%|▏| 2541/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  17%|▏| 2538/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  17%|▏| 2538/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -24196,8 +24159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2542/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  17%|▏| 2542/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  17%|▏| 2539/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  17%|▏| 2539/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -24205,8 +24168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2543/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  17%|▏| 2543/14932 [03:45<18:18, 11.28it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  17%|▏| 2540/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  17%|▏| 2540/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -24214,8 +24177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2544/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  17%|▏| 2544/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  17%|▏| 2541/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  17%|▏| 2541/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -24223,8 +24186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2545/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  17%|▏| 2545/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  17%|▏| 2542/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  17%|▏| 2542/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -24232,8 +24195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2546/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  17%|▏| 2546/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  17%|▏| 2543/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  17%|▏| 2543/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -24241,8 +24204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2547/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  17%|▏| 2547/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  17%|▏| 2544/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  17%|▏| 2544/14932 [03:40<17:56, 11.51it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -24250,8 +24213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2548/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  17%|▏| 2548/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  17%|▏| 2545/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  17%|▏| 2545/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -24259,8 +24222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2549/14932 [03:45<18:17, 11.29it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  17%|▏| 2549/14932 [03:45<18:17, 11.29it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  17%|▏| 2546/14932 [03:41<17:56, 11.51it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  17%|▏| 2546/14932 [03:41<17:56, 11.51it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -24268,8 +24231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2550/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  17%|▏| 2550/14932 [03:45<18:17, 11.28it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  17%|▏| 2547/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  17%|▏| 2547/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -24277,8 +24240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2551/14932 [03:46<18:17, 11.28it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  17%|▏| 2551/14932 [03:46<18:17, 11.28it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  17%|▏| 2548/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  17%|▏| 2548/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -24286,8 +24249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2552/14932 [03:46<18:17, 11.28it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  17%|▏| 2552/14932 [03:46<18:17, 11.28it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  17%|▏| 2549/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  17%|▏| 2549/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -24295,8 +24258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2553/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  17%|▏| 2553/14932 [03:46<18:16, 11.28it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  17%|▏| 2550/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  17%|▏| 2550/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -24304,8 +24267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2554/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  17%|▏| 2554/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  17%|▏| 2551/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  17%|▏| 2551/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -24313,8 +24276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2555/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  17%|▏| 2555/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  17%|▏| 2552/14932 [03:41<17:55, 11.52it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  17%|▏| 2552/14932 [03:41<17:55, 11.51it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -24322,8 +24285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2556/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  17%|▏| 2556/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  17%|▏| 2553/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  17%|▏| 2553/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -24331,8 +24294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2557/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  17%|▏| 2557/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  17%|▏| 2554/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  17%|▏| 2554/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -24340,8 +24303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2558/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  17%|▏| 2558/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  17%|▏| 2555/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  17%|▏| 2555/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -24349,8 +24312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2559/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  17%|▏| 2559/14932 [03:46<18:16, 11.29it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  17%|▏| 2556/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  17%|▏| 2556/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -24358,8 +24321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2560/14932 [03:46<18:16, 11.28it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  17%|▏| 2560/14932 [03:46<18:16, 11.28it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  17%|▏| 2557/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  17%|▏| 2557/14932 [03:41<17:54, 11.52it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -24367,8 +24330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2561/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  17%|▏| 2561/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  17%|▏| 2558/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  17%|▏| 2558/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -24376,8 +24339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2562/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  17%|▏| 2562/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  17%|▏| 2559/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  17%|▏| 2559/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -24385,8 +24348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2563/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  17%|▏| 2563/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  17%|▏| 2560/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  17%|▏| 2560/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=5.81"
      ]
     },
     {
@@ -24394,8 +24357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2564/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  17%|▏| 2564/14932 [03:47<18:16, 11.28it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  17%|▏| 2561/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=5.81\r",
+      "Epoch 0:  17%|▏| 2561/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -24403,8 +24366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2565/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  17%|▏| 2565/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  17%|▏| 2562/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  17%|▏| 2562/14932 [03:42<17:54, 11.52it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -24412,8 +24375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2566/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  17%|▏| 2566/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  17%|▏| 2563/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  17%|▏| 2563/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -24421,8 +24384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2567/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  17%|▏| 2567/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  17%|▏| 2564/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  17%|▏| 2564/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -24430,8 +24393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2568/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  17%|▏| 2568/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=1.50"
+      "Epoch 0:  17%|▏| 2565/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  17%|▏| 2565/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -24439,8 +24402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2569/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=1.50\r",
-      "Epoch 0:  17%|▏| 2569/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  17%|▏| 2566/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  17%|▏| 2566/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -24448,8 +24411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2570/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  17%|▏| 2570/14932 [03:47<18:15, 11.29it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  17%|▏| 2567/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  17%|▏| 2567/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -24457,8 +24420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2571/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  17%|▏| 2571/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  17%|▏| 2568/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  17%|▏| 2568/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -24466,8 +24429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2572/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  17%|▏| 2572/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  17%|▏| 2569/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  17%|▏| 2569/14932 [03:42<17:53, 11.52it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -24475,8 +24438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2573/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  17%|▏| 2573/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  17%|▏| 2570/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  17%|▏| 2570/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -24484,8 +24447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2574/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  17%|▏| 2574/14932 [03:47<18:14, 11.29it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  17%|▏| 2571/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  17%|▏| 2571/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -24493,8 +24456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2575/14932 [03:48<18:14, 11.29it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  17%|▏| 2575/14932 [03:48<18:14, 11.29it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  17%|▏| 2572/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  17%|▏| 2572/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -24502,8 +24465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2576/14932 [03:48<18:14, 11.29it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  17%|▏| 2576/14932 [03:48<18:14, 11.29it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  17%|▏| 2573/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  17%|▏| 2573/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -24511,8 +24474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2577/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  17%|▏| 2577/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  17%|▏| 2574/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  17%|▏| 2574/14932 [03:43<17:52, 11.52it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -24520,8 +24483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2578/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  17%|▏| 2578/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  17%|▏| 2575/14932 [03:43<17:52, 11.53it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  17%|▏| 2575/14932 [03:43<17:52, 11.53it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -24529,8 +24492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2579/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  17%|▏| 2579/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  17%|▏| 2576/14932 [03:43<17:52, 11.53it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  17%|▏| 2576/14932 [03:43<17:52, 11.53it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -24538,8 +24501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2580/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  17%|▏| 2580/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=5.16"
+      "Epoch 0:  17%|▏| 2577/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  17%|▏| 2577/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -24547,8 +24510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2581/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=5.16\r",
-      "Epoch 0:  17%|▏| 2581/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  17%|▏| 2578/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  17%|▏| 2578/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -24556,8 +24519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2582/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  17%|▏| 2582/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  17%|▏| 2579/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  17%|▏| 2579/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -24565,8 +24528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2583/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  17%|▏| 2583/14932 [03:48<18:13, 11.29it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  17%|▏| 2580/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  17%|▏| 2580/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -24574,8 +24537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2584/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  17%|▏| 2584/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  17%|▏| 2581/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  17%|▏| 2581/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -24583,8 +24546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2585/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  17%|▏| 2585/14932 [03:48<18:13, 11.30it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  17%|▏| 2582/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  17%|▏| 2582/14932 [03:43<17:51, 11.53it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -24592,8 +24555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2586/14932 [03:48<18:12, 11.30it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  17%|▏| 2586/14932 [03:48<18:12, 11.30it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  17%|▏| 2583/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  17%|▏| 2583/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -24601,8 +24564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2587/14932 [03:48<18:12, 11.30it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  17%|▏| 2587/14932 [03:48<18:12, 11.30it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  17%|▏| 2584/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  17%|▏| 2584/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -24610,8 +24573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2588/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  17%|▏| 2588/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  17%|▏| 2585/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  17%|▏| 2585/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -24619,8 +24582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2589/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  17%|▏| 2589/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  17%|▏| 2586/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  17%|▏| 2586/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -24628,8 +24591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2590/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  17%|▏| 2590/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  17%|▏| 2587/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  17%|▏| 2587/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -24637,8 +24600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2591/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  17%|▏| 2591/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  17%|▏| 2588/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  17%|▏| 2588/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -24646,8 +24609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2592/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  17%|▏| 2592/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  17%|▏| 2589/14932 [03:44<17:50, 11.54it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  17%|▏| 2589/14932 [03:44<17:50, 11.54it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -24655,8 +24618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2593/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  17%|▏| 2593/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  17%|▏| 2590/14932 [03:44<17:49, 11.54it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  17%|▏| 2590/14932 [03:44<17:49, 11.54it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -24664,8 +24627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2594/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  17%|▏| 2594/14932 [03:49<18:12, 11.30it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  17%|▏| 2591/14932 [03:44<17:49, 11.54it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  17%|▏| 2591/14932 [03:44<17:49, 11.54it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -24673,8 +24636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2595/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  17%|▏| 2595/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  17%|▏| 2592/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  17%|▏| 2592/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -24682,8 +24645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2596/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  17%|▏| 2596/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  17%|▏| 2593/14932 [03:44<17:49, 11.53it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  17%|▏| 2593/14932 [03:44<17:49, 11.53it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -24691,8 +24654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2597/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  17%|▏| 2597/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  17%|▏| 2594/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  17%|▏| 2594/14932 [03:44<17:50, 11.53it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -24700,8 +24663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2598/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  17%|▏| 2598/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  17%|▏| 2595/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  17%|▏| 2595/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -24709,8 +24672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2599/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  17%|▏| 2599/14932 [03:49<18:11, 11.30it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  17%|▏| 2596/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  17%|▏| 2596/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -24718,8 +24681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2600/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  17%|▏| 2600/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  17%|▏| 2597/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  17%|▏| 2597/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -24727,8 +24690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2601/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  17%|▏| 2601/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  17%|▏| 2598/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  17%|▏| 2598/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -24736,8 +24699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2602/14932 [03:50<18:10, 11.31it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  17%|▏| 2602/14932 [03:50<18:10, 11.31it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  17%|▏| 2599/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  17%|▏| 2599/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -24745,8 +24708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2603/14932 [03:50<18:11, 11.30it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  17%|▏| 2603/14932 [03:50<18:11, 11.30it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  17%|▏| 2600/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  17%|▏| 2600/14932 [03:45<17:49, 11.53it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -24754,8 +24717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2604/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  17%|▏| 2604/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  17%|▏| 2601/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  17%|▏| 2601/14932 [03:45<17:49, 11.54it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -24763,8 +24726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2605/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  17%|▏| 2605/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  17%|▏| 2602/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  17%|▏| 2602/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -24772,8 +24735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2606/14932 [03:50<18:11, 11.30it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  17%|▏| 2606/14932 [03:50<18:11, 11.30it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  17%|▏| 2603/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  17%|▏| 2603/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -24781,8 +24744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2607/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  17%|▏| 2607/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  17%|▏| 2604/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  17%|▏| 2604/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -24790,8 +24753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2608/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  17%|▏| 2608/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  17%|▏| 2605/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  17%|▏| 2605/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -24799,8 +24762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2609/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  17%|▏| 2609/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  17%|▏| 2606/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  17%|▏| 2606/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -24808,8 +24771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2610/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  17%|▏| 2610/14932 [03:50<18:10, 11.30it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  17%|▏| 2607/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  17%|▏| 2607/14932 [03:45<17:48, 11.54it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -24817,8 +24780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2611/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  17%|▏| 2611/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  17%|▏| 2608/14932 [03:45<17:47, 11.54it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  17%|▏| 2608/14932 [03:45<17:47, 11.54it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -24826,8 +24789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2612/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  17%|▏| 2612/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=0.87"
+      "Epoch 0:  17%|▏| 2609/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  17%|▏| 2609/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -24835,8 +24798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  17%|▏| 2613/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=0.87\r",
-      "Epoch 0:  17%|▏| 2613/14932 [03:51<18:10, 11.30it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  17%|▏| 2610/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  17%|▏| 2610/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -24844,8 +24807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2614/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  18%|▏| 2614/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  17%|▏| 2611/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  17%|▏| 2611/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -24853,8 +24816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2615/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  18%|▏| 2615/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  17%|▏| 2612/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  17%|▏| 2612/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -24862,8 +24825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2616/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  18%|▏| 2616/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  17%|▏| 2613/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  17%|▏| 2613/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -24871,8 +24834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2617/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  18%|▏| 2617/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  18%|▏| 2614/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  18%|▏| 2614/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -24880,8 +24843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2618/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  18%|▏| 2618/14932 [03:51<18:09, 11.30it/s, v_num=o30c, train/loss=1.69"
+      "Epoch 0:  18%|▏| 2615/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  18%|▏| 2615/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -24889,8 +24852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2619/14932 [03:51<18:09, 11.31it/s, v_num=o30c, train/loss=1.69\r",
-      "Epoch 0:  18%|▏| 2619/14932 [03:51<18:09, 11.31it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  18%|▏| 2616/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  18%|▏| 2616/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -24898,8 +24861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2620/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  18%|▏| 2620/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  18%|▏| 2617/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  18%|▏| 2617/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -24907,8 +24870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2621/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  18%|▏| 2621/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=1.32"
+      "Epoch 0:  18%|▏| 2618/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  18%|▏| 2618/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -24916,8 +24879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2622/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=1.32\r",
-      "Epoch 0:  18%|▏| 2622/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:  18%|▏| 2619/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  18%|▏| 2619/14932 [03:46<17:47, 11.54it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -24925,8 +24888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2623/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:  18%|▏| 2623/14932 [03:51<18:08, 11.31it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  18%|▏| 2620/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  18%|▏| 2620/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -24934,8 +24897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2624/14932 [03:52<18:08, 11.30it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  18%|▏| 2624/14932 [03:52<18:08, 11.30it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  18%|▏| 2621/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  18%|▏| 2621/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -24943,8 +24906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2625/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  18%|▏| 2625/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  18%|▏| 2622/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  18%|▏| 2622/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -24952,8 +24915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2626/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  18%|▏| 2626/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  18%|▏| 2623/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  18%|▏| 2623/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -24961,8 +24924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2627/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  18%|▏| 2627/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  18%|▏| 2624/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  18%|▏| 2624/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -24970,8 +24933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2628/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  18%|▏| 2628/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  18%|▏| 2625/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  18%|▏| 2625/14932 [03:47<17:46, 11.54it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -24979,8 +24942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2629/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  18%|▏| 2629/14932 [03:52<18:08, 11.31it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  18%|▏| 2626/14932 [03:47<17:47, 11.53it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  18%|▏| 2626/14932 [03:47<17:47, 11.53it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -24988,8 +24951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2630/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  18%|▏| 2630/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  18%|▏| 2627/14932 [03:47<17:46, 11.53it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  18%|▏| 2627/14932 [03:47<17:46, 11.53it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -24997,8 +24960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2631/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  18%|▏| 2631/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  18%|▏| 2628/14932 [03:47<17:46, 11.53it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  18%|▏| 2628/14932 [03:47<17:46, 11.53it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -25006,8 +24969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2632/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  18%|▏| 2632/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  18%|▏| 2629/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  18%|▏| 2629/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -25015,8 +24978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2633/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  18%|▏| 2633/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  18%|▏| 2630/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  18%|▏| 2630/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -25024,8 +24987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2634/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  18%|▏| 2634/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  18%|▏| 2631/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  18%|▏| 2631/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -25033,8 +24996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2635/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  18%|▏| 2635/14932 [03:52<18:07, 11.31it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  18%|▏| 2632/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  18%|▏| 2632/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -25042,8 +25005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2636/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  18%|▏| 2636/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  18%|▏| 2633/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  18%|▏| 2633/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -25051,8 +25014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2637/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  18%|▏| 2637/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  18%|▏| 2634/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  18%|▏| 2634/14932 [03:48<17:46, 11.53it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -25060,8 +25023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2638/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  18%|▏| 2638/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  18%|▏| 2635/14932 [03:48<17:46, 11.54it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  18%|▏| 2635/14932 [03:48<17:46, 11.54it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -25069,8 +25032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2639/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  18%|▏| 2639/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  18%|▏| 2636/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  18%|▏| 2636/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -25078,8 +25041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2640/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  18%|▏| 2640/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  18%|▏| 2637/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  18%|▏| 2637/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -25087,8 +25050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2641/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  18%|▏| 2641/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  18%|▏| 2638/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  18%|▏| 2638/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -25096,8 +25059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2642/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  18%|▏| 2642/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  18%|▏| 2639/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  18%|▏| 2639/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -25105,8 +25068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2643/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  18%|▏| 2643/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  18%|▏| 2640/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  18%|▏| 2640/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -25114,8 +25077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2644/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  18%|▏| 2644/14932 [03:53<18:06, 11.31it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  18%|▏| 2641/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  18%|▏| 2641/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -25123,8 +25086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2645/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  18%|▏| 2645/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  18%|▏| 2642/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  18%|▏| 2642/14932 [03:48<17:45, 11.54it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -25132,8 +25095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2646/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  18%|▏| 2646/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  18%|▏| 2643/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  18%|▏| 2643/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -25141,8 +25104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2647/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  18%|▏| 2647/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  18%|▏| 2644/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  18%|▏| 2644/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -25150,8 +25113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2648/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  18%|▏| 2648/14932 [03:53<18:05, 11.32it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  18%|▏| 2645/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  18%|▏| 2645/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -25159,8 +25122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2649/14932 [03:54<18:05, 11.32it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  18%|▏| 2649/14932 [03:54<18:05, 11.32it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  18%|▏| 2646/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  18%|▏| 2646/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -25168,8 +25131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2650/14932 [03:54<18:05, 11.32it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  18%|▏| 2650/14932 [03:54<18:05, 11.32it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  18%|▏| 2647/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  18%|▏| 2647/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -25177,8 +25140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2651/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  18%|▏| 2651/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  18%|▏| 2648/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  18%|▏| 2648/14932 [03:49<17:44, 11.54it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -25186,8 +25149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2652/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  18%|▏| 2652/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  18%|▏| 2649/14932 [03:49<17:43, 11.54it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  18%|▏| 2649/14932 [03:49<17:43, 11.54it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -25195,8 +25158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2653/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  18%|▏| 2653/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  18%|▏| 2650/14932 [03:49<17:43, 11.54it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  18%|▏| 2650/14932 [03:49<17:43, 11.54it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -25204,8 +25167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2654/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  18%|▏| 2654/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  18%|▏| 2651/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  18%|▏| 2651/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -25213,8 +25176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2655/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  18%|▏| 2655/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  18%|▏| 2652/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  18%|▏| 2652/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -25222,8 +25185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2656/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  18%|▏| 2656/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  18%|▏| 2653/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  18%|▏| 2653/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -25231,8 +25194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2657/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  18%|▏| 2657/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  18%|▏| 2654/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  18%|▏| 2654/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -25240,8 +25203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2658/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  18%|▏| 2658/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  18%|▏| 2655/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  18%|▏| 2655/14932 [03:49<17:43, 11.55it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -25249,8 +25212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2659/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  18%|▏| 2659/14932 [03:54<18:04, 11.32it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  18%|▏| 2656/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  18%|▏| 2656/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -25258,8 +25221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2660/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  18%|▏| 2660/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  18%|▏| 2657/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  18%|▏| 2657/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -25267,8 +25230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2661/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  18%|▏| 2661/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  18%|▏| 2658/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  18%|▏| 2658/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -25276,8 +25239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2662/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  18%|▏| 2662/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  18%|▏| 2659/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  18%|▏| 2659/14932 [03:50<17:43, 11.54it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -25285,8 +25248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2663/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  18%|▏| 2663/14932 [03:55<18:04, 11.31it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  18%|▏| 2660/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  18%|▏| 2660/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -25294,8 +25257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2664/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  18%|▏| 2664/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  18%|▏| 2661/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  18%|▏| 2661/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -25303,8 +25266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2665/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  18%|▏| 2665/14932 [03:55<18:04, 11.32it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  18%|▏| 2662/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  18%|▏| 2662/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -25312,8 +25275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2666/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  18%|▏| 2666/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=1.08"
+      "Epoch 0:  18%|▏| 2663/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  18%|▏| 2663/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -25321,8 +25284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2667/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=1.08\r",
-      "Epoch 0:  18%|▏| 2667/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  18%|▏| 2664/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  18%|▏| 2664/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -25330,8 +25293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2668/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  18%|▏| 2668/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  18%|▏| 2665/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  18%|▏| 2665/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -25339,8 +25302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2669/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  18%|▏| 2669/14932 [03:55<18:03, 11.32it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  18%|▏| 2666/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  18%|▏| 2666/14932 [03:50<17:42, 11.55it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -25348,8 +25311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2670/14932 [03:55<18:03, 11.31it/s, v_num=o30c, train/loss=4.84\r",
-      "Epoch 0:  18%|▏| 2670/14932 [03:55<18:03, 11.31it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  18%|▏| 2667/14932 [03:50<17:41, 11.55it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  18%|▏| 2667/14932 [03:50<17:41, 11.55it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -25357,8 +25320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2671/14932 [03:56<18:03, 11.31it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  18%|▏| 2671/14932 [03:56<18:03, 11.31it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  18%|▏| 2668/14932 [03:50<17:41, 11.55it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  18%|▏| 2668/14932 [03:50<17:41, 11.55it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -25366,8 +25329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2672/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  18%|▏| 2672/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  18%|▏| 2669/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  18%|▏| 2669/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -25375,8 +25338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2673/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  18%|▏| 2673/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  18%|▏| 2670/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  18%|▏| 2670/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -25384,8 +25347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2674/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  18%|▏| 2674/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  18%|▏| 2671/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  18%|▏| 2671/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -25393,8 +25356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2675/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  18%|▏| 2675/14932 [03:56<18:03, 11.32it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  18%|▏| 2672/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  18%|▏| 2672/14932 [03:51<17:41, 11.55it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -25402,8 +25365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2676/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  18%|▏| 2676/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  18%|▏| 2673/14932 [03:51<17:40, 11.55it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  18%|▏| 2673/14932 [03:51<17:40, 11.55it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -25411,8 +25374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2677/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  18%|▏| 2677/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  18%|▏| 2674/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  18%|▏| 2674/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=0.99"
      ]
     },
     {
@@ -25420,8 +25383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2678/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  18%|▏| 2678/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  18%|▏| 2675/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=0.99\r",
+      "Epoch 0:  18%|▏| 2675/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -25429,8 +25392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2679/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  18%|▏| 2679/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  18%|▏| 2676/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  18%|▏| 2676/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -25438,8 +25401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2680/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  18%|▏| 2680/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  18%|▏| 2677/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  18%|▏| 2677/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -25447,8 +25410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2681/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  18%|▏| 2681/14932 [03:56<18:02, 11.32it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  18%|▏| 2678/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  18%|▏| 2678/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -25456,8 +25419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2682/14932 [03:56<18:01, 11.32it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  18%|▏| 2682/14932 [03:56<18:01, 11.32it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  18%|▏| 2679/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  18%|▏| 2679/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -25465,8 +25428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2683/14932 [03:56<18:01, 11.32it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  18%|▏| 2683/14932 [03:56<18:01, 11.32it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  18%|▏| 2680/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  18%|▏| 2680/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -25474,8 +25437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2684/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  18%|▏| 2684/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  18%|▏| 2681/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  18%|▏| 2681/14932 [03:51<17:40, 11.56it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -25483,8 +25446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2685/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  18%|▏| 2685/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  18%|▏| 2682/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  18%|▏| 2682/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -25492,8 +25455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2686/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  18%|▏| 2686/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  18%|▏| 2683/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  18%|▏| 2683/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -25501,8 +25464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2687/14932 [03:57<18:01, 11.33it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  18%|▏| 2687/14932 [03:57<18:01, 11.33it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  18%|▏| 2684/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  18%|▏| 2684/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -25510,8 +25473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2688/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  18%|▏| 2688/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  18%|▏| 2685/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  18%|▏| 2685/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -25519,8 +25482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2689/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  18%|▏| 2689/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  18%|▏| 2686/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  18%|▏| 2686/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -25528,8 +25491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2690/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  18%|▏| 2690/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  18%|▏| 2687/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  18%|▏| 2687/14932 [03:52<17:39, 11.56it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -25537,8 +25500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2691/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  18%|▏| 2691/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  18%|▏| 2688/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  18%|▏| 2688/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -25546,8 +25509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2692/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  18%|▏| 2692/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  18%|▏| 2689/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  18%|▏| 2689/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=4.97"
      ]
     },
     {
@@ -25555,8 +25518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2693/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  18%|▏| 2693/14932 [03:57<18:01, 11.32it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  18%|▏| 2690/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=4.97\r",
+      "Epoch 0:  18%|▏| 2690/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -25564,8 +25527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2694/14932 [03:57<18:00, 11.32it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  18%|▏| 2694/14932 [03:57<18:00, 11.32it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  18%|▏| 2691/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  18%|▏| 2691/14932 [03:52<17:39, 11.55it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -25573,8 +25536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2695/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  18%|▏| 2695/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  18%|▏| 2692/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  18%|▏| 2692/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -25582,7 +25545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2696/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  18%|▏| 2693/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  18%|▏| 2693/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -25590,7 +25554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2696/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  18%|▏| 2694/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  18%|▏| 2694/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -25598,8 +25563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2697/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  18%|▏| 2697/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  18%|▏| 2695/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  18%|▏| 2695/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -25607,8 +25572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2698/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  18%|▏| 2698/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  18%|▏| 2696/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  18%|▏| 2696/14932 [03:53<17:39, 11.55it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -25616,8 +25581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2699/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  18%|▏| 2699/14932 [03:58<18:00, 11.32it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  18%|▏| 2697/14932 [03:53<17:38, 11.55it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  18%|▏| 2697/14932 [03:53<17:38, 11.55it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -25625,8 +25590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2700/14932 [03:58<18:00, 11.33it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  18%|▏| 2700/14932 [03:58<18:00, 11.33it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  18%|▏| 2698/14932 [03:53<17:38, 11.55it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  18%|▏| 2698/14932 [03:53<17:38, 11.55it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -25634,8 +25599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2701/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  18%|▏| 2701/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  18%|▏| 2699/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  18%|▏| 2699/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -25643,8 +25608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2702/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  18%|▏| 2702/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  18%|▏| 2700/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  18%|▏| 2700/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -25652,8 +25617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2703/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  18%|▏| 2703/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  18%|▏| 2701/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  18%|▏| 2701/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -25661,8 +25626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2704/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  18%|▏| 2704/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  18%|▏| 2702/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  18%|▏| 2702/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -25670,8 +25635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2705/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  18%|▏| 2705/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  18%|▏| 2703/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  18%|▏| 2703/14932 [03:53<17:38, 11.56it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -25679,8 +25644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2706/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  18%|▏| 2706/14932 [03:58<17:59, 11.33it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  18%|▏| 2704/14932 [03:53<17:37, 11.56it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  18%|▏| 2704/14932 [03:53<17:37, 11.56it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -25688,8 +25653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2707/14932 [03:58<17:58, 11.33it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  18%|▏| 2707/14932 [03:58<17:58, 11.33it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  18%|▏| 2705/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  18%|▏| 2705/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -25697,8 +25662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2708/14932 [03:58<17:58, 11.33it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  18%|▏| 2708/14932 [03:58<17:58, 11.33it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  18%|▏| 2706/14932 [03:54<17:38, 11.55it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  18%|▏| 2706/14932 [03:54<17:38, 11.55it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -25706,8 +25671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2709/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  18%|▏| 2709/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  18%|▏| 2707/14932 [03:54<17:38, 11.55it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  18%|▏| 2707/14932 [03:54<17:38, 11.55it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -25715,8 +25680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2710/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  18%|▏| 2710/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  18%|▏| 2708/14932 [03:54<17:37, 11.55it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  18%|▏| 2708/14932 [03:54<17:37, 11.55it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -25724,8 +25689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2711/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  18%|▏| 2711/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  18%|▏| 2709/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  18%|▏| 2709/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -25733,8 +25698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2712/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  18%|▏| 2712/14932 [03:59<17:58, 11.33it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  18%|▏| 2710/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  18%|▏| 2710/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -25742,8 +25707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2713/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  18%|▏| 2713/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  18%|▏| 2711/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  18%|▏| 2711/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -25751,8 +25716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2714/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  18%|▏| 2714/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  18%|▏| 2712/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  18%|▏| 2712/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -25760,8 +25725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2715/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  18%|▏| 2715/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  18%|▏| 2713/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  18%|▏| 2713/14932 [03:54<17:37, 11.56it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -25769,8 +25734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2716/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  18%|▏| 2716/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  18%|▏| 2714/14932 [03:54<17:36, 11.56it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  18%|▏| 2714/14932 [03:54<17:36, 11.56it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -25778,8 +25743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2717/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  18%|▏| 2717/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  18%|▏| 2715/14932 [03:54<17:36, 11.56it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  18%|▏| 2715/14932 [03:54<17:36, 11.56it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -25787,8 +25752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2718/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  18%|▏| 2718/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  18%|▏| 2716/14932 [03:55<17:37, 11.56it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  18%|▏| 2716/14932 [03:55<17:37, 11.56it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -25796,8 +25761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2719/14932 [03:59<17:56, 11.34it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  18%|▏| 2719/14932 [03:59<17:56, 11.34it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  18%|▏| 2717/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  18%|▏| 2717/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=0.91"
      ]
     },
     {
@@ -25805,8 +25770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2720/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  18%|▏| 2720/14932 [03:59<17:57, 11.34it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  18%|▏| 2718/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=0.91\r",
+      "Epoch 0:  18%|▏| 2718/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -25814,8 +25779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2721/14932 [04:00<17:57, 11.34it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  18%|▏| 2721/14932 [04:00<17:57, 11.34it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  18%|▏| 2719/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  18%|▏| 2719/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -25823,8 +25788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2722/14932 [04:00<17:57, 11.34it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  18%|▏| 2722/14932 [04:00<17:57, 11.34it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  18%|▏| 2720/14932 [03:55<17:36, 11.55it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  18%|▏| 2720/14932 [03:55<17:36, 11.55it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -25832,8 +25797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2723/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  18%|▏| 2723/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  18%|▏| 2721/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  18%|▏| 2721/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -25841,8 +25806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2724/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  18%|▏| 2724/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  18%|▏| 2722/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  18%|▏| 2722/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -25850,8 +25815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2725/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  18%|▏| 2725/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  18%|▏| 2723/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  18%|▏| 2723/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -25859,8 +25824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2726/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  18%|▏| 2726/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  18%|▏| 2724/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  18%|▏| 2724/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -25868,8 +25833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2727/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  18%|▏| 2727/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  18%|▏| 2725/14932 [03:55<17:36, 11.55it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  18%|▏| 2725/14932 [03:55<17:36, 11.55it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -25877,8 +25842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2728/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  18%|▏| 2728/14932 [04:00<17:56, 11.34it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  18%|▏| 2726/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  18%|▏| 2726/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -25886,8 +25851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2729/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  18%|▏| 2729/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  18%|▏| 2727/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  18%|▏| 2727/14932 [03:55<17:36, 11.56it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -25895,8 +25860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2730/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  18%|▏| 2730/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  18%|▏| 2728/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  18%|▏| 2728/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -25904,8 +25869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2731/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  18%|▏| 2731/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  18%|▏| 2729/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  18%|▏| 2729/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -25913,8 +25878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2732/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  18%|▏| 2732/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  18%|▏| 2730/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  18%|▏| 2730/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -25922,8 +25887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2733/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  18%|▏| 2733/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  18%|▏| 2731/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  18%|▏| 2731/14932 [03:56<17:35, 11.56it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -25931,7 +25896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2734/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  18%|▏| 2732/14932 [03:56<17:36, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  18%|▏| 2732/14932 [03:56<17:36, 11.55it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -25939,7 +25905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2734/14932 [04:00<17:55, 11.34it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  18%|▏| 2733/14932 [03:56<17:36, 11.55it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  18%|▏| 2733/14932 [03:56<17:36, 11.55it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -25947,8 +25914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2735/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  18%|▏| 2735/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  18%|▏| 2734/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  18%|▏| 2734/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -25956,8 +25923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2736/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  18%|▏| 2736/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  18%|▏| 2735/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  18%|▏| 2735/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -25965,8 +25932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2737/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  18%|▏| 2737/14932 [04:01<17:55, 11.34it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  18%|▏| 2736/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  18%|▏| 2736/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -25974,8 +25941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2738/14932 [04:01<17:54, 11.34it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  18%|▏| 2738/14932 [04:01<17:54, 11.34it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  18%|▏| 2737/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  18%|▏| 2737/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -25983,8 +25950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2739/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  18%|▏| 2739/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  18%|▏| 2738/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  18%|▏| 2738/14932 [03:56<17:35, 11.55it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -25992,8 +25959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2740/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  18%|▏| 2740/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  18%|▏| 2739/14932 [03:57<17:35, 11.55it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  18%|▏| 2739/14932 [03:57<17:35, 11.55it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -26001,8 +25968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2741/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  18%|▏| 2741/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  18%|▏| 2740/14932 [03:57<17:35, 11.56it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  18%|▏| 2740/14932 [03:57<17:35, 11.56it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -26010,8 +25977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2742/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  18%|▏| 2742/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  18%|▏| 2741/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  18%|▏| 2741/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -26019,8 +25986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2743/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  18%|▏| 2743/14932 [04:01<17:54, 11.35it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  18%|▏| 2742/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  18%|▏| 2742/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -26028,8 +25995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2744/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  18%|▏| 2744/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  18%|▏| 2743/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  18%|▏| 2743/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -26037,8 +26004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2745/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  18%|▏| 2745/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  18%|▏| 2744/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  18%|���| 2744/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -26046,8 +26013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2746/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  18%|▏| 2746/14932 [04:01<17:53, 11.35it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  18%|▏| 2745/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  18%|▏| 2745/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -26055,8 +26022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2747/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  18%|▏| 2747/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  18%|▏| 2746/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  18%|▏| 2746/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -26064,8 +26031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2748/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  18%|▏| 2748/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  18%|▏| 2747/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  18%|▏| 2747/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -26073,8 +26040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2749/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  18%|▏| 2749/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  18%|▏| 2748/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  18%|▏| 2748/14932 [03:57<17:34, 11.56it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -26082,8 +26049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2750/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  18%|▏| 2750/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  18%|▏| 2749/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  18%|▏| 2749/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -26091,8 +26058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2751/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  18%|▏| 2751/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  18%|▏| 2750/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  18%|▏| 2750/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -26100,8 +26067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2752/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  18%|▏| 2752/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  18%|▏| 2751/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  18%|▏| 2751/14932 [03:57<17:33, 11.56it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -26109,8 +26076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2753/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  18%|▏| 2753/14932 [04:02<17:53, 11.35it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  18%|▏| 2752/14932 [03:58<17:34, 11.56it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  18%|▏| 2752/14932 [03:58<17:34, 11.56it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -26118,8 +26085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2754/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  18%|▏| 2754/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  18%|▏| 2753/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  18%|▏| 2753/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -26127,8 +26094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2755/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  18%|▏| 2755/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  18%|▏| 2754/14932 [03:58<17:34, 11.55it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  18%|▏| 2754/14932 [03:58<17:34, 11.55it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -26136,8 +26103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2756/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  18%|▏| 2756/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  18%|▏| 2755/14932 [03:58<17:34, 11.55it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  18%|▏| 2755/14932 [03:58<17:34, 11.55it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -26145,8 +26112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2757/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  18%|▏| 2757/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  18%|▏| 2756/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  18%|▏| 2756/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -26154,8 +26121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2758/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  18%|▏| 2758/14932 [04:02<17:52, 11.35it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  18%|▏| 2757/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  18%|▏| 2757/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -26163,8 +26130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2759/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  18%|▏| 2759/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  18%|▏| 2758/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  18%|▏| 2758/14932 [03:58<17:33, 11.55it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -26172,8 +26139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2760/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  18%|▏| 2760/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  18%|▏| 2759/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  18%|▏| 2759/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -26181,8 +26148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2761/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  18%|▏| 2761/14932 [04:03<17:52, 11.35it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  18%|▏| 2760/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  18%|▏| 2760/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -26190,8 +26157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  18%|▏| 2762/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  18%|▏| 2762/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  18%|▏| 2761/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  18%|▏| 2761/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -26199,8 +26166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2763/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  19%|▏| 2763/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  18%|▏| 2762/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  18%|▏| 2762/14932 [03:58<17:33, 11.56it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -26208,8 +26175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2764/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  19%|▏| 2764/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  19%|▏| 2763/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  19%|▏| 2763/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -26217,8 +26184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2765/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  19%|▏| 2765/14932 [04:03<17:51, 11.35it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  19%|▏| 2764/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  19%|▏| 2764/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -26226,8 +26193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2766/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  19%|▏| 2766/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  19%|▏| 2765/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  19%|▏| 2765/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -26235,8 +26202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2767/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  19%|▏| 2767/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  19%|▏| 2766/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  19%|▏| 2766/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -26244,8 +26211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2768/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  19%|▏| 2768/14932 [04:03<17:51, 11.36it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  19%|▏| 2767/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  19%|▏| 2767/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -26253,8 +26220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2769/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  19%|▏| 2769/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=1.57"
+      "Epoch 0:  19%|▏| 2768/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  19%|▏| 2768/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -26262,8 +26229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2770/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=1.57\r",
-      "Epoch 0:  19%|▏| 2770/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  19%|▏| 2769/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  19%|▏| 2769/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -26271,8 +26238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2771/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  19%|▏| 2771/14932 [04:03<17:50, 11.36it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  19%|▏| 2770/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  19%|▏| 2770/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -26280,8 +26247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2772/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  19%|▏| 2772/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  19%|▏| 2771/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  19%|▏| 2771/14932 [03:59<17:32, 11.56it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -26289,8 +26256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2773/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  19%|▏| 2773/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  19%|▏| 2772/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  19%|▏| 2772/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -26298,8 +26265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2774/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  19%|▏| 2774/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  19%|▏| 2773/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  19%|▏| 2773/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -26307,8 +26274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2775/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  19%|▏| 2775/14932 [04:04<17:50, 11.36it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  19%|▏| 2774/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  19%|▏| 2774/14932 [03:59<17:31, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -26316,8 +26283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2776/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  19%|▏| 2776/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  19%|▏| 2775/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  19%|▏| 2775/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -26325,8 +26292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2777/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  19%|▏| 2777/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  19%|▏| 2776/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  19%|▏| 2776/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -26334,8 +26301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2778/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  19%|▏| 2778/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  19%|▏| 2777/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  19%|▏| 2777/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -26343,8 +26310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2779/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  19%|▏| 2779/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  19%|▏| 2778/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  19%|▏| 2778/14932 [04:00<17:31, 11.56it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -26352,8 +26319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2780/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  19%|▏| 2780/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  19%|▏| 2779/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  19%|▏| 2779/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -26361,8 +26328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2781/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  19%|▏| 2781/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:  19%|▏| 2780/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  19%|▏| 2780/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -26370,8 +26337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2782/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:  19%|▏| 2782/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  19%|▏| 2781/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  19%|▏| 2781/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -26379,8 +26346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2783/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  19%|▏| 2783/14932 [04:04<17:49, 11.36it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  19%|▏| 2782/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  19%|▏| 2782/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -26388,8 +26355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2784/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  19%|▏| 2784/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  19%|▏| 2783/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  19%|▏| 2783/14932 [04:00<17:30, 11.57it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -26397,8 +26364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2785/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  19%|▏| 2785/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  19%|▏| 2784/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  19%|▏| 2784/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -26406,8 +26373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2786/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  19%|▏| 2786/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  19%|▏| 2785/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  19%|▏| 2785/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -26415,8 +26382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2787/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  19%|▏| 2787/14932 [04:05<17:49, 11.36it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  19%|▏| 2786/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  19%|▏| 2786/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -26424,8 +26391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2788/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  19%|▏| 2788/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  19%|▏| 2787/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  19%|▏| 2787/14932 [04:00<17:30, 11.56it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -26433,8 +26400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2789/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  19%|▏| 2789/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  19%|▏| 2788/14932 [04:01<17:30, 11.56it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  19%|▏| 2788/14932 [04:01<17:30, 11.56it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -26442,8 +26409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2790/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  19%|▏| 2790/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  19%|▏| 2789/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  19%|▏| 2789/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -26451,8 +26418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2791/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  19%|▏| 2791/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  19%|▏| 2790/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  19%|▏| 2790/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -26460,8 +26427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2792/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  19%|▏| 2792/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  19%|▏| 2791/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  19%|▏| 2791/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -26469,8 +26436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2793/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  19%|▏| 2793/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  19%|▏| 2792/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  19%|▏| 2792/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -26478,8 +26445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2794/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  19%|▏| 2794/14932 [04:05<17:48, 11.36it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  19%|▏| 2793/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  19%|▏| 2793/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -26487,8 +26454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2795/14932 [04:05<17:47, 11.37it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  19%|▏| 2795/14932 [04:05<17:47, 11.37it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  19%|▏| 2794/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  19%|▏| 2794/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -26496,8 +26463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2796/14932 [04:05<17:47, 11.37it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  19%|▏| 2796/14932 [04:05<17:47, 11.37it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  19%|▏| 2795/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  19%|▏| 2795/14932 [04:01<17:29, 11.57it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -26505,8 +26472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2797/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  19%|▏| 2797/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  19%|▏| 2796/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  19%|▏| 2796/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -26514,8 +26481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2798/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  19%|▏| 2798/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  19%|▏| 2797/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  19%|▏| 2797/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -26523,8 +26490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2799/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  19%|▏| 2799/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  19%|▏| 2798/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  19%|▏| 2798/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -26532,8 +26499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2800/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  19%|▏| 2800/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  19%|▏| 2799/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  19%|▏| 2799/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -26541,8 +26508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2801/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  19%|▏| 2801/14932 [04:06<17:47, 11.37it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  19%|▏| 2800/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  19%|▏| 2800/14932 [04:01<17:28, 11.57it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -26550,8 +26517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2802/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  19%|▏| 2802/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  19%|▏| 2801/14932 [04:02<17:28, 11.57it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  19%|▏| 2801/14932 [04:02<17:28, 11.57it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -26559,8 +26526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2803/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  19%|▏| 2803/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  19%|▏| 2802/14932 [04:02<17:28, 11.57it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  19%|▏| 2802/14932 [04:02<17:28, 11.57it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -26568,8 +26535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2804/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  19%|▏| 2804/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  19%|▏| 2803/14932 [04:02<17:27, 11.57it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  19%|▏| 2803/14932 [04:02<17:27, 11.57it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -26577,8 +26544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2805/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  19%|▏| 2805/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  19%|▏| 2804/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  19%|▏| 2804/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -26586,8 +26553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2806/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  19%|▏| 2806/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  19%|▏| 2805/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  19%|▏| 2805/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -26595,8 +26562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2807/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  19%|▏| 2807/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  19%|▏| 2806/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  19%|▏| 2806/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -26604,8 +26571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2808/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  19%|▏| 2808/14932 [04:06<17:46, 11.37it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  19%|▏| 2807/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  19%|▏| 2807/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=1.49"
      ]
     },
     {
@@ -26613,8 +26580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2809/14932 [04:06<17:45, 11.37it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  19%|▏| 2809/14932 [04:06<17:45, 11.37it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  19%|▏| 2808/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=1.49\r",
+      "Epoch 0:  19%|▏| 2808/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -26622,8 +26589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2810/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  19%|▏| 2810/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  19%|▏| 2809/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  19%|▏| 2809/14932 [04:02<17:27, 11.58it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -26631,8 +26598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2811/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  19%|▏| 2811/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  19%|▏| 2810/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  19%|▏| 2810/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -26640,8 +26607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2812/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  19%|▏| 2812/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  19%|▏| 2811/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  19%|▏| 2811/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -26649,8 +26616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2813/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  19%|▏| 2813/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  19%|▏| 2812/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  19%|▏| 2812/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -26658,8 +26625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2814/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  19%|▏| 2814/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  19%|▏| 2813/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  19%|▏| 2813/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -26667,8 +26634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2815/14932 [04:07<17:45, 11.38it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  19%|▏| 2815/14932 [04:07<17:45, 11.38it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  19%|▏| 2814/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  19%|▏| 2814/14932 [04:02<17:26, 11.58it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -26676,8 +26643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2816/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  19%|▏| 2816/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  19%|▏| 2815/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  19%|▏| 2815/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -26685,8 +26652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2817/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  19%|▏| 2817/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  19%|▏| 2816/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  19%|▏| 2816/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -26694,8 +26661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2818/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  19%|▏| 2818/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  19%|▏| 2817/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  19%|▏| 2817/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -26703,8 +26670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2819/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  19%|▏| 2819/14932 [04:07<17:45, 11.37it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  19%|▏| 2818/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  19%|▏| 2818/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -26712,8 +26679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2820/14932 [04:07<17:44, 11.37it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  19%|▏| 2820/14932 [04:07<17:44, 11.37it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  19%|▏| 2819/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  19%|▏| 2819/14932 [04:03<17:26, 11.58it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -26721,8 +26688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2821/14932 [04:08<17:44, 11.37it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  19%|▏| 2821/14932 [04:08<17:44, 11.37it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  19%|▏| 2820/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  19%|▏| 2820/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -26730,8 +26697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2822/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  19%|▏| 2822/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  19%|▏| 2821/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  19%|▏| 2821/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -26739,8 +26706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2823/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  19%|▏| 2823/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  19%|▏| 2822/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  19%|▏| 2822/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -26748,8 +26715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2824/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  19%|▏| 2824/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  19%|▏| 2823/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  19%|▏| 2823/14932 [04:03<17:25, 11.58it/s, v_num=ui8w, train/loss=1.05"
      ]
     },
     {
@@ -26757,8 +26724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2825/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  19%|▏| 2825/14932 [04:08<17:44, 11.38it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  19%|▏| 2824/14932 [04:03<17:26, 11.57it/s, v_num=ui8w, train/loss=1.05\r",
+      "Epoch 0:  19%|▏| 2824/14932 [04:03<17:26, 11.57it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -26766,8 +26733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2826/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  19%|▏| 2826/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  19%|▏| 2825/14932 [04:04<17:25, 11.57it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  19%|▏| 2825/14932 [04:04<17:25, 11.57it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -26775,8 +26742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2827/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  19%|▏| 2827/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  19%|▏| 2826/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  19%|▏| 2826/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -26784,8 +26751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2828/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  19%|▏| 2828/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  19%|▏| 2827/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  19%|▏| 2827/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -26793,8 +26760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2829/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  19%|▏| 2829/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  19%|▏| 2828/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  19%|▏| 2828/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -26802,8 +26769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2830/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  19%|▏| 2830/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  19%|▏| 2829/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  19%|▏| 2829/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -26811,8 +26778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2831/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  19%|▏| 2831/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  19%|▏| 2830/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  19%|▏| 2830/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -26820,8 +26787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2832/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  19%|▏| 2832/14932 [04:08<17:43, 11.38it/s, v_num=o30c, train/loss=5.22"
+      "Epoch 0:  19%|▏| 2831/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  19%|▏| 2831/14932 [04:04<17:25, 11.58it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -26829,8 +26796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2833/14932 [04:08<17:42, 11.38it/s, v_num=o30c, train/loss=5.22\r",
-      "Epoch 0:  19%|▏| 2833/14932 [04:08<17:42, 11.38it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  19%|▏| 2832/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  19%|▏| 2832/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -26838,8 +26805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2834/14932 [04:08<17:42, 11.38it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  19%|▏| 2834/14932 [04:08<17:42, 11.38it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  19%|▏| 2833/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  19%|▏| 2833/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -26847,8 +26814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2835/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  19%|▏| 2835/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  19%|▏| 2834/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  19%|▏| 2834/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -26856,8 +26823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2836/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  19%|▏| 2836/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  19%|▏| 2835/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  19%|▏| 2835/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -26865,8 +26832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2837/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  19%|▏| 2837/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  19%|▏| 2836/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  19%|▏| 2836/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -26874,8 +26841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2838/14932 [04:09<17:42, 11.39it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  19%|▏| 2838/14932 [04:09<17:42, 11.38it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  19%|▏| 2837/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  19%|▏| 2837/14932 [04:04<17:24, 11.58it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -26883,8 +26850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2839/14932 [04:09<17:42, 11.39it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  19%|▏| 2839/14932 [04:09<17:42, 11.39it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  19%|▏| 2838/14932 [04:05<17:24, 11.58it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  19%|▏| 2838/14932 [04:05<17:24, 11.58it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -26892,8 +26859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2840/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  19%|▏| 2840/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  19%|▏| 2839/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  19%|▏| 2839/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -26901,8 +26868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2841/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  19%|▏| 2841/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  19%|▏| 2840/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  19%|▏| 2840/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -26910,8 +26877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2842/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  19%|▏| 2842/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  19%|▏| 2841/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  19%|▏| 2841/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -26919,8 +26886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2843/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  19%|▏| 2843/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  19%|▏| 2842/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  19%|▏| 2842/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -26928,8 +26895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2844/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  19%|▏| 2844/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  19%|▏| 2843/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  19%|▏| 2843/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -26937,8 +26904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2845/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  19%|▏| 2845/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:  19%|▏| 2844/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  19%|▏| 2844/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -26946,8 +26913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2846/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:  19%|▏| 2846/14932 [04:09<17:41, 11.39it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  19%|▏| 2845/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  19%|▏| 2845/14932 [04:05<17:23, 11.59it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -26955,8 +26922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2847/14932 [04:09<17:40, 11.39it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  19%|▏| 2847/14932 [04:09<17:40, 11.39it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  19%|▏| 2846/14932 [04:05<17:22, 11.59it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  19%|▏| 2846/14932 [04:05<17:22, 11.59it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -26964,8 +26931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2848/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  19%|▏| 2848/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  19%|▏| 2847/14932 [04:05<17:22, 11.59it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  19%|▏| 2847/14932 [04:05<17:22, 11.59it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -26973,8 +26940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2849/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  19%|▏| 2849/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  19%|▏| 2848/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  19%|▏| 2848/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -26982,8 +26949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2850/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  19%|▏| 2850/14932 [04:10<17:41, 11.38it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  19%|▏| 2849/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  19%|▏| 2849/14932 [04:05<17:23, 11.58it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -26991,8 +26958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2851/14932 [04:10<17:41, 11.39it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  19%|▏| 2851/14932 [04:10<17:41, 11.39it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  19%|▏| 2850/14932 [04:06<17:22, 11.58it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  19%|▏| 2850/14932 [04:06<17:22, 11.58it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -27000,8 +26967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2852/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  19%|▏| 2852/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  19%|▏| 2851/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  19%|▏| 2851/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -27009,8 +26976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2853/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  19%|▏| 2853/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  19%|▏| 2852/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  19%|▏| 2852/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -27018,8 +26985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2854/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  19%|▏| 2854/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:  19%|▏| 2853/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  19%|▏| 2853/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -27027,8 +26994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2855/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:  19%|▏| 2855/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  19%|▏| 2854/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  19%|▏| 2854/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -27036,8 +27003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2856/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  19%|▏| 2856/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  19%|▏| 2855/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  19%|▏| 2855/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -27045,8 +27012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2857/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  19%|▏| 2857/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  19%|▏| 2856/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  19%|▏| 2856/14932 [04:06<17:22, 11.59it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -27054,8 +27021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2858/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  19%|▏| 2858/14932 [04:10<17:40, 11.39it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  19%|▏| 2857/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  19%|▏| 2857/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -27063,8 +27030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2859/14932 [04:10<17:39, 11.39it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  19%|▏| 2859/14932 [04:10<17:39, 11.39it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  19%|▏| 2858/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  19%|▏| 2858/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -27072,8 +27039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2860/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  19%|▏| 2860/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  19%|▏| 2859/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  19%|▏| 2859/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -27081,8 +27048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2861/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  19%|▏| 2861/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  19%|▏| 2860/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  19%|▏| 2860/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -27090,8 +27057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2862/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  19%|▏| 2862/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=5.88"
+      "Epoch 0:  19%|▏| 2861/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  19%|▏| 2861/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -27099,8 +27066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2863/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=5.88\r",
-      "Epoch 0:  19%|▏| 2863/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  19%|▏| 2862/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  19%|▏| 2862/14932 [04:06<17:21, 11.59it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -27108,8 +27075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2864/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  19%|▏| 2864/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  19%|▏| 2863/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  19%|▏| 2863/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -27117,8 +27084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2865/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  19%|▏| 2865/14932 [04:11<17:39, 11.39it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  19%|▏| 2864/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  19%|▏| 2864/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -27126,8 +27093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2866/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  19%|▏| 2866/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=5.28"
+      "Epoch 0:  19%|▏| 2865/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  19%|▏| 2865/14932 [04:07<17:21, 11.59it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -27135,8 +27102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2867/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=5.28\r",
-      "Epoch 0:  19%|▏| 2867/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  19%|▏| 2866/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  19%|▏| 2866/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -27144,8 +27111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2868/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  19%|▏| 2868/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  19%|▏| 2867/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  19%|▏| 2867/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -27153,8 +27120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2869/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  19%|▏| 2869/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  19%|▏| 2868/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  19%|▏| 2868/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -27162,8 +27129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2870/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  19%|▏| 2870/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=0.83"
+      "Epoch 0:  19%|▏| 2869/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  19%|▏| 2869/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -27171,8 +27138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2871/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=0.83\r",
-      "Epoch 0:  19%|▏| 2871/14932 [04:11<17:38, 11.40it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  19%|▏| 2870/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  19%|▏| 2870/14932 [04:07<17:20, 11.59it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -27180,8 +27147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2872/14932 [04:11<17:37, 11.40it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  19%|▏| 2872/14932 [04:11<17:37, 11.40it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  19%|▏| 2871/14932 [04:07<17:20, 11.60it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  19%|▏| 2871/14932 [04:07<17:20, 11.60it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -27189,8 +27156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2873/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  19%|▏| 2873/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  19%|▏| 2872/14932 [04:07<17:20, 11.60it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  19%|▏| 2872/14932 [04:07<17:20, 11.60it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -27198,8 +27165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2874/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  19%|▏| 2874/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  19%|▏| 2873/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  19%|▏| 2873/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -27207,8 +27174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2875/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  19%|▏| 2875/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  19%|▏| 2874/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  19%|▏| 2874/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -27216,8 +27183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2876/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  19%|▏| 2876/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  19%|▏| 2875/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  19%|▏| 2875/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -27225,8 +27192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2877/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  19%|▏| 2877/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  19%|▏| 2876/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  19%|▏| 2876/14932 [04:07<17:19, 11.60it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -27234,8 +27201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2878/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  19%|▏| 2878/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  19%|▏| 2877/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  19%|▏| 2877/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -27243,8 +27210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2879/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  19%|▏| 2879/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  19%|▏| 2878/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  19%|▏| 2878/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -27252,8 +27219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2880/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  19%|▏| 2880/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  19%|▏| 2879/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  19%|▏| 2879/14932 [04:08<17:19, 11.60it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -27261,8 +27228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2881/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  19%|▏| 2881/14932 [04:12<17:37, 11.40it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  19%|▏| 2880/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  19%|▏| 2880/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -27270,8 +27237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2882/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  19%|▏| 2882/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  19%|▏| 2881/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  19%|▏| 2881/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -27279,8 +27246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2883/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  19%|▏| 2883/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  19%|▏| 2882/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  19%|▏| 2882/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -27288,8 +27255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2884/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  19%|▏| 2884/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  19%|▏| 2883/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  19%|▏| 2883/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -27297,8 +27264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2885/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  19%|▏| 2885/14932 [04:12<17:36, 11.40it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  19%|▏| 2884/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  19%|▏| 2884/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -27306,8 +27273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2886/14932 [04:13<17:36, 11.40it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  19%|▏| 2886/14932 [04:13<17:36, 11.40it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  19%|▏| 2885/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  19%|▏| 2885/14932 [04:08<17:19, 11.59it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -27315,8 +27282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2887/14932 [04:13<17:36, 11.40it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  19%|▏| 2887/14932 [04:13<17:36, 11.40it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  19%|▏| 2886/14932 [04:08<17:18, 11.59it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  19%|▏| 2886/14932 [04:08<17:18, 11.59it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -27324,8 +27291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2888/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  19%|▏| 2888/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  19%|▏| 2887/14932 [04:08<17:18, 11.59it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  19%|▏| 2887/14932 [04:08<17:18, 11.59it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -27333,8 +27300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2889/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  19%|▏| 2889/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  19%|▏| 2888/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:  19%|▏| 2888/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -27342,8 +27309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2890/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  19%|▏| 2890/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  19%|▏| 2889/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  19%|▏| 2889/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -27351,8 +27318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2891/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  19%|▏| 2891/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  19%|▏| 2890/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  19%|▏| 2890/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -27360,7 +27327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2892/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  19%|▏| 2891/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  19%|▏| 2891/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -27368,7 +27336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2892/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  19%|▏| 2892/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  19%|▏| 2892/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -27376,8 +27345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2893/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  19%|▏| 2893/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  19%|▏| 2893/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  19%|▏| 2893/14932 [04:09<17:18, 11.60it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -27385,8 +27354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2894/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  19%|▏| 2894/14932 [04:13<17:35, 11.41it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  19%|▏| 2894/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  19%|▏| 2894/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -27394,8 +27363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2895/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  19%|▏| 2895/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  19%|▏| 2895/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  19%|▏| 2895/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -27403,8 +27372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2896/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  19%|▏| 2896/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  19%|▏| 2896/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  19%|▏| 2896/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -27412,8 +27381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2897/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  19%|▏| 2897/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  19%|▏| 2897/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  19%|▏| 2897/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -27421,8 +27390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2898/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  19%|▏| 2898/14932 [04:13<17:34, 11.41it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  19%|▏| 2898/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  19%|▏| 2898/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -27430,8 +27399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2899/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  19%|▏| 2899/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  19%|▏| 2899/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  19%|▏| 2899/14932 [04:09<17:17, 11.60it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -27439,8 +27408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2900/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  19%|▏| 2900/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  19%|▏| 2900/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  19%|▏| 2900/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -27448,8 +27417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2901/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  19%|▏| 2901/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  19%|▏| 2901/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  19%|▏| 2901/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -27457,8 +27426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2902/14932 [04:14<17:33, 11.41it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  19%|▏| 2902/14932 [04:14<17:33, 11.41it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  19%|▏| 2902/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  19%|▏| 2902/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -27466,8 +27435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2903/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  19%|▏| 2903/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  19%|▏| 2903/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  19%|▏| 2903/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -27475,8 +27444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2904/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  19%|▏| 2904/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  19%|▏| 2904/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  19%|▏| 2904/14932 [04:10<17:17, 11.60it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -27484,8 +27453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2905/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  19%|▏| 2905/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  19%|▏| 2905/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  19%|▏| 2905/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -27493,8 +27462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2906/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  19%|▏| 2906/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  19%|▏| 2906/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  19%|▏| 2906/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -27502,8 +27471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2907/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  19%|▏| 2907/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  19%|▏| 2907/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  19%|▏| 2907/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -27511,8 +27480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2908/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  19%|▏| 2908/14932 [04:14<17:34, 11.41it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  19%|▏| 2908/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  19%|▏| 2908/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -27520,8 +27489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2909/14932 [04:14<17:33, 11.41it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  19%|▏| 2909/14932 [04:14<17:33, 11.41it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  19%|▏| 2909/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  19%|▏| 2909/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -27529,8 +27498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2910/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  19%|▏| 2910/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  19%|▏| 2910/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  19%|▏| 2910/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -27538,8 +27507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  19%|▏| 2911/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  19%|▏| 2911/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  19%|▏| 2911/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  19%|▏| 2911/14932 [04:10<17:16, 11.60it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -27547,8 +27516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2912/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  20%|▏| 2912/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  20%|▏| 2912/14932 [04:11<17:16, 11.60it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  20%|▏| 2912/14932 [04:11<17:16, 11.60it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -27556,8 +27525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2913/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  20%|▏| 2913/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  20%|▏| 2913/14932 [04:11<17:16, 11.60it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  20%|▏| 2913/14932 [04:11<17:16, 11.60it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -27565,8 +27534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2914/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  20%|▏| 2914/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  20%|▏| 2914/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  20%|▏| 2914/14932 [04:11<17:17, 11.59it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -27574,8 +27543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2915/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  20%|▏| 2915/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  20%|▏| 2915/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  20%|▏| 2915/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -27583,8 +27552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2916/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  20%|▏| 2916/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  20%|▏| 2916/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  20%|▏| 2916/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -27592,8 +27561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2917/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  20%|▏| 2917/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  20%|▏| 2917/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  20%|▏| 2917/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -27601,8 +27570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2918/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  20%|▏| 2918/14932 [04:15<17:33, 11.41it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  20%|▏| 2918/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  20%|▏| 2918/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -27610,8 +27579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2919/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  20%|▏| 2919/14932 [04:15<17:33, 11.40it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  20%|▏| 2919/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  20%|▏| 2919/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -27619,8 +27588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2920/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  20%|▏| 2920/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  20%|▏| 2920/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  20%|▏| 2920/14932 [04:11<17:16, 11.59it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -27628,8 +27597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2921/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  20%|▏| 2921/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  20%|▏| 2921/14932 [04:12<17:16, 11.59it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  20%|▏| 2921/14932 [04:12<17:16, 11.59it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -27637,8 +27606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2922/14932 [04:16<17:33, 11.41it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  20%|▏| 2922/14932 [04:16<17:33, 11.41it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  20%|▏| 2922/14932 [04:12<17:16, 11.59it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  20%|▏| 2922/14932 [04:12<17:16, 11.59it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -27646,8 +27615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2923/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  20%|▏| 2923/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  20%|▏| 2923/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  20%|▏| 2923/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -27655,8 +27624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2924/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  20%|▏| 2924/14932 [04:16<17:33, 11.40it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  20%|▏| 2924/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  20%|▏| 2924/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -27664,8 +27633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2925/14932 [04:16<17:32, 11.40it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  20%|▏| 2925/14932 [04:16<17:32, 11.40it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  20%|▏| 2925/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  20%|▏| 2925/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -27673,8 +27642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2926/14932 [04:16<17:32, 11.40it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  20%|▏| 2926/14932 [04:16<17:32, 11.40it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  20%|▏| 2926/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  20%|▏| 2926/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -27682,8 +27651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2927/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  20%|▏| 2927/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  20%|▏| 2927/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  20%|▏| 2927/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -27691,8 +27660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2928/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  20%|▏| 2928/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  20%|▏| 2928/14932 [04:12<17:15, 11.60it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  20%|▏| 2928/14932 [04:12<17:15, 11.60it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -27700,8 +27669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2929/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  20%|▏| 2929/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  20%|▏| 2929/14932 [04:12<17:15, 11.60it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  20%|▏| 2929/14932 [04:12<17:15, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -27709,8 +27678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2930/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  20%|▏| 2930/14932 [04:16<17:32, 11.41it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  20%|▏| 2930/14932 [04:12<17:14, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  20%|▏| 2930/14932 [04:12<17:14, 11.60it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -27718,8 +27687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2931/14932 [04:16<17:31, 11.41it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  20%|▏| 2931/14932 [04:16<17:31, 11.41it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  20%|▏| 2931/14932 [04:12<17:14, 11.60it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  20%|▏| 2931/14932 [04:12<17:14, 11.60it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -27727,8 +27696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2932/14932 [04:16<17:31, 11.41it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  20%|▏| 2932/14932 [04:16<17:31, 11.41it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  20%|▏| 2932/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  20%|▏| 2932/14932 [04:12<17:15, 11.59it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -27736,8 +27705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2933/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  20%|▏| 2933/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  20%|▏| 2933/14932 [04:13<17:15, 11.59it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  20%|▏| 2933/14932 [04:13<17:15, 11.59it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -27745,8 +27714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2934/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  20%|▏| 2934/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=5.41"
+      "Epoch 0:  20%|▏| 2934/14932 [04:13<17:15, 11.59it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  20%|▏| 2934/14932 [04:13<17:15, 11.59it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -27754,8 +27723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2935/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=5.41\r",
-      "Epoch 0:  20%|▏| 2935/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  20%|▏| 2935/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  20%|▏| 2935/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -27763,8 +27732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2936/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  20%|▏| 2936/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  20%|▏| 2936/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  20%|▏| 2936/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -27772,8 +27741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2937/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  20%|▏| 2937/14932 [04:17<17:31, 11.41it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  20%|▏| 2937/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  20%|▏| 2937/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -27781,8 +27750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2938/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  20%|▏| 2938/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  20%|▏| 2938/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  20%|▏| 2938/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -27790,8 +27759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2939/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  20%|▏| 2939/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  20%|▏| 2939/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  20%|▏| 2939/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -27799,8 +27768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2940/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  20%|▏| 2940/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  20%|▏| 2940/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  20%|▏| 2940/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -27808,8 +27777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2941/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  20%|▏| 2941/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  20%|▏| 2941/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  20%|▏| 2941/14932 [04:13<17:14, 11.60it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -27817,8 +27786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2942/14932 [04:17<17:30, 11.42it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  20%|▏| 2942/14932 [04:17<17:30, 11.42it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  20%|▏| 2942/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  20%|▏| 2942/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -27826,8 +27795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2943/14932 [04:17<17:30, 11.42it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  20%|▏| 2943/14932 [04:17<17:30, 11.42it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  20%|▏| 2943/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  20%|▏| 2943/14932 [04:13<17:14, 11.59it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -27835,8 +27804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2944/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  20%|▏| 2944/14932 [04:17<17:30, 11.41it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  20%|▏| 2944/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  20%|▏| 2944/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -27844,8 +27813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2945/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  20%|▏| 2945/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  20%|▏| 2945/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  20%|▏| 2945/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -27853,8 +27822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2946/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  20%|▏| 2946/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  20%|▏| 2946/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  20%|▏| 2946/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -27862,8 +27831,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2947/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  20%|▏| 2947/14932 [04:18<17:30, 11.41it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  20%|▏| 2947/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -27871,8 +27839,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2948/14932 [04:18<17:29, 11.41it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  20%|▏| 2948/14932 [04:18<17:29, 11.41it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  20%|▏| 2947/14932 [04:14<17:14, 11.59it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -27880,8 +27847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2949/14932 [04:18<17:29, 11.41it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  20%|▏| 2949/14932 [04:18<17:29, 11.41it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  20%|▏| 2948/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  20%|▏| 2948/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -27889,8 +27856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2950/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  20%|▏| 2950/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  20%|▏| 2949/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  20%|▏| 2949/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -27898,8 +27865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2951/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  20%|▏| 2951/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  20%|▏| 2950/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  20%|▏| 2950/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -27907,8 +27874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2952/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  20%|▏| 2952/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  20%|▏| 2951/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  20%|▏| 2951/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -27916,8 +27883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2953/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  20%|▏| 2953/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  20%|▏| 2952/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  20%|▏| 2952/14932 [04:14<17:13, 11.59it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -27925,8 +27892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2954/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  20%|▏| 2954/14932 [04:18<17:29, 11.42it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  20%|▏| 2953/14932 [04:14<17:13, 11.60it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  20%|▏| 2953/14932 [04:14<17:13, 11.60it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -27934,8 +27901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2955/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  20%|▏| 2955/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  20%|▏| 2954/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  20%|▏| 2954/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -27943,8 +27910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2956/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  20%|▏| 2956/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  20%|▏| 2955/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  20%|▏| 2955/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -27952,8 +27919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2957/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  20%|▏| 2957/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  20%|▏| 2956/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  20%|▏| 2956/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -27961,8 +27928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2958/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  20%|▏| 2958/14932 [04:18<17:28, 11.42it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  20%|▏| 2957/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  20%|▏| 2957/14932 [04:14<17:12, 11.60it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -27970,8 +27937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2959/14932 [04:19<17:28, 11.42it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  20%|▏| 2959/14932 [04:19<17:28, 11.42it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  20%|▏| 2958/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  20%|▏| 2958/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -27979,8 +27946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2960/14932 [04:19<17:28, 11.42it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  20%|▏| 2960/14932 [04:19<17:28, 11.42it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  20%|▏| 2959/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  20%|▏| 2959/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -27988,8 +27955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2961/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  20%|▏| 2961/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  20%|▏| 2960/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  20%|▏| 2960/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -27997,8 +27964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2962/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  20%|▏| 2962/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  20%|▏| 2961/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  20%|▏| 2961/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -28006,8 +27973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2963/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  20%|▏| 2963/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  20%|▏| 2962/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  20%|▏| 2962/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -28015,8 +27982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2964/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  20%|▏| 2964/14932 [04:19<17:27, 11.42it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  20%|▏| 2963/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  20%|▏| 2963/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -28024,8 +27991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2965/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  20%|▏| 2965/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  20%|▏| 2964/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  20%|▏| 2964/14932 [04:15<17:12, 11.60it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -28033,8 +28000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2966/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  20%|▏| 2966/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  20%|▏| 2965/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  20%|▏| 2965/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -28042,8 +28009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2967/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  20%|▏| 2967/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  20%|▏| 2966/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  20%|▏| 2966/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -28051,8 +28018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2968/14932 [04:19<17:26, 11.43it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  20%|▏| 2968/14932 [04:19<17:26, 11.43it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  20%|▏| 2967/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  20%|▏| 2967/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -28060,8 +28027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2969/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  20%|▏| 2969/14932 [04:19<17:27, 11.43it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  20%|▏| 2968/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  20%|▏| 2968/14932 [04:15<17:11, 11.60it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -28069,8 +28036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2970/14932 [04:19<17:26, 11.43it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  20%|▏| 2970/14932 [04:19<17:26, 11.43it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  20%|▏| 2969/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  20%|▏| 2969/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -28078,8 +28045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2971/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  20%|▏| 2971/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  20%|▏| 2970/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  20%|▏| 2970/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -28087,8 +28054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2972/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  20%|▏| 2972/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  20%|▏| 2971/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  20%|▏| 2971/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -28096,8 +28063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2973/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  20%|▏| 2973/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  20%|▏| 2972/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  20%|▏| 2972/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -28105,8 +28072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2974/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  20%|▏| 2974/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  20%|▏| 2973/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  20%|▏| 2973/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -28114,8 +28081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2975/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  20%|▏| 2975/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  20%|▏| 2974/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  20%|▏| 2974/14932 [04:16<17:11, 11.60it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -28123,8 +28090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2976/14932 [04:20<17:26, 11.42it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  20%|▏| 2976/14932 [04:20<17:26, 11.42it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  20%|▏| 2975/14932 [04:16<17:10, 11.60it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  20%|▏| 2975/14932 [04:16<17:10, 11.60it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -28132,8 +28099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2977/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  20%|▏| 2977/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  20%|▏| 2976/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  20%|▏| 2976/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -28141,8 +28108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2978/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  20%|▏| 2978/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  20%|▏| 2977/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  20%|▏| 2977/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -28150,8 +28117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2979/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  20%|▏| 2979/14932 [04:20<17:26, 11.43it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  20%|▏| 2978/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  20%|▏| 2978/14932 [04:16<17:11, 11.59it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -28159,8 +28126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2980/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  20%|▏| 2980/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  20%|▏| 2979/14932 [04:16<17:10, 11.59it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  20%|▏| 2979/14932 [04:16<17:10, 11.59it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -28168,8 +28135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2981/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  20%|▏| 2981/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=0.93"
+      "Epoch 0:  20%|▏| 2980/14932 [04:17<17:10, 11.60it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  20%|▏| 2980/14932 [04:17<17:10, 11.60it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -28177,8 +28144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2982/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=0.93\r",
-      "Epoch 0:  20%|▏| 2982/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  20%|▏| 2981/14932 [04:17<17:10, 11.60it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  20%|▏| 2981/14932 [04:17<17:10, 11.60it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -28186,8 +28153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2983/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  20%|▏| 2983/14932 [04:20<17:25, 11.43it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  20%|▏| 2982/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  20%|▏| 2982/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -28195,8 +28162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2984/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  20%|▏| 2984/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  20%|▏| 2983/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  20%|▏| 2983/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -28204,8 +28171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2985/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  20%|▏| 2985/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  20%|▏| 2984/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  20%|▏| 2984/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -28213,8 +28180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2986/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  20%|▏| 2986/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  20%|▏| 2985/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  20%|▏| 2985/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -28222,8 +28189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2987/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  20%|▏| 2987/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  20%|▏| 2986/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  20%|▏| 2986/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -28231,8 +28198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2988/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  20%|▏| 2988/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  20%|▏| 2987/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  20%|▏| 2987/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -28240,8 +28207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2989/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  20%|▏| 2989/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  20%|▏| 2988/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  20%|▏| 2988/14932 [04:17<17:11, 11.58it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -28249,8 +28216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2990/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  20%|��| 2990/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  20%|▏| 2989/14932 [04:18<17:10, 11.58it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  20%|▏| 2989/14932 [04:18<17:10, 11.58it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -28258,8 +28225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2991/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  20%|▏| 2991/14932 [04:21<17:25, 11.42it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  20%|▏| 2990/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  20%|▏| 2990/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -28267,8 +28234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2992/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  20%|▏| 2992/14932 [04:21<17:25, 11.43it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  20%|▏| 2991/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  20%|▏| 2991/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -28276,8 +28243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2993/14932 [04:21<17:24, 11.43it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  20%|▏| 2993/14932 [04:21<17:24, 11.43it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  20%|▏| 2992/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  20%|▏| 2992/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -28285,8 +28252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2994/14932 [04:22<17:24, 11.42it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  20%|▏| 2994/14932 [04:22<17:24, 11.42it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  20%|▏| 2993/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  20%|▏| 2993/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -28294,8 +28261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2995/14932 [04:22<17:24, 11.42it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  20%|▏| 2995/14932 [04:22<17:24, 11.42it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  20%|▏| 2994/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  20%|▏| 2994/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -28303,8 +28270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2996/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  20%|▏| 2996/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  20%|▏| 2995/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  20%|▏| 2995/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -28312,8 +28279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2997/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  20%|▏| 2997/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  20%|▏| 2996/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  20%|▏| 2996/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -28321,8 +28288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2998/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  20%|▏| 2998/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  20%|▏| 2997/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  20%|▏| 2997/14932 [04:18<17:10, 11.59it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -28330,8 +28297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 2999/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  20%|▏| 2999/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  20%|▏| 2998/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  20%|▏| 2998/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -28339,8 +28306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3000/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  20%|▏| 3000/14932 [04:22<17:24, 11.43it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  20%|▏| 2999/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  20%|▏| 2999/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -28348,8 +28315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3001/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  20%|▏| 3001/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  20%|▏| 3000/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  20%|▏| 3000/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -28357,8 +28324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3002/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  20%|▏| 3002/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  20%|▏| 3001/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  20%|▏| 3001/14932 [04:18<17:09, 11.59it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -28366,8 +28333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3003/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  20%|▏| 3003/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  20%|▏| 3002/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  20%|▏| 3002/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -28375,8 +28342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3004/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  20%|▏| 3004/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  20%|▏| 3003/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  20%|▏| 3003/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -28384,8 +28351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3005/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  20%|▏| 3005/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  20%|▏| 3004/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  20%|▏| 3004/14932 [04:19<17:09, 11.59it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -28393,8 +28360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3006/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  20%|▏| 3006/14932 [04:22<17:23, 11.43it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  20%|▏| 3005/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  20%|▏| 3005/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -28402,8 +28369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3007/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  20%|▏| 3007/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  20%|▏| 3006/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  20%|▏| 3006/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -28411,8 +28378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3008/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  20%|▏| 3008/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  20%|▏| 3007/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  20%|▏| 3007/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -28420,8 +28387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3009/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  20%|▏| 3009/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  20%|▏| 3008/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  20%|▏| 3008/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -28429,8 +28396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3010/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  20%|▏| 3010/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  20%|▏| 3009/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  20%|▏| 3009/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.19"
      ]
     },
     {
@@ -28438,8 +28405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3011/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  20%|▏| 3011/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  20%|▏| 3010/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.19\r",
+      "Epoch 0:  20%|▏| 3010/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -28447,8 +28414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3012/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  20%|▏| 3012/14932 [04:23<17:23, 11.43it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  20%|▏| 3011/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  20%|▏| 3011/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -28456,8 +28423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3013/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  20%|▏| 3013/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  20%|▏| 3012/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  20%|▏| 3012/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -28465,8 +28432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3014/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  20%|▏| 3014/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  20%|▏| 3013/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  20%|▏| 3013/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -28474,8 +28441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3015/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  20%|▏| 3015/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  20%|▏| 3014/14932 [04:19<17:07, 11.59it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  20%|▏| 3014/14932 [04:19<17:08, 11.59it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -28483,8 +28450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3016/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  20%|▏| 3016/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  20%|▏| 3015/14932 [04:20<17:08, 11.59it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  20%|▏| 3015/14932 [04:20<17:08, 11.59it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -28492,8 +28459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3017/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  20%|▏| 3017/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  20%|▏| 3016/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  20%|▏| 3016/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -28501,8 +28468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3018/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  20%|▏| 3018/14932 [04:23<17:22, 11.43it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  20%|▏| 3017/14932 [04:20<17:08, 11.59it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  20%|▏| 3017/14932 [04:20<17:08, 11.59it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -28510,8 +28477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3019/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  20%|▏| 3019/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  20%|▏| 3018/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  20%|▏| 3018/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -28519,8 +28486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3020/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  20%|▏| 3020/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  20%|▏| 3019/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  20%|▏| 3019/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -28528,8 +28495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3021/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  20%|▏| 3021/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  20%|▏| 3020/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  20%|▏| 3020/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -28537,8 +28504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3022/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  20%|▏| 3022/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  20%|▏| 3021/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  20%|▏| 3021/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -28546,8 +28513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3023/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  20%|▏| 3023/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  20%|▏| 3022/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  20%|▏| 3022/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -28555,8 +28522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3024/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  20%|▏| 3024/14932 [04:24<17:21, 11.44it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  20%|▏| 3023/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  20%|▏| 3023/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -28564,8 +28531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3025/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  20%|▏| 3025/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  20%|▏| 3024/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  20%|▏| 3024/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -28573,8 +28540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3026/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  20%|▏| 3026/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  20%|▏| 3025/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  20%|▏| 3025/14932 [04:20<17:07, 11.59it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -28582,8 +28549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3027/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  20%|▏| 3027/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  20%|▏| 3026/14932 [04:21<17:08, 11.58it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  20%|▏| 3026/14932 [04:21<17:08, 11.58it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -28591,8 +28558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3028/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  20%|▏| 3028/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  20%|▏| 3027/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  20%|▏| 3027/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -28600,8 +28567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3029/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  20%|▏| 3029/14932 [04:24<17:21, 11.43it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  20%|▏| 3028/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  20%|▏| 3028/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -28609,8 +28576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3030/14932 [04:25<17:21, 11.43it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  20%|▏| 3030/14932 [04:25<17:21, 11.43it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  20%|▏| 3029/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  20%|▏| 3029/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -28618,8 +28585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3031/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  20%|▏| 3031/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  20%|▏| 3030/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  20%|▏| 3030/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -28627,8 +28594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3032/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  20%|▏| 3032/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  20%|▏| 3031/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  20%|▏| 3031/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -28636,8 +28603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3033/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  20%|▏| 3033/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  20%|▏| 3032/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  20%|▏| 3032/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -28645,8 +28612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3034/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  20%|▏| 3034/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  20%|▏| 3033/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  20%|▏| 3033/14932 [04:21<17:07, 11.58it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -28654,8 +28621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3035/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  20%|▏| 3035/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  20%|▏| 3034/14932 [04:21<17:06, 11.59it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  20%|▏| 3034/14932 [04:21<17:06, 11.59it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -28663,8 +28630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3036/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  20%|▏| 3036/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  20%|▏| 3035/14932 [04:22<17:07, 11.58it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  20%|▏| 3035/14932 [04:22<17:07, 11.58it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -28672,8 +28639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3037/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  20%|▏| 3037/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  20%|▏| 3036/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  20%|▏| 3036/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -28681,8 +28648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3038/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  20%|▏| 3038/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  20%|▏| 3037/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  20%|▏| 3037/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -28690,8 +28657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3039/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  20%|▏| 3039/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  20%|▏| 3038/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  20%|▏| 3038/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -28699,8 +28666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3040/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  20%|▏| 3040/14932 [04:25<17:20, 11.43it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  20%|▏| 3039/14932 [04:22<17:06, 11.59it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  20%|▏| 3039/14932 [04:22<17:06, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -28708,8 +28675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3041/14932 [04:26<17:20, 11.43it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  20%|▏| 3041/14932 [04:26<17:20, 11.43it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  20%|▏| 3040/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  20%|▏| 3040/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -28717,8 +28684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3042/14932 [04:26<17:20, 11.43it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  20%|▏| 3042/14932 [04:26<17:20, 11.43it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  20%|▏| 3041/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  20%|▏| 3041/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -28726,8 +28693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3043/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  20%|▏| 3043/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  20%|▏| 3042/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  20%|▏| 3042/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -28735,8 +28702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3044/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  20%|▏| 3044/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  20%|▏| 3043/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  20%|▏| 3043/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -28744,8 +28711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3045/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  20%|▏| 3045/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  20%|▏| 3044/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  20%|▏| 3044/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -28753,8 +28720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3046/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  20%|▏| 3046/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  20%|▏| 3045/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  20%|▏| 3045/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -28762,8 +28729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3047/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  20%|▏| 3047/14932 [04:26<17:19, 11.43it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  20%|▏| 3046/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  20%|▏| 3046/14932 [04:22<17:06, 11.58it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -28771,8 +28738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3048/14932 [04:26<17:19, 11.44it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  20%|▏| 3048/14932 [04:26<17:19, 11.44it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  20%|▏| 3047/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  20%|▏| 3047/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -28780,8 +28747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3049/14932 [04:26<17:19, 11.44it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  20%|▏| 3049/14932 [04:26<17:19, 11.44it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  20%|▏| 3048/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  20%|▏| 3048/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -28789,8 +28756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3050/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  20%|▏| 3050/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  20%|▏| 3049/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  20%|▏| 3049/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -28798,8 +28765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3051/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  20%|▏| 3051/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  20%|▏| 3050/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  20%|▏| 3050/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -28807,8 +28774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3052/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  20%|▏| 3052/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  20%|▏| 3051/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  20%|▏| 3051/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -28816,8 +28783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3053/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  20%|▏| 3053/14932 [04:26<17:18, 11.44it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  20%|▏| 3052/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  20%|▏| 3052/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -28825,8 +28792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3054/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  20%|▏| 3054/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  20%|▏| 3053/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  20%|▏| 3053/14932 [04:23<17:05, 11.59it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -28834,8 +28801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3055/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  20%|▏| 3055/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  20%|▏| 3054/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  20%|▏| 3054/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -28843,8 +28810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3056/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  20%|▏| 3056/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  20%|▏| 3055/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  20%|▏| 3055/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -28852,8 +28819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3057/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  20%|▏| 3057/14932 [04:27<17:18, 11.44it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  20%|▏| 3056/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  20%|▏| 3056/14932 [04:23<17:04, 11.59it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -28861,8 +28828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3058/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  20%|▏| 3058/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  20%|▏| 3057/14932 [04:23<17:05, 11.58it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  20%|▏| 3057/14932 [04:23<17:05, 11.58it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -28870,8 +28837,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3059/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  20%|▏| 3059/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  20%|▏| 3058/14932 [04:23<17:05, 11.58it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -28879,8 +28845,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3060/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  20%|▏| 3060/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  20%|▏| 3058/14932 [04:23<17:05, 11.58it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -28888,8 +28853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  20%|▏| 3061/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  20%|▏| 3061/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  20%|▏| 3059/14932 [04:24<17:04, 11.58it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  20%|▏| 3059/14932 [04:24<17:04, 11.58it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -28897,8 +28862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3062/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  21%|▏| 3062/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  20%|▏| 3060/14932 [04:24<17:04, 11.58it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  20%|▏| 3060/14932 [04:24<17:04, 11.58it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -28906,8 +28871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3063/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  21%|▏| 3063/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  20%|▏| 3061/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  20%|▏| 3061/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -28915,8 +28880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3064/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  21%|▏| 3064/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  21%|▏| 3062/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  21%|▏| 3062/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -28924,8 +28889,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3065/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  21%|▏| 3065/14932 [04:27<17:17, 11.44it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  21%|▏| 3063/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -28933,8 +28897,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3066/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  21%|▏| 3066/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  21%|▏| 3063/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -28942,8 +28905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3067/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  21%|▏| 3067/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  21%|▏| 3064/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  21%|▏| 3064/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -28951,8 +28914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3068/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  21%|▏| 3068/14932 [04:28<17:17, 11.44it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  21%|▏| 3065/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  21%|▏| 3065/14932 [04:24<17:04, 11.59it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -28960,8 +28923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3069/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  21%|▏| 3069/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  21%|▏| 3066/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  21%|▏| 3066/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -28969,8 +28932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3070/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  21%|▏| 3070/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  21%|▏| 3067/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  21%|▏| 3067/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -28978,8 +28941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3071/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  21%|▏| 3071/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=5.34"
+      "Epoch 0:  21%|▏| 3068/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  21%|▏| 3068/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -28987,8 +28950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3072/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=5.34\r",
-      "Epoch 0:  21%|▏| 3072/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  21%|▏| 3069/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  21%|▏| 3069/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -28996,8 +28959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3073/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  21%|▏| 3073/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  21%|▏| 3070/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  21%|▏| 3070/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -29005,8 +28968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3074/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  21%|▏| 3074/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  21%|▏| 3071/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  21%|▏| 3071/14932 [04:24<17:03, 11.59it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -29014,8 +28977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3075/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  21%|▏| 3075/14932 [04:28<17:16, 11.44it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  21%|▏| 3072/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  21%|▏| 3072/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -29023,8 +28986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3076/14932 [04:29<17:16, 11.43it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  21%|▏| 3076/14932 [04:29<17:16, 11.43it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  21%|▏| 3073/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  21%|▏| 3073/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -29032,8 +28995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3077/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  21%|▏| 3077/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  21%|▏| 3074/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  21%|▏| 3074/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -29041,8 +29004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3078/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  21%|▏| 3078/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  21%|▏| 3075/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  21%|▏| 3075/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -29050,8 +29013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3079/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  21%|▏| 3079/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  21%|▏| 3076/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  21%|▏| 3076/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -29059,8 +29022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3080/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  21%|▏| 3080/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  21%|▏| 3077/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  21%|▏| 3077/14932 [04:25<17:03, 11.59it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -29068,8 +29031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3081/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  21%|▏| 3081/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  21%|▏| 3078/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  21%|▏| 3078/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -29077,8 +29040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3082/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  21%|▏| 3082/14932 [04:29<17:16, 11.44it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  21%|▏| 3079/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  21%|▏| 3079/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -29086,8 +29049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3083/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  21%|▏| 3083/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  21%|▏| 3080/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  21%|▏| 3080/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -29095,8 +29058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3084/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  21%|▏| 3084/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  21%|▏| 3081/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  21%|▏| 3081/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -29104,8 +29067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3085/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  21%|▏| 3085/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  21%|▏| 3082/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  21%|▏| 3082/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -29113,8 +29076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3086/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  21%|▏| 3086/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  21%|▏| 3083/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  21%|▏| 3083/14932 [04:25<17:02, 11.59it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -29122,8 +29085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3087/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  21%|▏| 3087/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  21%|▏| 3084/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  21%|▏| 3084/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -29131,8 +29094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3088/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  21%|▏| 3088/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  21%|▏| 3085/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  21%|▏| 3085/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -29140,8 +29103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3089/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  21%|▏| 3089/14932 [04:29<17:15, 11.44it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  21%|▏| 3086/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  21%|▏| 3086/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -29149,8 +29112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3090/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  21%|▏| 3090/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  21%|▏| 3087/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  21%|▏| 3087/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -29158,8 +29121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3091/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  21%|▏| 3091/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  21%|▏| 3088/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  21%|▏| 3088/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -29167,8 +29130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3092/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  21%|▏| 3092/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  21%|▏| 3089/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  21%|▏| 3089/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -29176,8 +29139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3093/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  21%|▏| 3093/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  21%|▏| 3090/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  21%|▏| 3090/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -29185,8 +29148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3094/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  21%|▏| 3094/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  21%|▏| 3091/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  21%|▏| 3091/14932 [04:26<17:01, 11.59it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -29194,8 +29157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3095/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  21%|▏| 3095/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  21%|▏| 3092/14932 [04:26<17:01, 11.60it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  21%|▏| 3092/14932 [04:26<17:01, 11.60it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -29203,8 +29166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3096/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  21%|▏| 3096/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  21%|▏| 3093/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  21%|▏| 3093/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -29212,8 +29175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3097/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  21%|▏| 3097/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  21%|▏| 3094/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  21%|▏| 3094/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -29221,8 +29184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3098/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  21%|▏| 3098/14932 [04:30<17:14, 11.44it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  21%|▏| 3095/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  21%|▏| 3095/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -29230,8 +29193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3099/14932 [04:30<17:13, 11.44it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  21%|▏| 3099/14932 [04:30<17:13, 11.44it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  21%|▏| 3096/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  21%|▏| 3096/14932 [04:26<17:00, 11.60it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -29239,8 +29202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3100/14932 [04:30<17:13, 11.44it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  21%|▏| 3100/14932 [04:30<17:13, 11.44it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  21%|▏| 3097/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  21%|▏| 3097/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -29248,8 +29211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3101/14932 [04:30<17:13, 11.45it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  21%|▏| 3101/14932 [04:30<17:13, 11.45it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  21%|▏| 3098/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  21%|▏| 3098/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -29257,8 +29220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3102/14932 [04:31<17:13, 11.45it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  21%|▏| 3102/14932 [04:31<17:13, 11.45it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  21%|▏| 3099/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  21%|▏| 3099/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -29266,8 +29229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3103/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  21%|▏| 3103/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  21%|▏| 3100/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  21%|▏| 3100/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -29275,8 +29238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3104/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  21%|▏| 3104/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  21%|▏| 3101/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  21%|▏| 3101/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -29284,8 +29247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3105/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  21%|▏| 3105/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  21%|▏| 3102/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  21%|▏| 3102/14932 [04:27<17:00, 11.60it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -29293,8 +29256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3106/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  21%|▏| 3106/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  21%|▏| 3103/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  21%|▏| 3103/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -29302,8 +29265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3107/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  21%|▏| 3107/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  21%|▏| 3104/14932 [04:27<17:00, 11.59it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  21%|▏| 3104/14932 [04:27<17:00, 11.59it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -29311,8 +29274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3108/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  21%|▏| 3108/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  21%|▏| 3105/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  21%|▏| 3105/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -29320,8 +29283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3109/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  21%|▏| 3109/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=1.50"
+      "Epoch 0:  21%|▏| 3106/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  21%|▏| 3106/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -29329,8 +29292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3110/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=1.50\r",
-      "Epoch 0:  21%|▏| 3110/14932 [04:31<17:13, 11.44it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  21%|▏| 3107/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  21%|▏| 3107/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -29338,8 +29301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3111/14932 [04:31<17:12, 11.44it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  21%|▏| 3111/14932 [04:31<17:12, 11.44it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  21%|▏| 3108/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  21%|▏| 3108/14932 [04:27<16:59, 11.60it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -29347,8 +29310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3112/14932 [04:31<17:12, 11.44it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  21%|▏| 3112/14932 [04:31<17:12, 11.44it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  21%|▏| 3109/14932 [04:28<16:59, 11.59it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  21%|▏| 3109/14932 [04:28<16:59, 11.59it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -29356,8 +29319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3113/14932 [04:31<17:12, 11.45it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  21%|▏| 3113/14932 [04:31<17:12, 11.45it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  21%|▏| 3110/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  21%|▏| 3110/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -29365,8 +29328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3114/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  21%|▏| 3114/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  21%|▏| 3111/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  21%|▏| 3111/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -29374,8 +29337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3115/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  21%|▏| 3115/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  21%|▏| 3112/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  21%|▏| 3112/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -29383,8 +29346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3116/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  21%|▏| 3116/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  21%|▏| 3113/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  21%|▏| 3113/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -29392,8 +29355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3117/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  21%|▏| 3117/14932 [04:32<17:12, 11.45it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  21%|▏| 3114/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  21%|▏| 3114/14932 [04:28<16:59, 11.60it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -29401,8 +29364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3118/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  21%|▏| 3118/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  21%|▏| 3115/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  21%|▏| 3115/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -29410,8 +29373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3119/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  21%|▏| 3119/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  21%|▏| 3116/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  21%|▏| 3116/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -29419,8 +29382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3120/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  21%|▏| 3120/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  21%|▏| 3117/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  21%|▏| 3117/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -29428,8 +29391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3121/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  21%|▏| 3121/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:  21%|▏| 3118/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  21%|▏| 3118/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -29437,8 +29400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3122/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:  21%|▏| 3122/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  21%|▏| 3119/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  21%|▏| 3119/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -29446,8 +29409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3123/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  21%|▏| 3123/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  21%|▏| 3120/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  21%|▏| 3120/14932 [04:28<16:58, 11.60it/s, v_num=ui8w, train/loss=1.40"
      ]
     },
     {
@@ -29455,8 +29418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3124/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  21%|▏| 3124/14932 [04:32<17:11, 11.45it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  21%|▏| 3121/14932 [04:29<16:58, 11.60it/s, v_num=ui8w, train/loss=1.40\r",
+      "Epoch 0:  21%|▏| 3121/14932 [04:29<16:58, 11.60it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -29464,8 +29427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3125/14932 [04:32<17:10, 11.45it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  21%|▏| 3125/14932 [04:32<17:10, 11.45it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  21%|▏| 3122/14932 [04:29<16:58, 11.60it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  21%|▏| 3122/14932 [04:29<16:58, 11.60it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -29473,8 +29436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3126/14932 [04:32<17:10, 11.45it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  21%|▏| 3126/14932 [04:32<17:10, 11.45it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  21%|▏| 3123/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  21%|▏| 3123/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -29482,8 +29445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3127/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  21%|▏| 3127/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  21%|▏| 3124/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  21%|▏| 3124/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -29491,8 +29454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3128/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  21%|▏| 3128/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  21%|▏| 3125/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  21%|▏| 3125/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -29500,8 +29463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3129/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  21%|▏| 3129/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  21%|▏| 3126/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  21%|▏| 3126/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -29509,8 +29472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3130/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  21%|▏| 3130/14932 [04:33<17:10, 11.45it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  21%|▏| 3127/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  21%|▏| 3127/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -29518,8 +29481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3131/14932 [04:33<17:10, 11.46it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  21%|▏| 3131/14932 [04:33<17:10, 11.46it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  21%|▏| 3128/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  21%|▏| 3128/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -29527,8 +29490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3132/14932 [04:33<17:10, 11.46it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  21%|▏| 3132/14932 [04:33<17:10, 11.46it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  21%|▏| 3129/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  21%|▏| 3129/14932 [04:29<16:57, 11.60it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -29536,8 +29499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3133/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  21%|▏| 3133/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  21%|▏| 3130/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  21%|▏| 3130/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -29545,8 +29508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3134/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  21%|▏| 3134/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  21%|▏| 3131/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  21%|▏| 3131/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -29554,8 +29517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3135/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  21%|▏| 3135/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  21%|▏| 3132/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  21%|▏| 3132/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -29563,8 +29526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3136/14932 [04:33<17:09, 11.45it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  21%|▏| 3136/14932 [04:33<17:09, 11.45it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  21%|▏| 3133/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  21%|▏| 3133/14932 [04:29<16:56, 11.61it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -29572,8 +29535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3137/14932 [04:33<17:09, 11.45it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  21%|▏| 3137/14932 [04:33<17:09, 11.45it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  21%|▏| 3134/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  21%|▏| 3134/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -29581,8 +29544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3138/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  21%|▏| 3138/14932 [04:33<17:09, 11.46it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  21%|▏| 3135/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  21%|▏| 3135/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -29590,8 +29553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3139/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  21%|▏| 3139/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  21%|▏| 3136/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  21%|▏| 3136/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -29599,8 +29562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3140/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  21%|▏| 3140/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  21%|▏| 3137/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  21%|▏| 3137/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -29608,8 +29571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3141/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  21%|▏| 3141/14932 [04:34<17:09, 11.46it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  21%|▏| 3138/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  21%|▏| 3138/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -29617,8 +29580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3142/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  21%|▏| 3142/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  21%|▏| 3139/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  21%|▏| 3139/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=1.15"
      ]
     },
     {
@@ -29626,8 +29589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3143/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  21%|▏| 3143/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  21%|▏| 3140/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=1.15\r",
+      "Epoch 0:  21%|▏| 3140/14932 [04:30<16:56, 11.61it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -29635,8 +29598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3144/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  21%|▏| 3144/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  21%|▏| 3141/14932 [04:30<16:55, 11.61it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  21%|▏| 3141/14932 [04:30<16:55, 11.61it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -29644,8 +29607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3145/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  21%|▏| 3145/14932 [04:34<17:09, 11.45it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  21%|▏| 3142/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  21%|▏| 3142/14932 [04:30<16:56, 11.60it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -29653,8 +29616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3146/14932 [04:34<17:08, 11.45it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  21%|▏| 3146/14932 [04:34<17:08, 11.45it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  21%|▏| 3143/14932 [04:30<16:55, 11.60it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  21%|▏| 3143/14932 [04:30<16:55, 11.60it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -29662,8 +29625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3147/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  21%|▏| 3147/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  21%|▏| 3144/14932 [04:30<16:55, 11.60it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  21%|▏| 3144/14932 [04:30<16:55, 11.60it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -29671,8 +29634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3148/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  21%|▏| 3148/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  21%|▏| 3145/14932 [04:30<16:55, 11.61it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  21%|▏| 3145/14932 [04:30<16:55, 11.61it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -29680,8 +29643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3149/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  21%|▏| 3149/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  21%|▏| 3146/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  21%|▏| 3146/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -29689,8 +29652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3150/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  21%|▏| 3150/14932 [04:34<17:08, 11.46it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  21%|▏| 3147/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  21%|▏| 3147/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -29698,8 +29661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3151/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  21%|▏| 3151/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  21%|▏| 3148/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  21%|▏| 3148/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -29707,8 +29670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3152/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  21%|▏| 3152/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  21%|▏| 3149/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  21%|▏| 3149/14932 [04:31<16:55, 11.61it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -29716,8 +29679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3153/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  21%|▏| 3153/14932 [04:35<17:08, 11.46it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  21%|▏| 3150/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  21%|▏| 3150/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -29725,8 +29688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3154/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  21%|▏| 3154/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  21%|▏| 3151/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  21%|▏| 3151/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -29734,8 +29697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3155/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  21%|▏| 3155/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  21%|▏| 3152/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  21%|▏| 3152/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -29743,8 +29706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3156/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  21%|▏| 3156/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  21%|▏| 3153/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  21%|▏| 3153/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -29752,8 +29715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3157/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  21%|▏| 3157/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  21%|▏| 3154/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  21%|▏| 3154/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -29761,8 +29724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3158/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  21%|▏| 3158/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  21%|▏| 3155/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  21%|▏| 3155/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -29770,8 +29733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3159/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  21%|▏| 3159/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  21%|▏| 3156/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  21%|▏| 3156/14932 [04:31<16:54, 11.61it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -29779,8 +29742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3160/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  21%|▏| 3160/14932 [04:35<17:07, 11.46it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  21%|▏| 3157/14932 [04:31<16:53, 11.61it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  21%|▏| 3157/14932 [04:31<16:53, 11.61it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -29788,8 +29751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3161/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  21%|▏| 3161/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  21%|▏| 3158/14932 [04:31<16:53, 11.61it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  21%|▏| 3158/14932 [04:31<16:53, 11.61it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -29797,8 +29760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3162/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  21%|▏| 3162/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=5.12"
+      "Epoch 0:  21%|▏| 3159/14932 [04:32<16:53, 11.61it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  21%|▏| 3159/14932 [04:32<16:53, 11.61it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -29806,8 +29769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3163/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=5.12\r",
-      "Epoch 0:  21%|▏| 3163/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  21%|▏| 3160/14932 [04:32<16:53, 11.61it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  21%|▏| 3160/14932 [04:32<16:53, 11.61it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -29815,8 +29778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3164/14932 [04:35<17:06, 11.46it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  21%|▏| 3164/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  21%|▏| 3161/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  21%|▏| 3161/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -29824,8 +29787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3165/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  21%|▏| 3165/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  21%|▏| 3162/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  21%|▏| 3162/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -29833,8 +29796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3166/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  21%|▏| 3166/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  21%|▏| 3163/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  21%|▏| 3163/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -29842,8 +29805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3167/14932 [04:36<17:06, 11.47it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  21%|▏| 3167/14932 [04:36<17:06, 11.47it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  21%|▏| 3164/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  21%|▏| 3164/14932 [04:32<16:53, 11.62it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -29851,8 +29814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3168/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  21%|▏| 3168/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  21%|▏| 3165/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  21%|▏| 3165/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -29860,8 +29823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3169/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  21%|▏| 3169/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  21%|▏| 3166/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  21%|▏| 3166/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -29869,8 +29832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3170/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  21%|▏| 3170/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  21%|▏| 3167/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  21%|▏| 3167/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -29878,7 +29841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3171/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  21%|▏| 3168/14932 [04:32<16:52, 11.61it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  21%|▏| 3168/14932 [04:32<16:52, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -29886,7 +29850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3171/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  21%|▏| 3169/14932 [04:32<16:52, 11.61it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  21%|▏| 3169/14932 [04:32<16:52, 11.61it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -29894,8 +29859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3172/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  21%|▏| 3172/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  21%|▏| 3170/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  21%|▏| 3170/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -29903,8 +29868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3173/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  21%|▏| 3173/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  21%|▏| 3171/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  21%|▏| 3171/14932 [04:32<16:52, 11.62it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -29912,8 +29877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3174/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  21%|▏| 3174/14932 [04:36<17:06, 11.46it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  21%|▏| 3172/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  21%|▏| 3172/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -29921,8 +29886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3175/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  21%|▏| 3175/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  21%|▏| 3173/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  21%|▏| 3173/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -29930,8 +29895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3176/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  21%|▏| 3176/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  21%|▏| 3174/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  21%|▏| 3174/14932 [04:33<16:52, 11.62it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -29939,8 +29904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3177/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  21%|▏| 3177/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  21%|▏| 3175/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  21%|▏| 3175/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -29948,8 +29913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3178/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  21%|▏| 3178/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  21%|▏| 3176/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  21%|▏| 3176/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -29957,8 +29922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3179/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  21%|▏| 3179/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  21%|▏| 3177/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  21%|▏| 3177/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -29966,8 +29931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3180/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  21%|▏| 3180/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  21%|▏| 3178/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  21%|▏| 3178/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -29975,8 +29940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3181/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  21%|▏| 3181/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  21%|▏| 3179/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  21%|▏| 3179/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -29984,8 +29949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3182/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  21%|▏| 3182/14932 [04:37<17:05, 11.46it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  21%|▏| 3180/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  21%|▏| 3180/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -29993,8 +29958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3183/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  21%|▏| 3183/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  21%|▏| 3181/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  21%|▏| 3181/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=5.09"
      ]
     },
     {
@@ -30002,8 +29967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3184/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  21%|▏| 3184/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  21%|▏| 3182/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=5.09\r",
+      "Epoch 0:  21%|▏| 3182/14932 [04:33<16:51, 11.62it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -30011,8 +29976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3185/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  21%|▏| 3185/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  21%|▏| 3183/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  21%|▏| 3183/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -30020,8 +29985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3186/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  21%|▏| 3186/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  21%|▏| 3184/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  21%|▏| 3184/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -30029,7 +29994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3187/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  21%|▏| 3185/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  21%|▏| 3185/14932 [04:33<16:50, 11.62it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -30037,7 +30003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3187/14932 [04:37<17:04, 11.46it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  21%|▏| 3186/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  21%|▏| 3186/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -30045,8 +30012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3188/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  21%|▏| 3188/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  21%|▏| 3187/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  21%|▏| 3187/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -30054,8 +30021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3189/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  21%|▏| 3189/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  21%|▏| 3188/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  21%|▏| 3188/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -30063,8 +30030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3190/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  21%|▏| 3190/14932 [04:38<17:04, 11.47it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  21%|▏| 3189/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  21%|▏| 3189/14932 [04:34<16:50, 11.63it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -30072,8 +30039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3191/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  21%|▏| 3191/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  21%|▏| 3190/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  21%|▏| 3190/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -30081,8 +30048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3192/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  21%|▏| 3192/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  21%|▏| 3191/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  21%|▏| 3191/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -30090,8 +30057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3193/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  21%|▏| 3193/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  21%|▏| 3192/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  21%|▏| 3192/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -30099,8 +30066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3194/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  21%|▏| 3194/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  21%|▏| 3193/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  21%|▏| 3193/14932 [04:34<16:49, 11.63it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -30108,8 +30075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3195/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  21%|▏| 3195/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  21%|▏| 3194/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  21%|▏| 3194/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -30117,8 +30084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3196/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  21%|▏| 3196/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  21%|▏| 3195/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  21%|▏| 3195/14932 [04:34<16:50, 11.62it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -30126,8 +30093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3197/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  21%|▏| 3197/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  21%|▏| 3196/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  21%|▏| 3196/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -30135,8 +30102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3198/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  21%|▏| 3198/14932 [04:38<17:03, 11.47it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  21%|▏| 3197/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  21%|▏| 3197/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -30144,8 +30111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3199/14932 [04:38<17:02, 11.47it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  21%|▏| 3199/14932 [04:38<17:02, 11.47it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  21%|▏| 3198/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  21%|▏| 3198/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -30153,8 +30120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3200/14932 [04:39<17:03, 11.47it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  21%|▏| 3200/14932 [04:39<17:03, 11.47it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  21%|▏| 3199/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  21%|▏| 3199/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -30162,8 +30129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3201/14932 [04:39<17:03, 11.47it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  21%|▏| 3201/14932 [04:39<17:03, 11.47it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  21%|▏| 3200/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  21%|▏| 3200/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -30171,8 +30138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3202/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  21%|▏| 3202/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  21%|▏| 3201/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  21%|▏| 3201/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -30180,8 +30147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3203/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  21%|▏| 3203/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  21%|▏| 3202/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  21%|▏| 3202/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -30189,8 +30156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3204/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  21%|▏| 3204/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  21%|▏| 3203/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  21%|▏| 3203/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -30198,8 +30165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3205/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  21%|▏| 3205/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  21%|▏| 3204/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  21%|▏| 3204/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -30207,8 +30174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3206/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  21%|▏| 3206/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  21%|▏| 3205/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  21%|▏| 3205/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -30216,8 +30183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3207/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  21%|▏| 3207/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  21%|▏| 3206/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  21%|▏| 3206/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -30225,8 +30192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3208/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  21%|▏| 3208/14932 [04:39<17:02, 11.47it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  21%|▏| 3207/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  21%|▏| 3207/14932 [04:35<16:49, 11.62it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -30234,8 +30201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3209/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  21%|▏| 3209/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  21%|▏| 3208/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  21%|▏| 3208/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -30243,8 +30210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  21%|▏| 3210/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  21%|▏| 3210/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  21%|▏| 3209/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  21%|▏| 3209/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -30252,8 +30219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3211/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  22%|▏| 3211/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:  21%|▏| 3210/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  21%|▏| 3210/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -30261,8 +30228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3212/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:  22%|▏| 3212/14932 [04:39<17:01, 11.47it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  22%|▏| 3211/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  22%|▏| 3211/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -30270,8 +30237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3213/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  22%|▏| 3213/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  22%|▏| 3212/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  22%|▏| 3212/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -30279,8 +30246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3214/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  22%|▏| 3214/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  22%|▏| 3213/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  22%|▏| 3213/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -30288,8 +30255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3215/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  22%|▏| 3215/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  22%|▏| 3214/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  22%|▏| 3214/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -30297,8 +30264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3216/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  22%|▏| 3216/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  22%|▏| 3215/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  22%|▏| 3215/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -30306,8 +30273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3217/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  22%|▏| 3217/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  22%|▏| 3216/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  22%|▏| 3216/14932 [04:36<16:48, 11.62it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -30315,8 +30282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3218/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  22%|▏| 3218/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  22%|▏| 3217/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  22%|▏| 3217/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -30324,8 +30291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3219/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  22%|▏| 3219/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  22%|▏| 3218/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  22%|▏| 3218/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -30333,8 +30300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3220/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  22%|▏| 3220/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  22%|▏| 3219/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  22%|▏| 3219/14932 [04:36<16:47, 11.62it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -30342,8 +30309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3221/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  22%|▏| 3221/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  22%|▏| 3220/14932 [04:37<16:47, 11.62it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  22%|▏| 3220/14932 [04:37<16:47, 11.62it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -30351,8 +30318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3222/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  22%|▏| 3222/14932 [04:40<17:01, 11.47it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  22%|▏| 3221/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  22%|▏| 3221/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -30360,8 +30327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3223/14932 [04:41<17:01, 11.47it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  22%|▏| 3223/14932 [04:41<17:01, 11.47it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  22%|▏| 3222/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  22%|▏| 3222/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -30369,8 +30336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3224/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  22%|▏| 3224/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  22%|▏| 3223/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  22%|▏| 3223/14932 [04:37<16:47, 11.63it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -30378,8 +30345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3225/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  22%|▏| 3225/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  22%|▏| 3224/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  22%|▏| 3224/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -30387,8 +30354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3226/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  22%|▏| 3226/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  22%|▏| 3225/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  22%|▏| 3225/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -30396,8 +30363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3227/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  22%|▏| 3227/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  22%|▏| 3226/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  22%|▏| 3226/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -30405,8 +30372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3228/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  22%|▏| 3228/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  22%|▏| 3227/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  22%|▏| 3227/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -30414,8 +30381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3229/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  22%|▏| 3229/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  22%|▏| 3228/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  22%|▏| 3228/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -30423,8 +30390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3230/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  22%|▏| 3230/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  22%|▏| 3229/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  22%|▏| 3229/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -30432,8 +30399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3231/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  22%|▏| 3231/14932 [04:41<17:00, 11.47it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  22%|▏| 3230/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  22%|▏| 3230/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -30441,8 +30408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3232/14932 [04:41<17:00, 11.46it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  22%|▏| 3232/14932 [04:41<17:00, 11.46it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  22%|▏| 3231/14932 [04:37<16:45, 11.63it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  22%|▏| 3231/14932 [04:37<16:45, 11.63it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -30450,8 +30417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3233/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  22%|▏| 3233/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  22%|▏| 3232/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  22%|▏| 3232/14932 [04:37<16:46, 11.63it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -30459,8 +30426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3234/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  22%|▏| 3234/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  22%|▏| 3233/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  22%|▏| 3233/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -30468,8 +30435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3235/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  22%|▏| 3235/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  22%|▏| 3234/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  22%|▏| 3234/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -30477,8 +30444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3236/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  22%|▏| 3236/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  22%|▏| 3235/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  22%|▏| 3235/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -30486,8 +30453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3237/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  22%|▏| 3237/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  22%|▏| 3236/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  22%|▏| 3236/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -30495,8 +30462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3238/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  22%|▏| 3238/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  22%|▏| 3237/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  22%|▏| 3237/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -30504,8 +30471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3239/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  22%|▏| 3239/14932 [04:42<17:00, 11.46it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  22%|▏| 3238/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  22%|▏| 3238/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -30513,8 +30480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3240/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  22%|▏| 3240/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  22%|▏| 3239/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  22%|▏| 3239/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -30522,8 +30489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3241/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  22%|▏| 3241/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  22%|▏| 3240/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  22%|▏| 3240/14932 [04:38<16:46, 11.62it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -30531,8 +30498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3242/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  22%|▏| 3242/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  22%|▏| 3241/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  22%|▏| 3241/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -30540,8 +30507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3243/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  22%|▏| 3243/14932 [04:42<16:59, 11.46it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  22%|▏| 3242/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  22%|▏| 3242/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -30549,8 +30516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3244/14932 [04:42<16:59, 11.47it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  22%|▏| 3244/14932 [04:42<16:59, 11.47it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  22%|▏| 3243/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  22%|▏| 3243/14932 [04:38<16:45, 11.62it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -30558,8 +30525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3245/14932 [04:43<16:59, 11.47it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  22%|▏| 3245/14932 [04:43<16:59, 11.47it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  22%|▏| 3244/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  22%|▏| 3244/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -30567,8 +30534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3246/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  22%|▏| 3246/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  22%|▏| 3245/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  22%|▏| 3245/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -30576,8 +30543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3247/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  22%|▏| 3247/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  22%|▏| 3246/14932 [04:39<16:45, 11.63it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  22%|▏| 3246/14932 [04:39<16:45, 11.63it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -30585,8 +30552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3248/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  22%|▏| 3248/14932 [04:43<16:59, 11.46it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  22%|▏| 3247/14932 [04:39<16:45, 11.63it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  22%|▏| 3247/14932 [04:39<16:45, 11.63it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -30594,8 +30561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3249/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  22%|▏| 3249/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  22%|▏| 3248/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  22%|▏| 3248/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -30603,8 +30570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3250/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  22%|▏| 3250/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  22%|▏| 3249/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  22%|▏| 3249/14932 [04:39<16:45, 11.62it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -30612,8 +30579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3251/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  22%|▏| 3251/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  22%|▏| 3250/14932 [04:39<16:44, 11.62it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  22%|▏| 3250/14932 [04:39<16:44, 11.62it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -30621,8 +30588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3252/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  22%|▏| 3252/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  22%|▏| 3251/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  22%|▏| 3251/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -30630,8 +30597,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3253/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  22%|▏| 3253/14932 [04:43<16:58, 11.46it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  22%|▏| 3252/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -30639,8 +30605,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3254/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  22%|▏| 3254/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  22%|▏| 3252/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -30648,8 +30613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3255/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  22%|▏| 3255/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  22%|▏| 3253/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  22%|▏| 3253/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -30657,8 +30622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3256/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  22%|▏| 3256/14932 [04:43<16:58, 11.47it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  22%|▏| 3254/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  22%|▏| 3254/14932 [04:39<16:44, 11.63it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -30666,8 +30631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3257/14932 [04:44<16:58, 11.47it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  22%|▏| 3257/14932 [04:44<16:58, 11.47it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  22%|▏| 3255/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  22%|▏| 3255/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -30675,8 +30640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3258/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  22%|▏| 3258/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  22%|▏| 3256/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  22%|▏| 3256/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -30684,8 +30649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3259/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  22%|▏| 3259/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  22%|▏| 3257/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  22%|▏| 3257/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -30693,8 +30658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3260/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  22%|▏| 3260/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  22%|▏| 3258/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  22%|▏| 3258/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -30702,8 +30667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3261/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  22%|▏| 3261/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  22%|▏| 3259/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  22%|▏| 3259/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -30711,8 +30676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3262/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  22%|▏| 3262/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  22%|▏| 3260/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  22%|▏| 3260/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -30720,8 +30685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3263/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  22%|▏| 3263/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  22%|▏| 3261/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  22%|▏| 3261/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -30729,8 +30694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3264/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  22%|▏| 3264/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  22%|▏| 3262/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  22%|▏| 3262/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -30738,8 +30703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3265/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  22%|▏| 3265/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  22%|▏| 3263/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  22%|▏| 3263/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -30747,8 +30712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3266/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  22%|▏| 3266/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  22%|▏| 3264/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  22%|▏| 3264/14932 [04:40<16:44, 11.62it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -30756,8 +30721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3267/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  22%|▏| 3267/14932 [04:44<16:57, 11.47it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  22%|▏| 3265/14932 [04:41<16:44, 11.62it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  22%|▏| 3265/14932 [04:41<16:44, 11.62it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -30765,8 +30730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3268/14932 [04:45<16:57, 11.47it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  22%|▏| 3268/14932 [04:45<16:57, 11.47it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  22%|▏| 3266/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  22%|▏| 3266/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -30774,8 +30739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3269/14932 [04:45<16:57, 11.47it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  22%|▏| 3269/14932 [04:45<16:57, 11.47it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  22%|▏| 3267/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  22%|▏| 3267/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -30783,8 +30748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3270/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  22%|▏| 3270/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  22%|▏| 3268/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  22%|▏| 3268/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -30792,8 +30757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3271/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  22%|▏| 3271/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  22%|▏| 3269/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  22%|▏| 3269/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -30801,8 +30766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3272/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  22%|▏| 3272/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  22%|▏| 3270/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  22%|▏| 3270/14932 [04:41<16:44, 11.61it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -30810,8 +30775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3273/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  22%|▏| 3273/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  22%|▏| 3271/14932 [04:41<16:43, 11.61it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  22%|▏| 3271/14932 [04:41<16:43, 11.61it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -30819,8 +30784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3274/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  22%|▏| 3274/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  22%|▏| 3272/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  22%|▏| 3272/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -30828,8 +30793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3275/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  22%|▏| 3275/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  22%|▏| 3273/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  22%|▏| 3273/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -30837,8 +30802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3276/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  22%|▏| 3276/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  22%|▏| 3274/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  22%|▏| 3274/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -30846,8 +30811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3277/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  22%|▏| 3277/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  22%|▏| 3275/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  22%|▏| 3275/14932 [04:41<16:43, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -30855,8 +30820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3278/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  22%|▏| 3278/14932 [04:45<16:56, 11.47it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  22%|▏| 3276/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  22%|▏| 3276/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -30864,8 +30829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3279/14932 [04:45<16:55, 11.47it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  22%|▏| 3279/14932 [04:45<16:55, 11.47it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  22%|▏| 3277/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  22%|▏| 3277/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -30873,8 +30838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3280/14932 [04:45<16:55, 11.47it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  22%|▏| 3280/14932 [04:45<16:55, 11.47it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  22%|▏| 3278/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  22%|▏| 3278/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -30882,8 +30847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3281/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  22%|▏| 3281/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  22%|▏| 3279/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  22%|▏| 3279/14932 [04:42<16:43, 11.62it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -30891,8 +30856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3282/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  22%|▏| 3282/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  22%|▏| 3280/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  22%|▏| 3280/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -30900,8 +30865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3283/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  22%|▏| 3283/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  22%|▏| 3281/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  22%|▏| 3281/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -30909,8 +30874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3284/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  22%|▏| 3284/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  22%|▏| 3282/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  22%|▏| 3282/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -30918,8 +30883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3285/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  22%|▏| 3285/14932 [04:46<16:55, 11.47it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  22%|▏| 3283/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  22%|▏| 3283/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -30927,8 +30892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3286/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  22%|▏| 3286/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  22%|▏| 3284/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  22%|▏| 3284/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -30936,8 +30901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3287/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  22%|▏| 3287/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  22%|▏| 3285/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  22%|▏| 3285/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -30945,8 +30910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3288/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  22%|▏| 3288/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  22%|▏| 3286/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  22%|▏| 3286/14932 [04:42<16:42, 11.62it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -30954,8 +30919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3289/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  22%|▏| 3289/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  22%|▏| 3287/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  22%|▏| 3287/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -30963,8 +30928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3290/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  22%|▏| 3290/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  22%|▏| 3288/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  22%|▏| 3288/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -30972,8 +30937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3291/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  22%|▏| 3291/14932 [04:46<16:54, 11.47it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  22%|▏| 3289/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  22%|▏| 3289/14932 [04:42<16:41, 11.62it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -30981,8 +30946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3292/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  22%|▏| 3292/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  22%|▏| 3290/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  22%|▏| 3290/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -30990,8 +30955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3293/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  22%|▏| 3293/14932 [04:46<16:54, 11.48it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  22%|▏| 3291/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  22%|▏| 3291/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -30999,8 +30964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3294/14932 [04:47<16:54, 11.48it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  22%|▏| 3294/14932 [04:47<16:54, 11.48it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  22%|▏| 3292/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  22%|▏| 3292/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -31008,8 +30973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3295/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  22%|▏| 3295/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  22%|▏| 3293/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  22%|▏| 3293/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -31017,8 +30982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3296/14932 [04:47<16:54, 11.47it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  22%|▏| 3296/14932 [04:47<16:54, 11.47it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  22%|▏| 3294/14932 [04:43<16:41, 11.63it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  22%|▏| 3294/14932 [04:43<16:41, 11.63it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -31026,8 +30991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3297/14932 [04:47<16:54, 11.47it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  22%|▏| 3297/14932 [04:47<16:54, 11.47it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  22%|▏| 3295/14932 [04:43<16:40, 11.63it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  22%|▏| 3295/14932 [04:43<16:40, 11.63it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -31035,8 +31000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3298/14932 [04:47<16:53, 11.47it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  22%|▏| 3298/14932 [04:47<16:53, 11.47it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  22%|▏| 3296/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  22%|▏| 3296/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -31044,8 +31009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3299/14932 [04:47<16:53, 11.47it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  22%|▏| 3299/14932 [04:47<16:53, 11.47it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  22%|▏| 3297/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  22%|▏| 3297/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -31053,8 +31018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3300/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  22%|▏| 3300/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  22%|▏| 3298/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  22%|▏| 3298/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -31062,8 +31027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3301/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  22%|▏| 3301/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  22%|▏| 3299/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  22%|▏| 3299/14932 [04:43<16:41, 11.62it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -31071,8 +31036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3302/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  22%|▏| 3302/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  22%|▏| 3300/14932 [04:43<16:40, 11.62it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  22%|▏| 3300/14932 [04:43<16:40, 11.62it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -31080,8 +31045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3303/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  22%|▏| 3303/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  22%|▏| 3301/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  22%|▏| 3301/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -31089,8 +31054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3304/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  22%|▏| 3304/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  22%|▏| 3302/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  22%|▏| 3302/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -31098,8 +31063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3305/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  22%|▏| 3305/14932 [04:47<16:53, 11.48it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  22%|▏| 3303/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  22%|▏| 3303/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -31107,8 +31072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3306/14932 [04:48<16:53, 11.48it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  22%|▏| 3306/14932 [04:48<16:53, 11.48it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  22%|▏| 3304/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  22%|▏| 3304/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -31116,8 +31081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3307/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  22%|▏| 3307/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  22%|▏| 3305/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  22%|▏| 3305/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -31125,8 +31090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3308/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  22%|▏| 3308/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  22%|▏| 3306/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  22%|▏| 3306/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -31134,8 +31099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3309/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  22%|▏| 3309/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  22%|▏| 3307/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  22%|▏| 3307/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -31143,8 +31108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3310/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  22%|▏| 3310/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  22%|▏| 3308/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  22%|▏| 3308/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -31152,8 +31117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3311/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  22%|▏| 3311/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  22%|▏| 3309/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  22%|▏| 3309/14932 [04:44<16:40, 11.62it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -31161,8 +31126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3312/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  22%|▏| 3312/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  22%|▏| 3310/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  22%|▏| 3310/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -31170,8 +31135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3313/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  22%|▏| 3313/14932 [04:48<16:52, 11.48it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  22%|▏| 3311/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  22%|▏| 3311/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -31179,8 +31144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3314/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  22%|▏| 3314/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  22%|▏| 3312/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  22%|▏| 3312/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -31188,8 +31153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3315/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  22%|▏| 3315/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  22%|▏| 3313/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  22%|▏| 3313/14932 [04:44<16:39, 11.62it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -31197,8 +31162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3316/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  22%|▏| 3316/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  22%|▏| 3314/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  22%|▏| 3314/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -31206,8 +31171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3317/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  22%|▏| 3317/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  22%|▏| 3315/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  22%|▏| 3315/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -31215,8 +31180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3318/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  22%|▏| 3318/14932 [04:48<16:51, 11.48it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  22%|▏| 3316/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  22%|▏| 3316/14932 [04:45<16:39, 11.63it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -31224,8 +31189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3319/14932 [04:49<16:51, 11.48it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  22%|▏| 3319/14932 [04:49<16:51, 11.48it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  22%|▏| 3317/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  22%|▏| 3317/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -31233,8 +31198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3320/14932 [04:49<16:51, 11.48it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  22%|▏| 3320/14932 [04:49<16:51, 11.48it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  22%|▏| 3318/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  22%|▏| 3318/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -31242,8 +31207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3321/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  22%|▏| 3321/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  22%|▏| 3319/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  22%|▏| 3319/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -31251,8 +31216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3322/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  22%|▏| 3322/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  22%|▏| 3320/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  22%|▏| 3320/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -31260,8 +31225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3323/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  22%|▏| 3323/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  22%|▏| 3321/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  22%|▏| 3321/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -31269,8 +31234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3324/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  22%|▏| 3324/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  22%|▏| 3322/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  22%|▏| 3322/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -31278,8 +31243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3325/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  22%|▏| 3325/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  22%|▏| 3323/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  22%|▏| 3323/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -31287,8 +31252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3326/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  22%|▏| 3326/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  22%|▏| 3324/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  22%|▏| 3324/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -31296,8 +31261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3327/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  22%|▏| 3327/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=1.25"
+      "Epoch 0:  22%|▏| 3325/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  22%|▏| 3325/14932 [04:45<16:38, 11.63it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -31305,8 +31270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3328/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=1.25\r",
-      "Epoch 0:  22%|▏| 3328/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  22%|▏| 3326/14932 [04:46<16:38, 11.63it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  22%|▏| 3326/14932 [04:46<16:38, 11.63it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -31314,8 +31279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3329/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  22%|▏| 3329/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  22%|▏| 3327/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  22%|▏| 3327/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -31323,8 +31288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3330/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  22%|▏| 3330/14932 [04:49<16:50, 11.49it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  22%|▏| 3328/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  22%|▏| 3328/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -31332,8 +31297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3331/14932 [04:49<16:49, 11.49it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  22%|▏| 3331/14932 [04:49<16:49, 11.49it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  22%|▏| 3329/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  22%|▏| 3329/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -31341,8 +31306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3332/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  22%|▏| 3332/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  22%|▏| 3330/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  22%|▏| 3330/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -31350,8 +31315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3333/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  22%|▏| 3333/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  22%|▏| 3331/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  22%|▏| 3331/14932 [04:46<16:37, 11.63it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -31359,8 +31324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3334/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  22%|▏| 3334/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  22%|▏| 3332/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  22%|▏| 3332/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -31368,8 +31333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3335/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  22%|▏| 3335/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  22%|▏| 3333/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  22%|▏| 3333/14932 [04:46<16:38, 11.62it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -31377,8 +31342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3336/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  22%|▏| 3336/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  22%|▏| 3334/14932 [04:46<16:37, 11.62it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  22%|▏| 3334/14932 [04:46<16:37, 11.62it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -31386,8 +31351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3337/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  22%|▏| 3337/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.57"
+      "Epoch 0:  22%|▏| 3335/14932 [04:46<16:37, 11.62it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  22%|▏| 3335/14932 [04:46<16:37, 11.62it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -31395,8 +31360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3338/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=1.57\r",
-      "Epoch 0:  22%|▏| 3338/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  22%|▏| 3336/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  22%|▏| 3336/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -31404,8 +31369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3339/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  22%|▏| 3339/14932 [04:50<16:49, 11.49it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  22%|▏| 3337/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  22%|▏| 3337/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -31413,8 +31378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3340/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  22%|▏| 3340/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  22%|▏| 3338/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  22%|▏| 3338/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -31422,8 +31387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3341/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  22%|▏| 3341/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  22%|▏| 3339/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  22%|▏| 3339/14932 [04:47<16:37, 11.62it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -31431,8 +31396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3342/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  22%|▏| 3342/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  22%|▏| 3340/14932 [04:47<16:37, 11.63it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  22%|▏| 3340/14932 [04:47<16:37, 11.63it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -31440,8 +31405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3343/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  22%|▏| 3343/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  22%|▏| 3341/14932 [04:47<16:37, 11.63it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  22%|▏| 3341/14932 [04:47<16:37, 11.63it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -31449,8 +31414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3344/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  22%|▏| 3344/14932 [04:50<16:48, 11.49it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  22%|▏| 3342/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  22%|▏| 3342/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -31458,8 +31423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3345/14932 [04:51<16:48, 11.49it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  22%|▏| 3345/14932 [04:51<16:48, 11.49it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  22%|▏| 3343/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  22%|▏| 3343/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -31467,8 +31432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3346/14932 [04:51<16:48, 11.49it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  22%|▏| 3346/14932 [04:51<16:48, 11.49it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  22%|▏| 3344/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  22%|▏| 3344/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -31476,8 +31441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3347/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  22%|▏| 3347/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  22%|▏| 3345/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  22%|▏| 3345/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -31485,8 +31450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3348/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  22%|▏| 3348/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  22%|▏| 3346/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  22%|▏| 3346/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -31494,8 +31459,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3349/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  22%|▏| 3349/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  22%|▏| 3347/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -31503,8 +31467,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3350/14932 [04:51<16:49, 11.48it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  22%|▏| 3350/14932 [04:51<16:49, 11.48it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  22%|▏| 3347/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -31512,8 +31475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3351/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  22%|▏| 3351/14932 [04:51<16:48, 11.48it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  22%|▏| 3348/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  22%|▏| 3348/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -31521,8 +31484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3352/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  22%|▏| 3352/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  22%|▏| 3349/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  22%|▏| 3349/14932 [04:47<16:36, 11.63it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -31530,8 +31493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3353/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  22%|▏| 3353/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  22%|▏| 3350/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  22%|▏| 3350/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -31539,8 +31502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3354/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  22%|▏| 3354/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  22%|▏| 3351/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  22%|▏| 3351/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -31548,8 +31511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3355/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  22%|▏| 3355/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  22%|▏| 3352/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  22%|▏| 3352/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -31557,8 +31520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3356/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  22%|▏| 3356/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:  22%|▏| 3353/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  22%|▏| 3353/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -31566,8 +31529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3357/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:  22%|▏| 3357/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  22%|▏| 3354/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  22%|▏| 3354/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=1.01"
      ]
     },
     {
@@ -31575,8 +31538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3358/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  22%|▏| 3358/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  22%|▏| 3355/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=1.01\r",
+      "Epoch 0:  22%|▏| 3355/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -31584,8 +31547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  22%|▏| 3359/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  22%|▏| 3359/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  22%|▏| 3356/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  22%|▏| 3356/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -31593,8 +31556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3360/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  23%|▏| 3360/14932 [04:52<16:48, 11.48it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  22%|▏| 3357/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  22%|▏| 3357/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -31602,8 +31565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3361/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  23%|▏| 3361/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  22%|▏| 3358/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  22%|▏| 3358/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=1.33"
      ]
     },
     {
@@ -31611,8 +31574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3362/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  23%|▏| 3362/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  22%|▏| 3359/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=1.33\r",
+      "Epoch 0:  22%|▏| 3359/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -31620,8 +31583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3363/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  23%|▏| 3363/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  23%|▏| 3360/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  23%|▏| 3360/14932 [04:48<16:35, 11.63it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -31629,8 +31592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3364/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  23%|▏| 3364/14932 [04:52<16:47, 11.48it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  23%|▏| 3361/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  23%|▏| 3361/14932 [04:48<16:34, 11.63it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -31638,8 +31601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3365/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  23%|▏| 3365/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  23%|▏| 3362/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  23%|▏| 3362/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -31647,8 +31610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3366/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  23%|▏| 3366/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  23%|▏| 3363/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  23%|▏| 3363/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -31656,8 +31619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3367/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  23%|▏| 3367/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  23%|▏| 3364/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  23%|▏| 3364/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -31665,8 +31628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3368/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  23%|▏| 3368/14932 [04:53<16:47, 11.48it/s, v_num=o30c, train/loss=0.82"
+      "Epoch 0:  23%|▏| 3365/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  23%|▏| 3365/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -31674,8 +31637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3369/14932 [04:53<16:46, 11.48it/s, v_num=o30c, train/loss=0.82\r",
-      "Epoch 0:  23%|▏| 3369/14932 [04:53<16:46, 11.48it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  23%|▏| 3366/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  23%|▏| 3366/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -31683,8 +31646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3370/14932 [04:53<16:46, 11.48it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  23%|▏| 3370/14932 [04:53<16:46, 11.48it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  23%|▏| 3367/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  23%|▏| 3367/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -31692,8 +31655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3371/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  23%|▏| 3371/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  23%|▏| 3368/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  23%|▏| 3368/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -31701,8 +31664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3372/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  23%|▏| 3372/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  23%|▏| 3369/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  23%|▏| 3369/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -31710,8 +31673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3373/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  23%|▏| 3373/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  23%|▏| 3370/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  23%|▏| 3370/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -31719,8 +31682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3374/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  23%|▏| 3374/14932 [04:53<16:46, 11.49it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  23%|▏| 3371/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  23%|▏| 3371/14932 [04:49<16:34, 11.63it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -31728,8 +31691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3375/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  23%|▏| 3375/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  23%|▏| 3372/14932 [04:49<16:33, 11.63it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  23%|▏| 3372/14932 [04:49<16:33, 11.63it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -31737,8 +31700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3376/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  23%|▏| 3376/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  23%|▏| 3373/14932 [04:49<16:33, 11.63it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  23%|▏| 3373/14932 [04:49<16:33, 11.63it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -31746,8 +31709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3377/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  23%|▏| 3377/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  23%|▏| 3374/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  23%|▏| 3374/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -31755,8 +31718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3378/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  23%|▏| 3378/14932 [04:53<16:45, 11.49it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  23%|▏| 3375/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  23%|▏| 3375/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -31764,8 +31727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3379/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  23%|▏| 3379/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  23%|▏| 3376/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  23%|▏| 3376/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -31773,7 +31736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3380/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  23%|▏| 3377/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  23%|▏| 3377/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -31781,7 +31745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3380/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  23%|▏| 3378/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  23%|▏| 3378/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -31789,8 +31754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3381/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  23%|▏| 3381/14932 [04:54<16:45, 11.49it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  23%|▏| 3379/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  23%|▏| 3379/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -31798,8 +31763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3382/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  23%|▏| 3382/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  23%|▏| 3380/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  23%|▏| 3380/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -31807,8 +31772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3383/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  23%|▏| 3383/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  23%|▏| 3381/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  23%|▏| 3381/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -31816,8 +31781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3384/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  23%|▏| 3384/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  23%|▏| 3382/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  23%|▏| 3382/14932 [04:50<16:33, 11.63it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -31825,8 +31790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3385/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  23%|▏| 3385/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  23%|▏| 3383/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  23%|▏| 3383/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -31834,8 +31799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3386/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  23%|▏| 3386/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  23%|▏| 3384/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  23%|▏| 3384/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -31843,8 +31808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3387/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  23%|▏| 3387/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  23%|▏| 3385/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  23%|▏| 3385/14932 [04:50<16:32, 11.63it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -31852,8 +31817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3388/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  23%|▏| 3388/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  23%|▏| 3386/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  23%|▏| 3386/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -31861,8 +31826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3389/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  23%|▏| 3389/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  23%|▏| 3387/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  23%|▏| 3387/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -31870,8 +31835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3390/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  23%|▏| 3390/14932 [04:54<16:44, 11.49it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  23%|▏| 3388/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  23%|▏| 3388/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -31879,8 +31844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3391/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  23%|▏| 3391/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  23%|▏| 3389/14932 [04:51<16:32, 11.64it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  23%|▏| 3389/14932 [04:51<16:32, 11.64it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -31888,8 +31853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3392/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  23%|▏| 3392/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  23%|▏| 3390/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  23%|▏| 3390/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -31897,8 +31862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3393/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  23%|▏| 3393/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  23%|▏| 3391/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  23%|▏| 3391/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -31906,8 +31871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3394/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  23%|▏| 3394/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  23%|▏| 3392/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  23%|▏| 3392/14932 [04:51<16:32, 11.63it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -31915,8 +31880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3395/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  23%|▏| 3395/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  23%|▏| 3393/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  23%|▏| 3393/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -31924,8 +31889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3396/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  23%|▏| 3396/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  23%|▏| 3394/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  23%|▏| 3394/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -31933,8 +31898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3397/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  23%|▏| 3397/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  23%|▏| 3395/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  23%|▏| 3395/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -31942,8 +31907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3398/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  23%|▏| 3398/14932 [04:55<16:44, 11.49it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  23%|▏| 3396/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  23%|▏| 3396/14932 [04:51<16:31, 11.63it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -31951,8 +31916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3399/14932 [04:55<16:43, 11.49it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  23%|▏| 3399/14932 [04:55<16:43, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  23%|▏| 3397/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  23%|▏| 3397/14932 [04:51<16:31, 11.64it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -31960,8 +31925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3400/14932 [04:55<16:43, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  23%|▏| 3400/14932 [04:55<16:43, 11.49it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  23%|▏| 3398/14932 [04:52<16:31, 11.64it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  23%|▏| 3398/14932 [04:52<16:31, 11.64it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -31969,8 +31934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3401/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  23%|▏| 3401/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  23%|▏| 3399/14932 [04:52<16:31, 11.64it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  23%|▏| 3399/14932 [04:52<16:31, 11.64it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -31978,8 +31943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3402/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  23%|▏| 3402/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  23%|▏| 3400/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  23%|▏| 3400/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -31987,8 +31952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3403/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  23%|▏| 3403/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  23%|▏| 3401/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  23%|▏| 3401/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -31996,8 +31961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3404/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  23%|▏| 3404/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  23%|▏| 3402/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  23%|▏| 3402/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -32005,8 +31970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3405/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  23%|▏| 3405/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  23%|▏| 3403/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  23%|▏| 3403/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -32014,8 +31979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3406/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  23%|▏| 3406/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  23%|▏| 3404/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  23%|▏| 3404/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -32023,8 +31988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3407/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  23%|▏| 3407/14932 [04:56<16:43, 11.49it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  23%|▏| 3405/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  23%|▏| 3405/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -32032,8 +31997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3408/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  23%|▏| 3408/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  23%|▏| 3406/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  23%|▏| 3406/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -32041,8 +32006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3409/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  23%|▏| 3409/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  23%|▏| 3407/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  23%|▏| 3407/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -32050,8 +32015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3410/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  23%|▏| 3410/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  23%|▏| 3408/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  23%|▏| 3408/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -32059,8 +32024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3411/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  23%|▏| 3411/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  23%|▏| 3409/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  23%|▏| 3409/14932 [04:52<16:30, 11.64it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -32068,8 +32033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3412/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  23%|▏| 3412/14932 [04:56<16:42, 11.49it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  23%|▏| 3410/14932 [04:52<16:29, 11.64it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  23%|▏| 3410/14932 [04:52<16:29, 11.64it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -32077,8 +32042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3413/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  23%|▏| 3413/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  23%|▏| 3411/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  23%|▏| 3411/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -32086,8 +32051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3414/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  23%|▏| 3414/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  23%|▏| 3412/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  23%|▏| 3412/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -32095,8 +32060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3415/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  23%|▏| 3415/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  23%|▏| 3413/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  23%|▏| 3413/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -32104,8 +32069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3416/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  23%|▏| 3416/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  23%|▏| 3414/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  23%|▏| 3414/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -32113,8 +32078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3417/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  23%|▏| 3417/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  23%|▏| 3415/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  23%|▏| 3415/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -32122,8 +32087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3418/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  23%|▏| 3418/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  23%|▏| 3416/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  23%|▏| 3416/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -32131,8 +32096,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3419/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  23%|▏| 3419/14932 [04:57<16:42, 11.49it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  23%|▏| 3417/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -32140,8 +32104,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3420/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  23%|▏| 3420/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  23%|▏| 3417/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -32149,8 +32112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3421/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  23%|▏| 3421/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  23%|▏| 3418/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  23%|▏| 3418/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -32158,8 +32121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3422/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  23%|▏| 3422/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  23%|▏| 3419/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  23%|▏| 3419/14932 [04:53<16:29, 11.64it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -32167,8 +32130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3423/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  23%|▏| 3423/14932 [04:57<16:41, 11.49it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  23%|▏| 3420/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  23%|▏| 3420/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -32176,8 +32139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3424/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  23%|▏| 3424/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  23%|▏| 3421/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  23%|▏| 3421/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -32185,7 +32148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3425/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  23%|▏| 3422/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  23%|▏| 3422/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -32193,7 +32157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3425/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  23%|▏| 3423/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  23%|▏| 3423/14932 [04:53<16:28, 11.64it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -32201,8 +32166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3426/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  23%|▏| 3426/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  23%|▏| 3424/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  23%|▏| 3424/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -32210,8 +32175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3427/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  23%|▏| 3427/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  23%|▏| 3425/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  23%|▏| 3425/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -32219,8 +32184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3428/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  23%|▏| 3428/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  23%|▏| 3426/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  23%|▏| 3426/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -32228,8 +32193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3429/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  23%|▏| 3429/14932 [04:58<16:41, 11.49it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  23%|▏| 3427/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  23%|▏| 3427/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -32237,8 +32202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3430/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  23%|▏| 3430/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  23%|▏| 3428/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  23%|▏| 3428/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -32246,8 +32211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3431/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  23%|▏| 3431/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  23%|▏| 3429/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  23%|▏| 3429/14932 [04:54<16:28, 11.64it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -32255,7 +32220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3432/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  23%|▏| 3430/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  23%|▏| 3430/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -32263,7 +32229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3432/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  23%|▏| 3431/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  23%|▏| 3431/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -32271,8 +32238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3433/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  23%|▏| 3433/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  23%|▏| 3432/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  23%|▏| 3432/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -32280,8 +32247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3434/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  23%|▏| 3434/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  23%|▏| 3433/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  23%|▏| 3433/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -32289,8 +32256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3435/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  23%|▏| 3435/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  23%|▏| 3434/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  23%|▏| 3434/14932 [04:54<16:27, 11.64it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -32298,8 +32265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3436/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  23%|▏| 3436/14932 [04:58<16:40, 11.49it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  23%|▏| 3435/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  23%|▏| 3435/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -32307,8 +32274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3437/14932 [04:58<16:39, 11.50it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  23%|▏| 3437/14932 [04:58<16:39, 11.50it/s, v_num=o30c, train/loss=4.91"
+      "Epoch 0:  23%|▏| 3436/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  23%|▏| 3436/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -32316,8 +32283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3438/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=4.91\r",
-      "Epoch 0:  23%|▏| 3438/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  23%|▏| 3437/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  23%|▏| 3437/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -32325,8 +32292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3439/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  23%|▏| 3439/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  23%|▏| 3438/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  23%|▏| 3438/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -32334,8 +32301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3440/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  23%|▏| 3440/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  23%|▏| 3439/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  23%|▏| 3439/14932 [04:55<16:27, 11.64it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -32343,8 +32310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3441/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  23%|▏| 3441/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  23%|▏| 3440/14932 [04:55<16:26, 11.64it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  23%|▏| 3440/14932 [04:55<16:26, 11.64it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -32352,8 +32319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3442/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  23%|▏| 3442/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=5.50"
+      "Epoch 0:  23%|▏| 3441/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  23%|▏| 3441/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -32361,8 +32328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3443/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=5.50\r",
-      "Epoch 0:  23%|▏| 3443/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  23%|▏| 3442/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  23%|▏| 3442/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -32370,8 +32337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3444/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  23%|▏| 3444/14932 [04:59<16:39, 11.50it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  23%|▏| 3443/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  23%|▏| 3443/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -32379,8 +32346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3445/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  23%|▏| 3445/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  23%|▏| 3444/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  23%|▏| 3444/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -32388,8 +32355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3446/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  23%|▏| 3446/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  23%|▏| 3445/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  23%|▏| 3445/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -32397,8 +32364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3447/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  23%|▏| 3447/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  23%|▏| 3446/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  23%|▏| 3446/14932 [04:55<16:26, 11.65it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -32406,8 +32373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3448/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  23%|▏| 3448/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  23%|▏| 3447/14932 [04:55<16:25, 11.65it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  23%|▏| 3447/14932 [04:55<16:25, 11.65it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -32415,8 +32382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3449/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  23%|▏| 3449/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  23%|▏| 3448/14932 [04:55<16:25, 11.65it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  23%|▏| 3448/14932 [04:55<16:25, 11.65it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -32424,8 +32391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3450/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  23%|▏| 3450/14932 [04:59<16:38, 11.50it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  23%|▏| 3449/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  23%|▏| 3449/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -32433,8 +32400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3451/14932 [05:00<16:38, 11.50it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  23%|▏| 3451/14932 [05:00<16:38, 11.50it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  23%|▏| 3450/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  23%|▏| 3450/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -32442,8 +32409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3452/14932 [05:00<16:38, 11.50it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  23%|▏| 3452/14932 [05:00<16:38, 11.50it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  23%|▏| 3451/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  23%|▏| 3451/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -32451,8 +32418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3453/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  23%|▏| 3453/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  23%|▏| 3452/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  23%|▏| 3452/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -32460,8 +32427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3454/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  23%|▏| 3454/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  23%|▏| 3453/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  23%|▏| 3453/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -32469,8 +32436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3455/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  23%|▏| 3455/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  23%|▏| 3454/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  23%|▏| 3454/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -32478,8 +32445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3456/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  23%|▏| 3456/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  23%|▏| 3455/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  23%|▏| 3455/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -32487,8 +32454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3457/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  23%|▏| 3457/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  23%|▏| 3456/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  23%|▏| 3456/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -32496,8 +32463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3458/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  23%|▏| 3458/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  23%|▏| 3457/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  23%|▏| 3457/14932 [04:56<16:25, 11.65it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -32505,8 +32472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3459/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  23%|▏| 3459/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  23%|▏| 3458/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  23%|▏| 3458/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -32514,8 +32481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3460/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  23%|▏| 3460/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  23%|▏| 3459/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  23%|▏| 3459/14932 [04:56<16:24, 11.65it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -32523,8 +32490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3461/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  23%|▏| 3461/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  23%|▏| 3460/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  23%|▏| 3460/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -32532,8 +32499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3462/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  23%|▏| 3462/14932 [05:00<16:37, 11.50it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  23%|▏| 3461/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  23%|▏| 3461/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -32541,8 +32508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3463/14932 [05:01<16:36, 11.50it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  23%|▏| 3463/14932 [05:01<16:37, 11.50it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  23%|▏| 3462/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  23%|▏| 3462/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -32550,8 +32517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3464/14932 [05:01<16:36, 11.50it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  23%|▏| 3464/14932 [05:01<16:36, 11.50it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  23%|▏| 3463/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  23%|▏| 3463/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -32559,8 +32526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3465/14932 [05:01<16:36, 11.50it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  23%|▏| 3465/14932 [05:01<16:36, 11.50it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  23%|▏| 3464/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  23%|▏| 3464/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -32568,8 +32535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3466/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  23%|▏| 3466/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  23%|▏| 3465/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  23%|▏| 3465/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -32577,8 +32544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3467/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  23%|▏| 3467/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  23%|▏| 3466/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  23%|▏| 3466/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -32586,8 +32553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3468/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  23%|▏| 3468/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  23%|▏| 3467/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  23%|▏| 3467/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -32595,8 +32562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3469/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  23%|▏| 3469/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  23%|▏| 3468/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  23%|▏| 3468/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -32604,8 +32571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3470/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  23%|▏| 3470/14932 [05:01<16:36, 11.51it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  23%|▏| 3469/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  23%|▏| 3469/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -32613,8 +32580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3471/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  23%|▏| 3471/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  23%|▏| 3470/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  23%|▏| 3470/14932 [04:57<16:24, 11.65it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -32622,8 +32589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3472/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  23%|▏| 3472/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  23%|▏| 3471/14932 [04:57<16:23, 11.65it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  23%|▏| 3471/14932 [04:57<16:23, 11.65it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -32631,8 +32598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3473/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  23%|▏| 3473/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  23%|▏| 3472/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  23%|▏| 3472/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -32640,8 +32607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3474/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  23%|▏| 3474/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  23%|▏| 3473/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  23%|▏| 3473/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -32649,8 +32616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3475/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  23%|▏| 3475/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  23%|▏| 3474/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  23%|▏| 3474/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -32658,8 +32625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3476/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  23%|▏| 3476/14932 [05:01<16:35, 11.51it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  23%|▏| 3475/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  23%|▏| 3475/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -32667,8 +32634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3477/14932 [05:02<16:35, 11.51it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  23%|▏| 3477/14932 [05:02<16:35, 11.51it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  23%|▏| 3476/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  23%|▏| 3476/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -32676,8 +32643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3478/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  23%|▏| 3478/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  23%|▏| 3477/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  23%|▏| 3477/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -32685,8 +32652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3479/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  23%|▏| 3479/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  23%|▏| 3478/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  23%|▏| 3478/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -32694,8 +32661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3480/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  23%|▏| 3480/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  23%|▏| 3479/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  23%|▏| 3479/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -32703,8 +32670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3481/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  23%|▏| 3481/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  23%|▏| 3480/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  23%|▏| 3480/14932 [04:58<16:23, 11.65it/s, v_num=ui8w, train/loss=1.00"
      ]
     },
     {
@@ -32712,8 +32679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3482/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  23%|▏| 3482/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  23%|▏| 3481/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=1.00\r",
+      "Epoch 0:  23%|▏| 3481/14932 [04:58<16:23, 11.64it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -32721,8 +32688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3483/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  23%|▏| 3483/14932 [05:02<16:34, 11.51it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  23%|▏| 3482/14932 [04:59<16:23, 11.64it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  23%|▏| 3482/14932 [04:59<16:23, 11.64it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -32730,8 +32697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3484/14932 [05:02<16:34, 11.52it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  23%|▏| 3484/14932 [05:02<16:34, 11.52it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  23%|▏| 3483/14932 [04:59<16:23, 11.64it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  23%|▏| 3483/14932 [04:59<16:23, 11.64it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -32739,8 +32706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3485/14932 [05:02<16:34, 11.52it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  23%|▏| 3485/14932 [05:02<16:34, 11.52it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  23%|▏| 3484/14932 [04:59<16:23, 11.65it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  23%|▏| 3484/14932 [04:59<16:23, 11.65it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -32748,8 +32715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3486/14932 [05:02<16:33, 11.52it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  23%|▏| 3486/14932 [05:02<16:33, 11.52it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  23%|▏| 3485/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  23%|▏| 3485/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=5.28"
      ]
     },
     {
@@ -32757,8 +32724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3487/14932 [05:02<16:33, 11.52it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  23%|▏| 3487/14932 [05:02<16:33, 11.52it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  23%|▏| 3486/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=5.28\r",
+      "Epoch 0:  23%|▏| 3486/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -32766,8 +32733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3488/14932 [05:02<16:33, 11.51it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  23%|▏| 3488/14932 [05:02<16:33, 11.51it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  23%|▏| 3487/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  23%|▏| 3487/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -32775,8 +32742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3489/14932 [05:03<16:33, 11.51it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  23%|▏| 3489/14932 [05:03<16:33, 11.51it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  23%|▏| 3488/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  23%|▏| 3488/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -32784,8 +32751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3490/14932 [05:03<16:33, 11.51it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  23%|▏| 3490/14932 [05:03<16:33, 11.51it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  23%|▏| 3489/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  23%|▏| 3489/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -32793,8 +32760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3491/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  23%|▏| 3491/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  23%|▏| 3490/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  23%|▏| 3490/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -32802,8 +32769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3492/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  23%|▏| 3492/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  23%|▏| 3491/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  23%|▏| 3491/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -32811,8 +32778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3493/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  23%|▏| 3493/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  23%|▏| 3492/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  23%|▏| 3492/14932 [04:59<16:22, 11.64it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -32820,8 +32787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3494/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  23%|▏| 3494/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  23%|▏| 3493/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  23%|▏| 3493/14932 [04:59<16:22, 11.65it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -32829,8 +32796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3495/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  23%|▏| 3495/14932 [05:03<16:33, 11.52it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  23%|▏| 3494/14932 [05:00<16:22, 11.65it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  23%|▏| 3494/14932 [05:00<16:22, 11.65it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -32838,8 +32805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3496/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  23%|▏| 3496/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  23%|▏| 3495/14932 [05:00<16:22, 11.65it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  23%|▏| 3495/14932 [05:00<16:22, 11.65it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -32847,8 +32814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3497/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  23%|▏| 3497/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  23%|▏| 3496/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  23%|▏| 3496/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -32856,8 +32823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3498/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  23%|▏| 3498/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  23%|▏| 3497/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  23%|▏| 3497/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -32865,8 +32832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3499/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  23%|▏| 3499/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  23%|▏| 3498/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  23%|▏| 3498/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -32874,8 +32841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3500/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  23%|▏| 3500/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  23%|▏| 3499/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  23%|▏| 3499/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -32883,8 +32850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3501/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  23%|▏| 3501/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  23%|▏| 3500/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  23%|▏| 3500/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -32892,8 +32859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3502/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  23%|▏| 3502/14932 [05:03<16:32, 11.52it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  23%|▏| 3501/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  23%|▏| 3501/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -32901,8 +32868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3503/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  23%|▏| 3503/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  23%|▏| 3502/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  23%|▏| 3502/14932 [05:00<16:21, 11.65it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -32910,8 +32877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3504/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  23%|▏| 3504/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  23%|▏| 3503/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  23%|▏| 3503/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -32919,8 +32886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3505/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  23%|▏| 3505/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  23%|▏| 3504/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  23%|▏| 3504/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -32928,8 +32895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3506/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  23%|▏| 3506/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  23%|▏| 3505/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  23%|▏| 3505/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -32937,8 +32904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3507/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  23%|▏| 3507/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  23%|▏| 3506/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  23%|▏| 3506/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -32946,8 +32913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3508/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  23%|▏| 3508/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  23%|▏| 3507/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  23%|▏| 3507/14932 [05:00<16:20, 11.65it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -32955,8 +32922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  23%|▏| 3509/14932 [05:04<16:31, 11.53it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  23%|▏| 3509/14932 [05:04<16:31, 11.52it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  23%|▏| 3508/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  23%|▏| 3508/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -32964,8 +32931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3510/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  24%|▏| 3510/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  23%|▏| 3509/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  23%|▏| 3509/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -32973,8 +32940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3511/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  24%|▏| 3511/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  24%|▏| 3510/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  24%|▏| 3510/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -32982,8 +32949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3512/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  24%|▏| 3512/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  24%|▏| 3511/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  24%|▏| 3511/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -32991,8 +32958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3513/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  24%|▏| 3513/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  24%|▏| 3512/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  24%|▏| 3512/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -33000,8 +32967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3514/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  24%|▏| 3514/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  24%|▏| 3513/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  24%|▏| 3513/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -33009,8 +32976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3515/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  24%|▏| 3515/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  24%|▏| 3514/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  24%|▏| 3514/14932 [05:01<16:20, 11.65it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -33018,8 +32985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3516/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  24%|▏| 3516/14932 [05:04<16:30, 11.53it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  24%|▏| 3515/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  24%|▏| 3515/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -33027,8 +32994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3517/14932 [05:05<16:30, 11.53it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  24%|▏| 3517/14932 [05:05<16:30, 11.53it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  24%|▏| 3516/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  24%|▏| 3516/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -33036,8 +33003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3518/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  24%|▏| 3518/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  24%|▏| 3517/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  24%|▏| 3517/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -33045,8 +33012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3519/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  24%|▏| 3519/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  24%|▏| 3518/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  24%|▏| 3518/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -33054,8 +33021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3520/14932 [05:05<16:30, 11.53it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  24%|▏| 3520/14932 [05:05<16:30, 11.53it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  24%|▏| 3519/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  24%|▏| 3519/14932 [05:01<16:19, 11.65it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -33063,8 +33030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3521/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  24%|▏| 3521/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  24%|▏| 3520/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  24%|▏| 3520/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -33072,8 +33039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3522/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  24%|▏| 3522/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=1.32"
+      "Epoch 0:  24%|▏| 3521/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  24%|▏| 3521/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -33081,8 +33048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3523/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=1.32\r",
-      "Epoch 0:  24%|▏| 3523/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  24%|▏| 3522/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  24%|▏| 3522/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -33090,8 +33057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3524/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  24%|▏| 3524/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  24%|▏| 3523/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  24%|▏| 3523/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -33099,8 +33066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3525/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  24%|▏| 3525/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  24%|▏| 3524/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  24%|▏| 3524/14932 [05:02<16:19, 11.65it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -33108,8 +33075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3526/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  24%|▏| 3526/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  24%|▏| 3525/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  24%|▏| 3525/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -33117,8 +33084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3527/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  24%|▏| 3527/14932 [05:05<16:29, 11.53it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  24%|▏| 3526/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  24%|▏| 3526/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -33126,8 +33093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3528/14932 [05:05<16:28, 11.53it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  24%|▏| 3528/14932 [05:05<16:28, 11.53it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  24%|▏| 3527/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  24%|▏| 3527/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -33135,8 +33102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3529/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  24%|▏| 3529/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  24%|▏| 3528/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  24%|▏| 3528/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -33144,8 +33111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3530/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  24%|▏| 3530/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  24%|▏| 3529/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  24%|▏| 3529/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -33153,8 +33120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3531/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  24%|▏| 3531/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  24%|▏| 3530/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  24%|▏| 3530/14932 [05:02<16:18, 11.65it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -33162,8 +33129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3532/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  24%|▏| 3532/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  24%|▏| 3531/14932 [05:02<16:18, 11.66it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  24%|▏| 3531/14932 [05:02<16:18, 11.66it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -33171,8 +33138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3533/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  24%|▏| 3533/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  24%|▏| 3532/14932 [05:03<16:18, 11.66it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  24%|▏| 3532/14932 [05:03<16:18, 11.66it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -33180,8 +33147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3534/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  24%|▏| 3534/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  24%|▏| 3533/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  24%|▏| 3533/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -33189,8 +33156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3535/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  24%|▏| 3535/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  24%|▏| 3534/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  24%|▏| 3534/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -33198,8 +33165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3536/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  24%|▏| 3536/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  24%|▏| 3535/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  24%|▏| 3535/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -33207,8 +33174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3537/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  24%|▏| 3537/14932 [05:06<16:28, 11.53it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  24%|▏| 3536/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  24%|▏| 3536/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -33216,8 +33183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3538/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  24%|▏| 3538/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  24%|▏| 3537/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  24%|▏| 3537/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -33225,8 +33192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3539/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  24%|▏| 3539/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  24%|▏| 3538/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  24%|▏| 3538/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -33234,8 +33201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3540/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  24%|▏| 3540/14932 [05:06<16:27, 11.53it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  24%|▏| 3539/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  24%|▏| 3539/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -33243,8 +33210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3541/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  24%|▏| 3541/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  24%|▏| 3540/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  24%|▏| 3540/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -33252,8 +33219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3542/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  24%|▏| 3542/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  24%|▏| 3541/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  24%|▏| 3541/14932 [05:03<16:17, 11.66it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -33261,8 +33228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3543/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  24%|▏| 3543/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  24%|▏| 3542/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  24%|▏| 3542/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -33270,8 +33237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3544/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  24%|▏| 3544/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  24%|▏| 3543/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  24%|▏| 3543/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -33279,8 +33246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3545/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  24%|▏| 3545/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  24%|▏| 3544/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  24%|▏| 3544/14932 [05:03<16:16, 11.66it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -33288,8 +33255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3546/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  24%|▏| 3546/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  24%|▏| 3545/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  24%|▏| 3545/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -33297,8 +33264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3547/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  24%|▏| 3547/14932 [05:07<16:27, 11.53it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  24%|▏| 3546/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  24%|▏| 3546/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -33306,8 +33273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3548/14932 [05:07<16:26, 11.53it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  24%|▏| 3548/14932 [05:07<16:26, 11.53it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  24%|▏| 3547/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  24%|▏| 3547/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -33315,8 +33282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3549/14932 [05:07<16:26, 11.53it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  24%|▏| 3549/14932 [05:07<16:26, 11.53it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  24%|▏| 3548/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  24%|▏| 3548/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -33324,8 +33291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3550/14932 [05:07<16:26, 11.54it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  24%|▏| 3550/14932 [05:07<16:26, 11.54it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  24%|▏| 3549/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  24%|▏| 3549/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -33333,8 +33300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3551/14932 [05:07<16:26, 11.54it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  24%|▏| 3551/14932 [05:07<16:26, 11.54it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  24%|▏| 3550/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  24%|▏| 3550/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -33342,8 +33309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3552/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  24%|▏| 3552/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  24%|▏| 3551/14932 [05:04<16:15, 11.66it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  24%|▏| 3551/14932 [05:04<16:15, 11.66it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -33351,8 +33318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3553/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  24%|▏| 3553/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  24%|▏| 3552/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  24%|▏| 3552/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -33360,8 +33327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3554/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  24%|▏| 3554/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  24%|▏| 3553/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  24%|▏| 3553/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -33369,8 +33336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3555/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  24%|▏| 3555/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  24%|▏| 3554/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  24%|▏| 3554/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -33378,8 +33345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3556/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  24%|▏| 3556/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  24%|▏| 3555/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  24%|▏| 3555/14932 [05:04<16:16, 11.66it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -33387,8 +33354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3557/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  24%|▏| 3557/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  24%|▏| 3556/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  24%|▏| 3556/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -33396,8 +33363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3558/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  24%|▏| 3558/14932 [05:08<16:26, 11.53it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  24%|▏| 3557/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  24%|▏| 3557/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -33405,8 +33372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3559/14932 [05:08<16:25, 11.53it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  24%|▏| 3559/14932 [05:08<16:25, 11.53it/s, v_num=o30c, train/loss=0.85"
+      "Epoch 0:  24%|▏| 3558/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  24%|▏| 3558/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -33414,8 +33381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3560/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=0.85\r",
-      "Epoch 0:  24%|▏| 3560/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  24%|▏| 3559/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  24%|▏| 3559/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -33423,8 +33390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3561/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  24%|▏| 3561/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  24%|▏| 3560/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  24%|▏| 3560/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -33432,8 +33399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3562/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  24%|▏| 3562/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  24%|▏| 3561/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  24%|▏| 3561/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -33441,8 +33408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3563/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  24%|▏| 3563/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  24%|▏| 3562/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  24%|▏| 3562/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=5.41"
      ]
     },
     {
@@ -33450,8 +33417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3564/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  24%|▏| 3564/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  24%|▏| 3563/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=5.41\r",
+      "Epoch 0:  24%|▏| 3563/14932 [05:05<16:15, 11.66it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -33459,8 +33426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3565/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  24%|▏| 3565/14932 [05:08<16:25, 11.54it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  24%|▏| 3564/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  24%|▏| 3564/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -33468,8 +33435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3566/14932 [05:09<16:25, 11.54it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  24%|▏| 3566/14932 [05:09<16:25, 11.54it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  24%|▏| 3565/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  24%|▏| 3565/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -33477,8 +33444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3567/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  24%|▏| 3567/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  24%|▏| 3566/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  24%|▏| 3566/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -33486,8 +33453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3568/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  24%|▏| 3568/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  24%|▏| 3567/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  24%|▏| 3567/14932 [05:05<16:14, 11.66it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -33495,8 +33462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3569/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  24%|▏| 3569/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  24%|▏| 3568/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  24%|▏| 3568/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -33504,8 +33471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3570/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  24%|▏| 3570/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  24%|▏| 3569/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  24%|▏| 3569/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -33513,8 +33480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3571/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  24%|▏| 3571/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  24%|▏| 3570/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  24%|▏| 3570/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -33522,8 +33489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3572/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  24%|▏| 3572/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  24%|▏| 3571/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  24%|▏| 3571/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -33531,8 +33498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3573/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  24%|▏| 3573/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  24%|▏| 3572/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  24%|▏| 3572/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -33540,8 +33507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3574/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  24%|▏| 3574/14932 [05:09<16:24, 11.54it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  24%|▏| 3573/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  24%|▏| 3573/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -33549,8 +33516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3575/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  24%|▏| 3575/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  24%|▏| 3574/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  24%|▏| 3574/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -33558,8 +33525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3576/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  24%|▏| 3576/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  24%|▏| 3575/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  24%|▏| 3575/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -33567,8 +33534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3577/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  24%|▏| 3577/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  24%|▏| 3576/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  24%|▏| 3576/14932 [05:06<16:14, 11.66it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -33576,8 +33543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3578/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  24%|▏| 3578/14932 [05:09<16:23, 11.54it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  24%|▏| 3577/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  24%|▏| 3577/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -33585,8 +33552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3579/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  24%|▏| 3579/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  24%|▏| 3578/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  24%|▏| 3578/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -33594,8 +33561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3580/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  24%|▏| 3580/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  24%|▏| 3579/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  24%|▏| 3579/14932 [05:06<16:13, 11.66it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -33603,8 +33570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3581/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  24%|▏| 3581/14932 [05:10<16:23, 11.55it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  24%|▏| 3580/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  24%|▏| 3580/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -33612,8 +33579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3582/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  24%|▏| 3582/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  24%|▏| 3581/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  24%|▏| 3581/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -33621,8 +33588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3583/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  24%|▏| 3583/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  24%|▏| 3582/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  24%|▏| 3582/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -33630,8 +33597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3584/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  24%|▏| 3584/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  24%|▏| 3583/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  24%|▏| 3583/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -33639,8 +33606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3585/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  24%|▏| 3585/14932 [05:10<16:23, 11.54it/s, v_num=o30c, train/loss=4.91"
+      "Epoch 0:  24%|▏| 3584/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  24%|▏| 3584/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -33648,8 +33615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3586/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=4.91\r",
-      "Epoch 0:  24%|▏| 3586/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  24%|▏| 3585/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  24%|▏| 3585/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -33657,8 +33624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3587/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  24%|▏| 3587/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  24%|▏| 3586/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  24%|▏| 3586/14932 [05:07<16:13, 11.66it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -33666,8 +33633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3588/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  24%|▏| 3588/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  24%|▏| 3587/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  24%|▏| 3587/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -33675,8 +33642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3589/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  24%|▏| 3589/14932 [05:10<16:22, 11.54it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  24%|▏| 3588/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  24%|▏| 3588/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -33684,8 +33651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3590/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  24%|▏| 3590/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  24%|▏| 3589/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  24%|▏| 3589/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -33693,8 +33660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3591/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  24%|▏| 3591/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  24%|▏| 3590/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  24%|▏| 3590/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -33702,8 +33669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3592/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  24%|▏| 3592/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  24%|▏| 3591/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  24%|▏| 3591/14932 [05:07<16:12, 11.66it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -33711,8 +33678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3593/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  24%|▏| 3593/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  24%|▏| 3592/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  24%|▏| 3592/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -33720,8 +33687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3594/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  24%|▏| 3594/14932 [05:11<16:22, 11.54it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  24%|▏| 3593/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  24%|▏| 3593/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -33729,8 +33696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3595/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  24%|▏| 3595/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  24%|▏| 3594/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  24%|▏| 3594/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -33738,8 +33705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3596/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  24%|▏| 3596/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  24%|▏| 3595/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  24%|▏| 3595/14932 [05:08<16:12, 11.66it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -33747,8 +33714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3597/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  24%|▏| 3597/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  24%|▏| 3596/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  24%|▏| 3596/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -33756,8 +33723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3598/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  24%|▏| 3598/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  24%|▏| 3597/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  24%|▏| 3597/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -33765,8 +33732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3599/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  24%|▏| 3599/14932 [05:11<16:21, 11.54it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  24%|▏| 3598/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  24%|▏| 3598/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -33774,8 +33741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3600/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  24%|▏| 3600/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  24%|▏| 3599/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  24%|▏| 3599/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -33783,8 +33750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3601/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  24%|▏| 3601/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  24%|▏| 3600/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  24%|▏| 3600/14932 [05:08<16:11, 11.66it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -33792,8 +33759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3602/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  24%|▏| 3602/14932 [05:11<16:21, 11.55it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  24%|▏| 3601/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  24%|▏| 3601/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -33801,8 +33768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3603/14932 [05:12<16:21, 11.55it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  24%|▏| 3603/14932 [05:12<16:21, 11.55it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  24%|▏| 3602/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  24%|▏| 3602/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -33810,8 +33777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3604/14932 [05:12<16:21, 11.55it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  24%|▏| 3604/14932 [05:12<16:21, 11.55it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  24%|▏| 3603/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  24%|▏| 3603/14932 [05:08<16:11, 11.67it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -33819,8 +33786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3605/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  24%|▏| 3605/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  24%|▏| 3604/14932 [05:08<16:10, 11.67it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  24%|▏| 3604/14932 [05:08<16:10, 11.67it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -33828,8 +33795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3606/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  24%|▏| 3606/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  24%|▏| 3605/14932 [05:08<16:10, 11.67it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  24%|▏| 3605/14932 [05:08<16:10, 11.67it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -33837,8 +33804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3607/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  24%|▏| 3607/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  24%|▏| 3606/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  24%|▏| 3606/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -33846,8 +33813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3608/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  24%|▏| 3608/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  24%|▏| 3607/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  24%|▏| 3607/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -33855,7 +33822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3609/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  24%|▏| 3608/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  24%|▏| 3608/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -33863,7 +33831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3609/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  24%|▏| 3609/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  24%|▏| 3609/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -33871,8 +33840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3610/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  24%|▏| 3610/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  24%|▏| 3610/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  24%|▏| 3610/14932 [05:09<16:10, 11.67it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -33880,8 +33849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3611/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  24%|▏| 3611/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  24%|▏| 3611/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  24%|▏| 3611/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -33889,8 +33858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3612/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  24%|▏| 3612/14932 [05:12<16:20, 11.55it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  24%|▏| 3612/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  24%|▏| 3612/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -33898,8 +33867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3613/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  24%|▏| 3613/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  24%|▏| 3613/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  24%|▏| 3613/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=1.49"
      ]
     },
     {
@@ -33907,7 +33876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3614/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  24%|▏| 3614/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=1.49\r",
+      "Epoch 0:  24%|▏| 3614/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -33915,7 +33885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3614/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  24%|▏| 3615/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  24%|▏| 3615/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -33923,8 +33894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3615/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  24%|▏| 3615/14932 [05:12<16:19, 11.55it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  24%|▏| 3616/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  24%|▏| 3616/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -33932,8 +33903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3616/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  24%|▏| 3616/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  24%|▏| 3617/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  24%|▏| 3617/14932 [05:09<16:09, 11.67it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -33941,8 +33912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3617/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  24%|▏| 3617/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  24%|▏| 3618/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  24%|▏| 3618/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -33950,8 +33921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3618/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  24%|▏| 3618/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  24%|▏| 3619/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  24%|▏| 3619/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -33959,8 +33930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3619/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  24%|▏| 3619/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  24%|▏| 3620/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  24%|▏| 3620/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -33968,8 +33939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3620/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  24%|▏| 3620/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  24%|▏| 3621/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  24%|▏| 3621/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -33977,8 +33948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3621/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  24%|▏| 3621/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  24%|▏| 3622/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  24%|▏| 3622/14932 [05:10<16:09, 11.67it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -33986,8 +33957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3622/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  24%|▏| 3622/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  24%|▏| 3623/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  24%|▏| 3623/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -33995,8 +33966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3623/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  24%|▏| 3623/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  24%|▏| 3624/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  24%|▏| 3624/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -34004,8 +33975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3624/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  24%|▏| 3624/14932 [05:13<16:19, 11.55it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  24%|▏| 3625/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  24%|▏| 3625/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -34013,8 +33984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3625/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  24%|▏| 3625/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  24%|▏| 3626/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  24%|▏| 3626/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -34022,8 +33993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3626/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  24%|▏| 3626/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  24%|▏| 3627/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  24%|▏| 3627/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -34031,8 +34002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3627/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  24%|▏| 3627/14932 [05:13<16:18, 11.55it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  24%|▏| 3628/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  24%|▏| 3628/14932 [05:10<16:08, 11.67it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -34040,8 +34011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3628/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  24%|▏| 3628/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:  24%|▏| 3629/14932 [05:10<16:08, 11.68it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  24%|▏| 3629/14932 [05:10<16:08, 11.68it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -34049,8 +34020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3629/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:  24%|▏| 3629/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  24%|▏| 3630/14932 [05:10<16:08, 11.68it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  24%|▏| 3630/14932 [05:10<16:08, 11.68it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -34058,8 +34029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3630/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  24%|▏| 3630/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  24%|▏| 3631/14932 [05:10<16:07, 11.68it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  24%|▏| 3631/14932 [05:10<16:07, 11.68it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -34067,8 +34038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3631/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  24%|▏| 3631/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  24%|▏| 3632/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  24%|▏| 3632/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -34076,8 +34047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3632/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  24%|▏| 3632/14932 [05:14<16:18, 11.55it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  24%|▏| 3633/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  24%|▏| 3633/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -34085,8 +34056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3633/14932 [05:14<16:17, 11.55it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  24%|▏| 3633/14932 [05:14<16:17, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  24%|▏| 3634/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  24%|▏| 3634/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -34094,8 +34065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3634/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  24%|▏| 3634/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  24%|▏| 3635/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  24%|▏| 3635/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -34103,8 +34074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3635/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  24%|▏| 3635/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  24%|▏| 3636/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  24%|▏| 3636/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -34112,8 +34083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3636/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  24%|▏| 3636/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  24%|▏| 3637/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  24%|▏| 3637/14932 [05:11<16:07, 11.68it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -34121,8 +34092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3637/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  24%|▏| 3637/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  24%|▏| 3638/14932 [05:11<16:08, 11.66it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  24%|▏| 3638/14932 [05:11<16:08, 11.66it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -34130,8 +34101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3638/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  24%|▏| 3638/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  24%|▏| 3639/14932 [05:11<16:08, 11.66it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  24%|▏| 3639/14932 [05:11<16:08, 11.66it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -34139,8 +34110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3639/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  24%|▏| 3639/14932 [05:14<16:17, 11.56it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  24%|▏| 3640/14932 [05:12<16:08, 11.66it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  24%|▏| 3640/14932 [05:12<16:08, 11.66it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -34148,8 +34119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3640/14932 [05:14<16:16, 11.56it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  24%|▏| 3640/14932 [05:14<16:16, 11.56it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  24%|▏| 3641/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  24%|▏| 3641/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -34157,8 +34128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3641/14932 [05:14<16:16, 11.56it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  24%|▏| 3641/14932 [05:14<16:16, 11.56it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  24%|▏| 3642/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  24%|▏| 3642/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -34166,8 +34137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3642/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  24%|▏| 3642/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  24%|▏| 3643/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  24%|▏| 3643/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -34175,8 +34146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3643/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  24%|▏| 3643/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  24%|▏| 3644/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  24%|▏| 3644/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -34184,8 +34155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3644/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  24%|▏| 3644/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=1.44"
+      "Epoch 0:  24%|▏| 3645/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  24%|▏| 3645/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -34193,8 +34164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3645/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=1.44\r",
-      "Epoch 0:  24%|▏| 3645/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  24%|▏| 3646/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  24%|▏| 3646/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -34202,8 +34173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3646/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  24%|▏| 3646/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  24%|▏| 3647/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  24%|▏| 3647/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -34211,8 +34182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3647/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  24%|▏| 3647/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  24%|▏| 3648/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  24%|▏| 3648/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -34220,8 +34191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3648/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  24%|▏| 3648/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  24%|▏| 3649/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  24%|▏| 3649/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -34229,8 +34200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3649/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  24%|▏| 3649/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  24%|▏| 3650/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  24%|▏| 3650/14932 [05:12<16:07, 11.66it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -34238,8 +34209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3650/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  24%|▏| 3650/14932 [05:15<16:16, 11.56it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  24%|▏| 3651/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  24%|▏| 3651/14932 [05:12<16:07, 11.67it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -34247,8 +34218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3651/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  24%|▏| 3651/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  24%|▏| 3652/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  24%|▏| 3652/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -34256,8 +34227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3652/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  24%|▏| 3652/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  24%|▏| 3653/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  24%|▏| 3653/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -34265,8 +34236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3653/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  24%|▏| 3653/14932 [05:15<16:15, 11.56it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  24%|▏| 3654/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  24%|▏| 3654/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -34274,8 +34245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3654/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  24%|▏| 3654/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  24%|▏| 3655/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  24%|▏| 3655/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -34283,8 +34254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3655/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  24%|▏| 3655/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  24%|▏| 3656/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  24%|▏| 3656/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -34292,8 +34263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3656/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  24%|▏| 3656/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  24%|▏| 3657/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  24%|▏| 3657/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -34301,8 +34272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3657/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  24%|▏| 3657/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  24%|▏| 3658/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  24%|▏| 3658/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -34310,8 +34281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  24%|▏| 3658/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  24%|▏| 3658/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  25%|▏| 3659/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  25%|▏| 3659/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -34319,8 +34290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3659/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  25%|▏| 3659/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  25%|▏| 3660/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  25%|▏| 3660/14932 [05:13<16:06, 11.67it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -34328,8 +34299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3660/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  25%|▏| 3660/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  25%|▏| 3661/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  25%|▏| 3661/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -34337,8 +34308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3661/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  25%|▏| 3661/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  25%|▏| 3662/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  25%|▏| 3662/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -34346,8 +34317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3662/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  25%|▏| 3662/14932 [05:16<16:14, 11.56it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  25%|▏| 3663/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  25%|▏| 3663/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -34355,8 +34326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3663/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  25%|▏| 3663/14932 [05:16<16:15, 11.56it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  25%|▏| 3664/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  25%|▏| 3664/14932 [05:13<16:05, 11.67it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -34364,8 +34335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3664/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  25%|▏| 3664/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  25%|▏| 3665/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  25%|▏| 3665/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -34373,8 +34344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3665/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  25%|▏| 3665/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  25%|▏| 3666/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  25%|▏| 3666/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -34382,8 +34353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3666/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  25%|▏| 3666/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  25%|▏| 3667/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  25%|▏| 3667/14932 [05:14<16:05, 11.67it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -34391,8 +34362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3667/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  25%|▏| 3667/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  25%|▏| 3668/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  25%|▏| 3668/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -34400,8 +34371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3668/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  25%|▏| 3668/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  25%|▏| 3669/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  25%|▏| 3669/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=1.15"
      ]
     },
     {
@@ -34409,8 +34380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3669/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  25%|▏| 3669/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  25%|▏| 3670/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=1.15\r",
+      "Epoch 0:  25%|▏| 3670/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -34418,8 +34389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3670/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  25%|▏| 3670/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  25%|▏| 3671/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  25%|▏| 3671/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -34427,8 +34398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3671/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  25%|▏| 3671/14932 [05:17<16:14, 11.56it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  25%|▏| 3672/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  25%|▏| 3672/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -34436,8 +34407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3672/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  25%|▏| 3672/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  25%|▏| 3673/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  25%|▏| 3673/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -34445,8 +34416,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3673/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  25%|▏| 3673/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  25%|▏| 3674/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -34454,8 +34424,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3674/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  25%|▏| 3674/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  25%|▏| 3674/14932 [05:14<16:04, 11.68it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -34463,8 +34432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3675/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  25%|▏| 3675/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  25%|▏| 3675/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  25%|▏| 3675/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -34472,8 +34441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3676/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  25%|▏| 3676/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  25%|▏| 3676/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  25%|▏| 3676/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -34481,8 +34450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3677/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  25%|▏| 3677/14932 [05:17<16:13, 11.56it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  25%|▏| 3677/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  25%|▏| 3677/14932 [05:14<16:04, 11.67it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -34490,8 +34459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3678/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  25%|▏| 3678/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  25%|▏| 3678/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  25%|▏| 3678/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -34499,8 +34468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3679/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  25%|▏| 3679/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  25%|▏| 3679/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  25%|▏| 3679/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -34508,8 +34477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3680/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  25%|▏| 3680/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  25%|▏| 3680/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  25%|▏| 3680/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -34517,8 +34486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3681/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  25%|▏| 3681/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  25%|▏| 3681/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  25%|▏| 3681/14932 [05:15<16:04, 11.67it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -34526,7 +34495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3682/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  25%|▏| 3682/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  25%|▏| 3682/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -34534,7 +34504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3682/14932 [05:18<16:13, 11.56it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  25%|▏| 3683/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  25%|▏| 3683/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -34542,8 +34513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3683/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  25%|▏| 3683/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  25%|▏| 3684/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  25%|▏| 3684/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -34551,8 +34522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3684/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  25%|▏| 3684/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  25%|▏| 3685/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  25%|▏| 3685/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -34560,8 +34531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3685/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  25%|▏| 3685/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  25%|▏| 3686/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  25%|▏| 3686/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -34569,8 +34540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3686/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  25%|▏| 3686/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  25%|▏| 3687/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  25%|▏| 3687/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=1.26"
      ]
     },
     {
@@ -34578,8 +34549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3687/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  25%|▏| 3687/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=1.32"
+      "Epoch 0:  25%|▏| 3688/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=1.26\r",
+      "Epoch 0:  25%|▏| 3688/14932 [05:15<16:03, 11.67it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -34587,8 +34558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3688/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=1.32\r",
-      "Epoch 0:  25%|▏| 3688/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  25%|▏| 3689/14932 [05:16<16:03, 11.67it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  25%|▏| 3689/14932 [05:16<16:03, 11.67it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -34596,8 +34567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3689/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  25%|▏| 3689/14932 [05:18<16:12, 11.56it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  25%|▏| 3690/14932 [05:16<16:03, 11.67it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  25%|▏| 3690/14932 [05:16<16:03, 11.67it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -34605,8 +34576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3690/14932 [05:19<16:12, 11.57it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  25%|▏| 3690/14932 [05:19<16:12, 11.57it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  25%|▏| 3691/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  25%|▏| 3691/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -34614,8 +34585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3691/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  25%|▏| 3691/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  25%|▏| 3692/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  25%|▏| 3692/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -34623,8 +34594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3692/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  25%|▏| 3692/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=0.96"
+      "Epoch 0:  25%|▏| 3693/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  25%|▏| 3693/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -34632,8 +34603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3693/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=0.96\r",
-      "Epoch 0:  25%|▏| 3693/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  25%|▏| 3694/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  25%|▏| 3694/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -34641,8 +34612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3694/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  25%|▏| 3694/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  25%|▏| 3695/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  25%|▏| 3695/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -34650,8 +34621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3695/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  25%|▏| 3695/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  25%|▏| 3696/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  25%|▏| 3696/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -34659,8 +34630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3696/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  25%|▏| 3696/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  25%|▏| 3697/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  25%|▏| 3697/14932 [05:16<16:02, 11.67it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -34668,8 +34639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3697/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  25%|▏| 3697/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  25%|▏| 3698/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  25%|▏| 3698/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=1.49"
      ]
     },
     {
@@ -34677,8 +34648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3698/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  25%|▏| 3698/14932 [05:19<16:11, 11.57it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  25%|▏| 3699/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=1.49\r",
+      "Epoch 0:  25%|▏| 3699/14932 [05:16<16:02, 11.68it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -34686,8 +34657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3699/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  25%|▏| 3699/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  25%|▏| 3700/14932 [05:16<16:01, 11.68it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  25%|▏| 3700/14932 [05:16<16:01, 11.68it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -34695,8 +34666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3700/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  25%|▏| 3700/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  25%|▏| 3701/14932 [05:16<16:01, 11.68it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  25%|▏| 3701/14932 [05:16<16:01, 11.68it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -34704,8 +34675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3701/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  25%|▏| 3701/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  25%|▏| 3702/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  25%|▏| 3702/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -34713,8 +34684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3702/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  25%|▏| 3702/14932 [05:19<16:10, 11.57it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  25%|▏| 3703/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  25%|▏| 3703/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -34722,8 +34693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3703/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  25%|▏| 3703/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  25%|▏| 3704/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  25%|▏| 3704/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -34731,8 +34702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3704/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  25%|▏| 3704/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  25%|▏| 3705/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  25%|▏| 3705/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -34740,8 +34711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3705/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  25%|▏| 3705/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  25%|▏| 3706/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  25%|▏| 3706/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -34749,8 +34720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3706/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  25%|▏| 3706/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  25%|▏| 3707/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  25%|▏| 3707/14932 [05:17<16:01, 11.68it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -34758,8 +34729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3707/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  25%|▏| 3707/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  25%|▏| 3708/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  25%|▏| 3708/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -34767,8 +34738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3708/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  25%|▏| 3708/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  25%|▏| 3709/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  25%|▏| 3709/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -34776,8 +34747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3709/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  25%|▏| 3709/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  25%|▏| 3710/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  25%|▏| 3710/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -34785,8 +34756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3710/14932 [05:20<16:09, 11.57it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  25%|▏| 3710/14932 [05:20<16:09, 11.57it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  25%|▏| 3711/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  25%|▏| 3711/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -34794,8 +34765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3711/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  25%|▏| 3711/14932 [05:20<16:10, 11.57it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  25%|▏| 3712/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  25%|▏| 3712/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -34803,8 +34774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3712/14932 [05:20<16:10, 11.56it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  25%|▏| 3712/14932 [05:21<16:10, 11.56it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  25%|▏| 3713/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  25%|▏| 3713/14932 [05:17<16:00, 11.68it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -34812,8 +34783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3713/14932 [05:21<16:10, 11.56it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  25%|▏| 3713/14932 [05:21<16:10, 11.56it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  25%|▏| 3714/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  25%|▏| 3714/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -34821,8 +34792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3714/14932 [05:21<16:10, 11.56it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  25%|▏| 3714/14932 [05:21<16:10, 11.56it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  25%|▏| 3715/14932 [05:18<16:01, 11.67it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  25%|▏| 3715/14932 [05:18<16:01, 11.67it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -34830,8 +34801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3715/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  25%|▏| 3715/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  25%|▏| 3716/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  25%|▏| 3716/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -34839,8 +34810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3716/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  25%|▏| 3716/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  25%|▏| 3717/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  25%|▏| 3717/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -34848,8 +34819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3717/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  25%|▏| 3717/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  25%|▏| 3718/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  25%|▏| 3718/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -34857,8 +34828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3718/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  25%|▏| 3718/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  25%|▏| 3719/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  25%|▏| 3719/14932 [05:18<16:00, 11.67it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -34866,8 +34837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3719/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  25%|▏| 3719/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  25%|▏| 3720/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  25%|▏| 3720/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -34875,8 +34846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3720/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  25%|▏| 3720/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:  25%|▏| 3721/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  25%|▏| 3721/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -34884,8 +34855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3721/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:  25%|▏| 3721/14932 [05:21<16:09, 11.57it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  25%|▏| 3722/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  25%|▏| 3722/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -34893,8 +34864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3722/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  25%|��| 3722/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  25%|▏| 3723/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  25%|▏| 3723/14932 [05:18<16:00, 11.68it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -34902,8 +34873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3723/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  25%|▏| 3723/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  25%|▏| 3724/14932 [05:18<15:59, 11.68it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  25%|▏| 3724/14932 [05:18<15:59, 11.68it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -34911,8 +34882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3724/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  25%|▏| 3724/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  25%|▏| 3725/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  25%|▏| 3725/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -34920,8 +34891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3725/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  25%|▏| 3725/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  25%|▏| 3726/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  25%|▏| 3726/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -34929,8 +34900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3726/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  25%|▏| 3726/14932 [05:21<16:08, 11.57it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  25%|▏| 3727/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  25%|▏| 3727/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -34938,8 +34909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3727/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  25%|▏| 3727/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  25%|▏| 3728/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  25%|▏| 3728/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -34947,8 +34918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3728/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  25%|▏| 3728/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  25%|▏| 3729/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  25%|▏| 3729/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -34956,8 +34927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3729/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  25%|▏| 3729/14932 [05:22<16:08, 11.57it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  25%|▏| 3730/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  25%|▏| 3730/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -34965,8 +34936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3730/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  25%|▏| 3730/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  25%|▏| 3731/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  25%|▏| 3731/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -34974,8 +34945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3731/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  25%|▏| 3731/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  25%|▏| 3732/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  25%|▏| 3732/14932 [05:19<15:59, 11.68it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -34983,8 +34954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▏| 3732/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  25%|▏| 3732/14932 [05:22<16:07, 11.57it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  25%|▎| 3733/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  25%|▎| 3733/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -34992,8 +34963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3733/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  25%|▎| 3733/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  25%|▎| 3734/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  25%|▎| 3734/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -35001,8 +34972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3734/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  25%|▎| 3734/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  25%|▎| 3735/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  25%|▎| 3735/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -35010,8 +34981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3735/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  25%|▎| 3735/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  25%|▎| 3736/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  25%|▎| 3736/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -35019,8 +34990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3736/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  25%|▎| 3736/14932 [05:22<16:07, 11.58it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  25%|▎| 3737/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  25%|▎| 3737/14932 [05:19<15:58, 11.68it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -35028,8 +34999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3737/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  25%|▎| 3737/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  25%|▎| 3738/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  25%|▎| 3738/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -35037,8 +35008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3738/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  25%|▎| 3738/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  25%|▎| 3739/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  25%|▎| 3739/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -35046,8 +35017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3739/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  25%|▎| 3739/14932 [05:22<16:06, 11.58it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  25%|▎| 3740/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  25%|▎| 3740/14932 [05:20<15:58, 11.68it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -35055,8 +35026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3740/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  25%|▎| 3740/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  25%|▎| 3741/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  25%|▎| 3741/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -35064,8 +35035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3741/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  25%|▎| 3741/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  25%|▎| 3742/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  25%|▎| 3742/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=1.26"
      ]
     },
     {
@@ -35073,8 +35044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3742/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  25%|▎| 3742/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  25%|▎| 3743/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=1.26\r",
+      "Epoch 0:  25%|▎| 3743/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -35082,8 +35053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3743/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  25%|▎| 3743/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  25%|▎| 3744/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  25%|▎| 3744/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -35091,8 +35062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3744/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  25%|▎| 3744/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  25%|▎| 3745/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  25%|▎| 3745/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -35100,8 +35071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3745/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  25%|▎| 3745/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  25%|▎| 3746/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  25%|▎| 3746/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -35109,8 +35080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3746/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  25%|▎| 3746/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  25%|▎| 3747/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  25%|▎| 3747/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -35118,8 +35089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3747/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  25%|▎| 3747/14932 [05:23<16:06, 11.58it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  25%|▎| 3748/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  25%|▎| 3748/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -35127,8 +35098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3748/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  25%|▎| 3748/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  25%|▎| 3749/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  25%|▎| 3749/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -35136,8 +35107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3749/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  25%|▎| 3749/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  25%|▎| 3750/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  25%|▎| 3750/14932 [05:20<15:57, 11.68it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -35145,8 +35116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3750/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  25%|▎| 3750/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  25%|▎| 3751/14932 [05:21<15:56, 11.68it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  25%|▎| 3751/14932 [05:21<15:56, 11.68it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -35154,8 +35125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3751/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  25%|▎| 3751/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  25%|▎| 3752/14932 [05:21<15:56, 11.68it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  25%|▎| 3752/14932 [05:21<15:56, 11.68it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -35163,8 +35134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3752/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  25%|▎| 3752/14932 [05:23<16:05, 11.58it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  25%|▎| 3753/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  25%|▎| 3753/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -35172,8 +35143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3753/14932 [05:24<16:05, 11.58it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  25%|▎| 3753/14932 [05:24<16:05, 11.58it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  25%|▎| 3754/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  25%|▎| 3754/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -35181,8 +35152,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3754/14932 [05:24<16:05, 11.58it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  25%|▎| 3754/14932 [05:24<16:05, 11.58it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  25%|▎| 3755/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -35190,8 +35160,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3755/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  25%|▎| 3755/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  25%|▎| 3755/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -35199,8 +35168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3756/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  25%|▎| 3756/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  25%|▎| 3756/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  25%|▎| 3756/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -35208,8 +35177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3757/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  25%|▎| 3757/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  25%|▎| 3757/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  25%|▎| 3757/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -35217,8 +35186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3758/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  25%|▎| 3758/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  25%|▎| 3758/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  25%|▎| 3758/14932 [05:21<15:56, 11.69it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -35226,8 +35195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3759/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  25%|▎| 3759/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  25%|▎| 3759/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  25%|▎| 3759/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -35235,8 +35204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3760/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  25%|▎| 3760/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  25%|▎| 3760/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  25%|▎| 3760/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -35244,8 +35213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3761/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  25%|▎| 3761/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  25%|▎| 3761/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  25%|▎| 3761/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -35253,8 +35222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3762/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  25%|▎| 3762/14932 [05:24<16:04, 11.58it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  25%|▎| 3762/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  25%|▎| 3762/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -35262,8 +35231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3763/14932 [05:24<16:04, 11.59it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  25%|▎| 3763/14932 [05:24<16:04, 11.59it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  25%|▎| 3763/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  25%|▎| 3763/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -35271,8 +35240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3764/14932 [05:24<16:03, 11.59it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  25%|▎| 3764/14932 [05:24<16:03, 11.59it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  25%|▎| 3764/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  25%|▎| 3764/14932 [05:21<15:55, 11.69it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -35280,8 +35249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3765/14932 [05:24<16:03, 11.59it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  25%|▎| 3765/14932 [05:24<16:03, 11.59it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  25%|▎| 3765/14932 [05:22<15:55, 11.69it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  25%|▎| 3765/14932 [05:22<15:55, 11.69it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -35289,8 +35258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3766/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  25%|▎| 3766/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  25%|▎| 3766/14932 [05:22<15:55, 11.69it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  25%|▎| 3766/14932 [05:22<15:55, 11.69it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -35298,8 +35267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3767/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  25%|▎| 3767/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  25%|▎| 3767/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  25%|▎| 3767/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=0.92"
      ]
     },
     {
@@ -35307,8 +35276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3768/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  25%|▎| 3768/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  25%|▎| 3768/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=0.92\r",
+      "Epoch 0:  25%|▎| 3768/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -35316,8 +35285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3769/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  25%|▎| 3769/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  25%|▎| 3769/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  25%|▎| 3769/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -35325,8 +35294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3770/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  25%|▎| 3770/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=0.90"
+      "Epoch 0:  25%|▎| 3770/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  25%|▎| 3770/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -35334,8 +35303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3771/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=0.90\r",
-      "Epoch 0:  25%|▎| 3771/14932 [05:25<16:03, 11.59it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  25%|▎| 3771/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  25%|▎| 3771/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -35343,8 +35312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3772/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  25%|▎| 3772/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  25%|▎| 3772/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  25%|▎| 3772/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -35352,8 +35321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3773/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  25%|▎| 3773/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  25%|▎| 3773/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  25%|▎| 3773/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -35361,8 +35330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3774/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  25%|▎| 3774/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  25%|▎| 3774/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  25%|▎| 3774/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -35370,8 +35339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3775/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  25%|▎| 3775/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  25%|▎| 3775/14932 [05:22<15:53, 11.70it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  25%|▎| 3775/14932 [05:22<15:53, 11.70it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -35379,8 +35348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3776/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  25%|▎| 3776/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  25%|▎| 3776/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  25%|▎| 3776/14932 [05:22<15:54, 11.69it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -35388,8 +35357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3777/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  25%|▎| 3777/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  25%|▎| 3777/14932 [05:23<15:54, 11.69it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  25%|▎| 3777/14932 [05:23<15:54, 11.69it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -35397,8 +35366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3778/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  25%|▎| 3778/14932 [05:25<16:02, 11.59it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  25%|▎| 3778/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  25%|▎| 3778/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -35406,8 +35375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3779/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  25%|▎| 3779/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  25%|▎| 3779/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  25%|▎| 3779/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -35415,8 +35384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3780/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  25%|▎| 3780/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  25%|▎| 3780/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  25%|▎| 3780/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -35424,8 +35393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3781/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  25%|▎| 3781/14932 [05:26<16:02, 11.59it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  25%|▎| 3781/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  25%|▎| 3781/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -35433,8 +35402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3782/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  25%|▎| 3782/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  25%|▎| 3782/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  25%|▎| 3782/14932 [05:23<15:53, 11.69it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -35442,8 +35411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3783/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  25%|▎| 3783/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  25%|▎| 3783/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  25%|▎| 3783/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -35451,8 +35420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3784/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  25%|▎| 3784/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  25%|▎| 3784/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  25%|▎| 3784/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -35460,8 +35429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3785/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  25%|▎| 3785/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  25%|▎| 3785/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  25%|▎| 3785/14932 [05:23<15:53, 11.70it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -35469,8 +35438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3786/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  25%|▎| 3786/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  25%|▎| 3786/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  25%|▎| 3786/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -35478,8 +35447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3787/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  25%|▎| 3787/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  25%|▎| 3787/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  25%|▎| 3787/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -35487,8 +35456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3788/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  25%|▎| 3788/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  25%|▎| 3788/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  25%|▎| 3788/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -35496,8 +35465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3789/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  25%|▎| 3789/14932 [05:26<16:01, 11.59it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  25%|▎| 3789/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  25%|▎| 3789/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -35505,8 +35474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3790/14932 [05:26<16:00, 11.59it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  25%|▎| 3790/14932 [05:26<16:00, 11.59it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  25%|▎| 3790/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  25%|▎| 3790/14932 [05:23<15:52, 11.70it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -35514,8 +35483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3791/14932 [05:26<16:00, 11.60it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  25%|▎| 3791/14932 [05:26<16:00, 11.60it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  25%|▎| 3791/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  25%|▎| 3791/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -35523,8 +35492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3792/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  25%|▎| 3792/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  25%|▎| 3792/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  25%|▎| 3792/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -35532,8 +35501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3793/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  25%|▎| 3793/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  25%|▎| 3793/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  25%|▎| 3793/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -35541,8 +35510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3794/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  25%|▎| 3794/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  25%|▎| 3794/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  25%|▎| 3794/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -35550,8 +35519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3795/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  25%|▎| 3795/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  25%|▎| 3795/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  25%|▎| 3795/14932 [05:24<15:52, 11.70it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -35559,8 +35528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3796/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  25%|▎| 3796/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  25%|▎| 3796/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  25%|▎| 3796/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -35568,8 +35537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3797/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  25%|▎| 3797/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=1.09"
+      "Epoch 0:  25%|▎| 3797/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  25%|▎| 3797/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -35577,8 +35546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3798/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=1.09\r",
-      "Epoch 0:  25%|▎| 3798/14932 [05:27<16:00, 11.60it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  25%|▎| 3798/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  25%|▎| 3798/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -35586,8 +35555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3799/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  25%|▎| 3799/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  25%|▎| 3799/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  25%|▎| 3799/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -35595,8 +35564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3800/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  25%|▎| 3800/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  25%|▎| 3800/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  25%|▎| 3800/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -35604,8 +35573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3801/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  25%|▎| 3801/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  25%|▎| 3801/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  25%|▎| 3801/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -35613,8 +35582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3802/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  25%|▎| 3802/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  25%|▎| 3802/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  25%|▎| 3802/14932 [05:24<15:51, 11.70it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -35622,8 +35591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3803/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  25%|▎| 3803/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  25%|▎| 3803/14932 [05:25<15:51, 11.70it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  25%|▎| 3803/14932 [05:25<15:51, 11.70it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -35631,8 +35600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3804/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  25%|▎| 3804/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  25%|▎| 3804/14932 [05:25<15:51, 11.70it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  25%|▎| 3804/14932 [05:25<15:51, 11.70it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -35640,8 +35609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3805/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  25%|▎| 3805/14932 [05:27<15:59, 11.60it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  25%|▎| 3805/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  25%|▎| 3805/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -35649,8 +35618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3806/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  25%|▎| 3806/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  25%|▎| 3806/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  25%|▎| 3806/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -35658,8 +35627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  25%|▎| 3807/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  25%|▎| 3807/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  25%|▎| 3807/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  25%|▎| 3807/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -35667,8 +35636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3808/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  26%|▎| 3808/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  26%|▎| 3808/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  26%|▎| 3808/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -35676,8 +35645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3809/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  26%|▎| 3809/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  26%|▎| 3809/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  26%|▎| 3809/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -35685,8 +35654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3810/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  26%|▎| 3810/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  26%|▎| 3810/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  26%|▎| 3810/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -35694,8 +35663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3811/14932 [05:28<15:59, 11.59it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  26%|▎| 3811/14932 [05:28<15:59, 11.59it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  26%|▎| 3811/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  26%|▎| 3811/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -35703,8 +35672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3812/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  26%|▎| 3812/14932 [05:28<15:59, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  26%|▎| 3812/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  26%|▎| 3812/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -35712,8 +35681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3813/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  26%|▎| 3813/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  26%|▎| 3813/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  26%|▎| 3813/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -35721,8 +35690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3814/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  26%|▎| 3814/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  26%|▎| 3814/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  26%|▎| 3814/14932 [05:25<15:50, 11.70it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -35730,8 +35699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3815/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  26%|▎| 3815/14932 [05:28<15:58, 11.60it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  26%|▎| 3815/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  26%|▎| 3815/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -35739,8 +35708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3816/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  26%|▎| 3816/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  26%|▎| 3816/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  26%|▎| 3816/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -35748,8 +35717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3817/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  26%|▎| 3817/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  26%|▎| 3817/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  26%|▎| 3817/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -35757,8 +35726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3818/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  26%|▎| 3818/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  26%|▎| 3818/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  26%|▎| 3818/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -35766,8 +35735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3819/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  26%|▎| 3819/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  26%|▎| 3819/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  26%|▎| 3819/14932 [05:26<15:49, 11.70it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -35775,8 +35744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3820/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  26%|▎| 3820/14932 [05:29<15:58, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  26%|▎| 3820/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  26%|▎| 3820/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -35784,8 +35753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3821/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  26%|▎| 3821/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:  26%|▎| 3821/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  26%|▎| 3821/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -35793,8 +35762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3822/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:  26%|▎| 3822/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  26%|▎| 3822/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  26%|▎| 3822/14932 [05:26<15:49, 11.71it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -35802,8 +35771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3823/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  26%|▎| 3823/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  26%|▎| 3823/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  26%|▎| 3823/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -35811,8 +35780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3824/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  26%|▎| 3824/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  26%|▎| 3824/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  26%|▎| 3824/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -35820,8 +35789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3825/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  26%|▎| 3825/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  26%|▎| 3825/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  26%|▎| 3825/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -35829,8 +35798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3826/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  26%|▎| 3826/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  26%|▎| 3826/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  26%|▎| 3826/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -35838,8 +35807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3827/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  26%|▎| 3827/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  26%|▎| 3827/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  26%|▎| 3827/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=0.97"
      ]
     },
     {
@@ -35847,8 +35816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3828/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  26%|▎| 3828/14932 [05:29<15:57, 11.60it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  26%|▎| 3828/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=0.97\r",
+      "Epoch 0:  26%|▎| 3828/14932 [05:26<15:48, 11.71it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -35856,8 +35825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3829/14932 [05:29<15:56, 11.60it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  26%|▎| 3829/14932 [05:29<15:56, 11.60it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  26%|▎| 3829/14932 [05:27<15:48, 11.71it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  26%|▎| 3829/14932 [05:27<15:48, 11.71it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -35865,8 +35834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3830/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  26%|▎| 3830/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  26%|▎| 3830/14932 [05:27<15:48, 11.71it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  26%|▎| 3830/14932 [05:27<15:48, 11.71it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -35874,8 +35843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3831/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  26%|▎| 3831/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  26%|▎| 3831/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  26%|▎| 3831/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -35883,8 +35852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3832/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  26%|▎| 3832/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  26%|▎| 3832/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  26%|▎| 3832/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -35892,8 +35861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3833/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  26%|▎| 3833/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  26%|▎| 3833/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  26%|▎| 3833/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -35901,8 +35870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3834/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  26%|▎| 3834/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  26%|▎| 3834/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  26%|▎| 3834/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -35910,8 +35879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3835/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  26%|▎| 3835/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  26%|▎| 3835/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  26%|▎| 3835/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -35919,8 +35888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3836/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  26%|▎| 3836/14932 [05:30<15:56, 11.61it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  26%|▎| 3836/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  26%|▎| 3836/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -35928,8 +35897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3837/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  26%|▎| 3837/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  26%|▎| 3837/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  26%|▎| 3837/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -35937,8 +35906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3838/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  26%|▎| 3838/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  26%|▎| 3838/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  26%|▎| 3838/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -35946,8 +35915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3839/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  26%|▎| 3839/14932 [05:30<15:56, 11.60it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  26%|▎| 3839/14932 [05:27<15:46, 11.71it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  26%|▎| 3839/14932 [05:27<15:46, 11.71it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -35955,8 +35924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3840/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  26%|▎| 3840/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  26%|▎| 3840/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  26%|▎| 3840/14932 [05:27<15:47, 11.71it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -35964,8 +35933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3841/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  26%|▎| 3841/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  26%|▎| 3841/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  26%|▎| 3841/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -35973,8 +35942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3842/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  26%|▎| 3842/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  26%|▎| 3842/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  26%|▎| 3842/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -35982,8 +35951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3843/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  26%|▎| 3843/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  26%|▎| 3843/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  26%|▎| 3843/14932 [05:28<15:47, 11.71it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -35991,8 +35960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3844/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  26%|▎| 3844/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  26%|▎| 3844/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  26%|▎| 3844/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -36000,8 +35969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3845/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  26%|▎| 3845/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  26%|▎| 3845/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  26%|▎| 3845/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -36009,8 +35978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3846/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  26%|▎| 3846/14932 [05:31<15:56, 11.59it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  26%|▎| 3846/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  26%|▎| 3846/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -36018,8 +35987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3847/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  26%|▎| 3847/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  26%|▎| 3847/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:  26%|▎| 3847/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -36027,8 +35996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3848/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  26%|▎| 3848/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  26%|▎| 3848/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  26%|▎| 3848/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -36036,8 +36005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3849/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  26%|▎| 3849/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  26%|▎| 3849/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  26%|▎| 3849/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -36045,8 +36014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3850/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  26%|▎| 3850/14932 [05:31<15:55, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  26%|▎| 3850/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  26%|▎| 3850/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -36054,8 +36023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3851/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  26%|▎| 3851/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  26%|▎| 3851/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  26%|▎| 3851/14932 [05:28<15:46, 11.71it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -36063,8 +36032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3852/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  26%|▎| 3852/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  26%|▎| 3852/14932 [05:28<15:45, 11.71it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  26%|▎| 3852/14932 [05:28<15:45, 11.71it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -36072,8 +36041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3853/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  26%|▎| 3853/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  26%|▎| 3853/14932 [05:28<15:45, 11.71it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  26%|▎| 3853/14932 [05:28<15:45, 11.71it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -36081,8 +36050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3854/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  26%|▎| 3854/14932 [05:32<15:55, 11.60it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  26%|▎| 3854/14932 [05:29<15:45, 11.71it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  26%|▎| 3854/14932 [05:29<15:45, 11.71it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -36090,8 +36059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3855/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  26%|▎| 3855/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  26%|▎| 3855/14932 [05:29<15:45, 11.71it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  26%|▎| 3855/14932 [05:29<15:45, 11.71it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -36099,8 +36068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3856/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  26%|▎| 3856/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  26%|▎| 3856/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  26%|▎| 3856/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -36108,8 +36077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3857/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  26%|▎| 3857/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  26%|▎| 3857/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  26%|▎| 3857/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -36117,8 +36086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3858/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  26%|▎| 3858/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  26%|▎| 3858/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  26%|▎| 3858/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -36126,8 +36095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3859/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  26%|▎| 3859/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  26%|▎| 3859/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  26%|▎| 3859/14932 [05:29<15:45, 11.72it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -36135,8 +36104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3860/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  26%|▎| 3860/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  26%|▎| 3860/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  26%|▎| 3860/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -36144,8 +36113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3861/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  26%|▎| 3861/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  26%|▎| 3861/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  26%|▎| 3861/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=1.86"
      ]
     },
     {
@@ -36153,8 +36122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3862/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  26%|▎| 3862/14932 [05:32<15:54, 11.60it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  26%|▎| 3862/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=1.86\r",
+      "Epoch 0:  26%|▎| 3862/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -36162,8 +36131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3863/14932 [05:32<15:53, 11.60it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  26%|▎| 3863/14932 [05:32<15:53, 11.60it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  26%|▎| 3863/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  26%|▎| 3863/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -36171,8 +36140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3864/14932 [05:32<15:53, 11.60it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  26%|▎| 3864/14932 [05:32<15:53, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  26%|▎| 3864/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  26%|▎| 3864/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -36180,8 +36149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3865/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  26%|▎| 3865/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  26%|▎| 3865/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  26%|▎| 3865/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -36189,8 +36158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3866/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  26%|▎| 3866/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  26%|▎| 3866/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  26%|▎| 3866/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -36198,8 +36167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3867/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  26%|▎| 3867/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  26%|▎| 3867/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  26%|▎| 3867/14932 [05:29<15:44, 11.72it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -36207,8 +36176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3868/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  26%|▎| 3868/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  26%|▎| 3868/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  26%|▎| 3868/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -36216,8 +36185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3869/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  26%|▎| 3869/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  26%|▎| 3869/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  26%|▎| 3869/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=0.87"
      ]
     },
     {
@@ -36225,8 +36194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3870/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  26%|▎| 3870/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  26%|▎| 3870/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=0.87\r",
+      "Epoch 0:  26%|▎| 3870/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -36234,8 +36203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3871/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  26%|▎| 3871/14932 [05:33<15:53, 11.61it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  26%|▎| 3871/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  26%|▎| 3871/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=0.80"
      ]
     },
     {
@@ -36243,8 +36212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3872/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  26%|▎| 3872/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  26%|▎| 3872/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=0.80\r",
+      "Epoch 0:  26%|▎| 3872/14932 [05:30<15:44, 11.72it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -36252,8 +36221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3873/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  26%|▎| 3873/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  26%|▎| 3873/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  26%|▎| 3873/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -36261,8 +36230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3874/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  26%|▎| 3874/14932 [05:33<15:53, 11.60it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  26%|▎| 3874/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  26%|▎| 3874/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -36270,8 +36239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3875/14932 [05:33<15:52, 11.60it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  26%|▎| 3875/14932 [05:33<15:52, 11.60it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  26%|▎| 3875/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  26%|▎| 3875/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=0.99"
      ]
     },
     {
@@ -36279,8 +36248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3876/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  26%|▎| 3876/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  26%|▎| 3876/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=0.99\r",
+      "Epoch 0:  26%|▎| 3876/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -36288,8 +36257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3877/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  26%|▎| 3877/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  26%|▎| 3877/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  26%|▎| 3877/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -36297,8 +36266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3878/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  26%|▎| 3878/14932 [05:34<15:52, 11.60it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  26%|▎| 3878/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  26%|▎| 3878/14932 [05:30<15:43, 11.72it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -36306,8 +36275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3879/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  26%|▎| 3879/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  26%|▎| 3879/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  26%|▎| 3879/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -36315,8 +36284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3880/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  26%|▎| 3880/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  26%|▎| 3880/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  26%|▎| 3880/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -36324,8 +36293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3881/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  26%|▎| 3881/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  26%|▎| 3881/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  26%|▎| 3881/14932 [05:31<15:43, 11.72it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -36333,8 +36302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3882/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  26%|▎| 3882/14932 [05:34<15:52, 11.61it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  26%|▎| 3882/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  26%|▎| 3882/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -36342,8 +36311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3883/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  26%|▎| 3883/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  26%|▎| 3883/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  26%|▎| 3883/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -36351,8 +36320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3884/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  26%|▎| 3884/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  26%|▎| 3884/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  26%|▎| 3884/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -36360,8 +36329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3885/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  26%|▎| 3885/14932 [05:34<15:51, 11.61it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  26%|▎| 3885/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  26%|▎| 3885/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -36369,8 +36338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3886/14932 [05:34<15:51, 11.60it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  26%|▎| 3886/14932 [05:34<15:51, 11.60it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  26%|▎| 3886/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  26%|▎| 3886/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -36378,8 +36347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3887/14932 [05:34<15:51, 11.60it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  26%|▎| 3887/14932 [05:34<15:51, 11.60it/s, v_num=o30c, train/loss=0.63"
+      "Epoch 0:  26%|▎| 3887/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  26%|▎| 3887/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -36387,8 +36356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3888/14932 [05:35<15:51, 11.60it/s, v_num=o30c, train/loss=0.63\r",
-      "Epoch 0:  26%|▎| 3888/14932 [05:35<15:51, 11.60it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:  26%|▎| 3888/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  26%|▎| 3888/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -36396,8 +36365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3889/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:  26%|▎| 3889/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  26%|▎| 3889/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  26%|▎| 3889/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -36405,8 +36374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3890/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  26%|▎| 3890/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  26%|▎| 3890/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  26%|▎| 3890/14932 [05:31<15:42, 11.72it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -36414,8 +36383,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3891/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  26%|▎| 3891/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  26%|▎| 3891/14932 [05:31<15:41, 11.72it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -36423,8 +36391,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3892/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  26%|▎| 3892/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  26%|▎| 3891/14932 [05:31<15:41, 11.72it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -36432,8 +36399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3893/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  26%|▎| 3893/14932 [05:35<15:51, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  26%|▎| 3892/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  26%|▎| 3892/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -36441,8 +36408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3894/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  26%|▎| 3894/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  26%|▎| 3893/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  26%|▎| 3893/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -36450,8 +36417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3895/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  26%|▎| 3895/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  26%|▎| 3894/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  26%|▎| 3894/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -36459,8 +36426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3896/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  26%|▎| 3896/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  26%|▎| 3895/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  26%|▎| 3895/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -36468,8 +36435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3897/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  26%|▎| 3897/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  26%|▎| 3896/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  26%|▎| 3896/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -36477,8 +36444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3898/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  26%|▎| 3898/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  26%|▎| 3897/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  26%|▎| 3897/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -36486,8 +36453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3899/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  26%|▎| 3899/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  26%|▎| 3898/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  26%|▎| 3898/14932 [05:32<15:41, 11.72it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -36495,8 +36462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3900/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  26%|▎| 3900/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  26%|▎| 3899/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  26%|▎| 3899/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -36504,8 +36471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3901/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  26%|▎| 3901/14932 [05:35<15:50, 11.61it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  26%|▎| 3900/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  26%|▎| 3900/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -36513,8 +36480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3902/14932 [05:36<15:50, 11.61it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  26%|▎| 3902/14932 [05:36<15:50, 11.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  26%|▎| 3901/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  26%|▎| 3901/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -36522,8 +36489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3903/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  26%|▎| 3903/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  26%|▎| 3902/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  26%|▎| 3902/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -36531,8 +36498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3904/14932 [05:36<15:50, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  26%|▎| 3904/14932 [05:36<15:50, 11.61it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  26%|▎| 3903/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  26%|▎| 3903/14932 [05:32<15:40, 11.73it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -36540,8 +36507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3905/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  26%|▎| 3905/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  26%|▎| 3904/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  26%|▎| 3904/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -36549,8 +36516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3906/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  26%|▎| 3906/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  26%|▎| 3905/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  26%|▎| 3905/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -36558,8 +36525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3907/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  26%|▎| 3907/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  26%|▎| 3906/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  26%|▎| 3906/14932 [05:33<15:40, 11.72it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -36567,8 +36534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3908/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  26%|▎| 3908/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  26%|▎| 3907/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  26%|▎| 3907/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -36576,8 +36543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3909/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  26%|▎| 3909/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  26%|▎| 3908/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  26%|▎| 3908/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -36585,8 +36552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3910/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  26%|▎| 3910/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  26%|▎| 3909/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  26%|▎| 3909/14932 [05:33<15:40, 11.73it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -36594,8 +36561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3911/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  26%|▎| 3911/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  26%|▎| 3910/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  26%|▎| 3910/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -36603,8 +36570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3912/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  26%|▎| 3912/14932 [05:36<15:49, 11.61it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  26%|▎| 3911/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  26%|▎| 3911/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -36612,8 +36579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3913/14932 [05:37<15:49, 11.61it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  26%|▎| 3913/14932 [05:37<15:49, 11.61it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  26%|▎| 3912/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  26%|▎| 3912/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -36621,8 +36588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3914/14932 [05:37<15:49, 11.61it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  26%|▎| 3914/14932 [05:37<15:49, 11.61it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  26%|▎| 3913/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  26%|▎| 3913/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -36630,8 +36597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3915/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  26%|▎| 3915/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  26%|▎| 3914/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  26%|▎| 3914/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -36639,8 +36606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3916/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  26%|▎| 3916/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  26%|▎| 3915/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  26%|▎| 3915/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -36648,8 +36615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3917/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  26%|▎| 3917/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  26%|▎| 3916/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  26%|▎| 3916/14932 [05:33<15:39, 11.73it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -36657,8 +36624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3918/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  26%|▎| 3918/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  26%|▎| 3917/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  26%|▎| 3917/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -36666,8 +36633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3919/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  26%|▎| 3919/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  26%|▎| 3918/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  26%|▎| 3918/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -36675,8 +36642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3920/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  26%|▎| 3920/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  26%|▎| 3919/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  26%|▎| 3919/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -36684,8 +36651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3921/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  26%|▎| 3921/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  26%|▎| 3920/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  26%|▎| 3920/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -36693,8 +36660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3922/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  26%|▎| 3922/14932 [05:37<15:48, 11.61it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  26%|▎| 3921/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  26%|▎| 3921/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -36702,8 +36669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3923/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  26%|▎| 3923/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  26%|▎| 3922/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  26%|▎| 3922/14932 [05:34<15:39, 11.72it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -36711,8 +36678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3924/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  26%|▎| 3924/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  26%|▎| 3923/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  26%|▎| 3923/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -36720,8 +36687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3925/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  26%|▎| 3925/14932 [05:37<15:47, 11.61it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  26%|▎| 3924/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  26%|▎| 3924/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -36729,8 +36696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3926/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  26%|▎| 3926/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  26%|▎| 3925/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  26%|▎| 3925/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -36738,8 +36705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3927/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  26%|▎| 3927/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  26%|▎| 3926/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  26%|▎| 3926/14932 [05:34<15:38, 11.73it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -36747,8 +36714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3928/14932 [05:38<15:47, 11.62it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  26%|▎| 3928/14932 [05:38<15:47, 11.62it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  26%|▎| 3927/14932 [05:34<15:38, 11.72it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  26%|▎| 3927/14932 [05:34<15:38, 11.72it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -36756,8 +36723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3929/14932 [05:38<15:47, 11.62it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  26%|▎| 3929/14932 [05:38<15:47, 11.62it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  26%|▎| 3928/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  26%|▎| 3928/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -36765,8 +36732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3930/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  26%|▎| 3930/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  26%|▎| 3929/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  26%|▎| 3929/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -36774,7 +36741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3931/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  26%|▎| 3930/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  26%|▎| 3930/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -36782,7 +36750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3931/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  26%|▎| 3931/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  26%|▎| 3931/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -36790,8 +36759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3932/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  26%|▎| 3932/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  26%|▎| 3932/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  26%|▎| 3932/14932 [05:35<15:38, 11.73it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -36799,8 +36768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3933/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  26%|▎| 3933/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  26%|▎| 3933/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  26%|▎| 3933/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -36808,8 +36777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3934/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  26%|▎| 3934/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  26%|▎| 3934/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  26%|▎| 3934/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -36817,8 +36786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3935/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  26%|▎| 3935/14932 [05:38<15:47, 11.61it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  26%|▎| 3935/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  26%|▎| 3935/14932 [05:35<15:37, 11.73it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -36826,8 +36795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3936/14932 [05:39<15:47, 11.61it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  26%|▎| 3936/14932 [05:39<15:47, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  26%|▎| 3936/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  26%|▎| 3936/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -36835,8 +36804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3937/14932 [05:39<15:47, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  26%|▎| 3937/14932 [05:39<15:47, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  26%|▎| 3937/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  26%|▎| 3937/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -36844,8 +36813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3938/14932 [05:39<15:46, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  26%|▎| 3938/14932 [05:39<15:47, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  26%|▎| 3938/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  26%|▎| 3938/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -36853,8 +36822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3939/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  26%|▎| 3939/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  26%|▎| 3939/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  26%|▎| 3939/14932 [05:35<15:37, 11.72it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -36862,8 +36831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3940/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  26%|▎| 3940/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  26%|▎| 3940/14932 [05:36<15:37, 11.72it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  26%|▎| 3940/14932 [05:36<15:37, 11.72it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -36871,8 +36840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3941/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  26%|▎| 3941/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  26%|▎| 3941/14932 [05:36<15:37, 11.72it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  26%|▎| 3941/14932 [05:36<15:37, 11.72it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -36880,8 +36849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3942/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  26%|▎| 3942/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  26%|▎| 3942/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  26%|▎| 3942/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -36889,8 +36858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3943/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  26%|▎| 3943/14932 [05:39<15:47, 11.60it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  26%|▎| 3943/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  26%|▎| 3943/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -36898,8 +36867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3944/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  26%|▎| 3944/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  26%|▎| 3944/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  26%|▎| 3944/14932 [05:36<15:37, 11.73it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -36907,8 +36876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3945/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  26%|▎| 3945/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  26%|▎| 3945/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  26%|▎| 3945/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -36916,8 +36885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3946/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  26%|▎| 3946/14932 [05:40<15:47, 11.60it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  26%|▎| 3946/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  26%|▎| 3946/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -36925,8 +36894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3947/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  26%|▎| 3947/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  26%|▎| 3947/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  26%|▎| 3947/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -36934,8 +36903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3948/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  26%|▎| 3948/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  26%|▎| 3948/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  26%|▎| 3948/14932 [05:36<15:36, 11.73it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -36943,8 +36912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3949/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  26%|▎| 3949/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  26%|▎| 3949/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  26%|▎| 3949/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -36952,8 +36921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3950/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  26%|▎| 3950/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  26%|▎| 3950/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  26%|▎| 3950/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -36961,8 +36930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3951/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  26%|▎| 3951/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  26%|▎| 3951/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  26%|▎| 3951/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -36970,8 +36939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3952/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  26%|▎| 3952/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  26%|▎| 3952/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  26%|▎| 3952/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -36979,8 +36948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3953/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  26%|▎| 3953/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  26%|▎| 3953/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  26%|▎| 3953/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -36988,8 +36957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3954/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  26%|▎| 3954/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  26%|▎| 3954/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  26%|▎| 3954/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -36997,8 +36966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3955/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  26%|▎| 3955/14932 [05:40<15:46, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  26%|▎| 3955/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  26%|▎| 3955/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -37006,8 +36975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  26%|▎| 3956/14932 [05:40<15:45, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  26%|▎| 3956/14932 [05:40<15:45, 11.60it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  26%|▎| 3956/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  26%|▎| 3956/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -37015,8 +36984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3957/14932 [05:40<15:45, 11.60it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  27%|▎| 3957/14932 [05:40<15:45, 11.60it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  27%|▎| 3957/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  27%|▎| 3957/14932 [05:37<15:37, 11.71it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -37024,8 +36993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3958/14932 [05:41<15:45, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  27%|▎| 3958/14932 [05:41<15:45, 11.60it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  27%|▎| 3958/14932 [05:37<15:36, 11.71it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  27%|▎| 3958/14932 [05:37<15:36, 11.71it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -37033,8 +37002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3959/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  27%|▎| 3959/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  27%|▎| 3959/14932 [05:37<15:36, 11.71it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  27%|▎| 3959/14932 [05:37<15:36, 11.71it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -37042,8 +37011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3960/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  27%|▎| 3960/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  27%|▎| 3960/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  27%|▎| 3960/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -37051,8 +37020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3961/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  27%|▎| 3961/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  27%|▎| 3961/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  27%|▎| 3961/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -37060,8 +37029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3962/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  27%|▎| 3962/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  27%|▎| 3962/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  27%|▎| 3962/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -37069,8 +37038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3963/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  27%|▎| 3963/14932 [05:41<15:45, 11.61it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  27%|▎| 3963/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  27%|▎| 3963/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -37078,8 +37047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3964/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  27%|▎| 3964/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  27%|▎| 3964/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  27%|▎| 3964/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -37087,8 +37056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3965/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  27%|▎| 3965/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  27%|▎| 3965/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  27%|▎| 3965/14932 [05:38<15:36, 11.72it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -37096,8 +37065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3966/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  27%|▎| 3966/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  27%|▎| 3966/14932 [05:38<15:35, 11.72it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  27%|▎| 3966/14932 [05:38<15:35, 11.72it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -37105,8 +37074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3967/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  27%|▎| 3967/14932 [05:41<15:44, 11.61it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  27%|▎| 3967/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  27%|▎| 3967/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -37114,8 +37083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3968/14932 [05:41<15:44, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  27%|▎| 3968/14932 [05:41<15:44, 11.60it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  27%|▎| 3968/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  27%|▎| 3968/14932 [05:38<15:36, 11.71it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -37123,8 +37092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3969/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  27%|▎| 3969/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  27%|▎| 3969/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  27%|▎| 3969/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -37132,8 +37101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3970/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  27%|▎| 3970/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=1.25"
+      "Epoch 0:  27%|▎| 3970/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  27%|▎| 3970/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -37141,8 +37110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3971/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=1.25\r",
-      "Epoch 0:  27%|▎| 3971/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  27%|▎| 3971/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  27%|▎| 3971/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -37150,8 +37119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3972/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  27%|▎| 3972/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  27%|▎| 3972/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  27%|▎| 3972/14932 [05:39<15:36, 11.71it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -37159,8 +37128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3973/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  27%|▎| 3973/14932 [05:42<15:44, 11.60it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:  27%|▎| 3973/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  27%|▎| 3973/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -37168,8 +37137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3974/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:  27%|▎| 3974/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  27%|▎| 3974/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  27%|▎| 3974/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -37177,8 +37146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3975/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  27%|▎| 3975/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  27%|▎| 3975/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  27%|▎| 3975/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -37186,8 +37155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3976/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  27%|▎| 3976/14932 [05:42<15:44, 11.61it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  27%|▎| 3976/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  27%|▎| 3976/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -37195,8 +37164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3977/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  27%|▎| 3977/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  27%|▎| 3977/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  27%|▎| 3977/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -37204,8 +37173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3978/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  27%|▎| 3978/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  27%|▎| 3978/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  27%|▎| 3978/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -37213,8 +37182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3979/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  27%|▎| 3979/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  27%|▎| 3979/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  27%|▎| 3979/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -37222,8 +37191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3980/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  27%|▎| 3980/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  27%|▎| 3980/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  27%|▎| 3980/14932 [05:39<15:35, 11.71it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -37231,8 +37200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3981/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  27%|▎| 3981/14932 [05:42<15:43, 11.61it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  27%|▎| 3981/14932 [05:39<15:34, 11.71it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  27%|▎| 3981/14932 [05:39<15:34, 11.71it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -37240,8 +37209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3982/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  27%|▎| 3982/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  27%|▎| 3982/14932 [05:39<15:34, 11.71it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  27%|▎| 3982/14932 [05:39<15:34, 11.71it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -37249,8 +37218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3983/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  27%|▎| 3983/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  27%|▎| 3983/14932 [05:40<15:34, 11.71it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  27%|▎| 3983/14932 [05:40<15:34, 11.71it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -37258,8 +37227,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3984/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  27%|▎| 3984/14932 [05:43<15:43, 11.61it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  27%|▎| 3984/14932 [05:40<15:34, 11.71it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -37267,7 +37235,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3985/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  27%|▎| 3984/14932 [05:40<15:34, 11.71it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -37275,7 +37243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3985/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  27%|▎| 3985/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  27%|▎| 3985/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=4.78"
      ]
     },
     {
@@ -37283,8 +37252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3986/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  27%|▎| 3986/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  27%|▎| 3986/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=4.78\r",
+      "Epoch 0:  27%|▎| 3986/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -37292,8 +37261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3987/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  27%|▎| 3987/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  27%|▎| 3987/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  27%|▎| 3987/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -37301,8 +37270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3988/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  27%|▎| 3988/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  27%|▎| 3988/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  27%|▎| 3988/14932 [05:40<15:34, 11.72it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -37310,8 +37279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3989/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  27%|▎| 3989/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  27%|▎| 3989/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  27%|▎| 3989/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -37319,8 +37288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3990/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  27%|▎| 3990/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  27%|▎| 3990/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  27%|▎| 3990/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -37328,8 +37297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3991/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  27%|▎| 3991/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  27%|▎| 3991/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  27%|▎| 3991/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -37337,8 +37306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3992/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  27%|▎| 3992/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  27%|▎| 3992/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  27%|▎| 3992/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -37346,8 +37315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3993/14932 [05:43<15:41, 11.61it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  27%|▎| 3993/14932 [05:43<15:41, 11.61it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  27%|▎| 3993/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  27%|▎| 3993/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -37355,8 +37324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3994/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=4.84\r",
-      "Epoch 0:  27%|▎| 3994/14932 [05:43<15:42, 11.61it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  27%|▎| 3994/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  27%|▎| 3994/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -37364,8 +37333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3995/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  27%|▎| 3995/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  27%|▎| 3995/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  27%|▎| 3995/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -37373,8 +37342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3996/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  27%|▎| 3996/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  27%|▎| 3996/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  27%|▎| 3996/14932 [05:40<15:33, 11.72it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -37382,8 +37351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3997/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  27%|▎| 3997/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  27%|▎| 3997/14932 [05:41<15:32, 11.72it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  27%|▎| 3997/14932 [05:41<15:32, 11.72it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -37391,8 +37360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3998/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  27%|▎| 3998/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  27%|▎| 3998/14932 [05:41<15:32, 11.72it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  27%|▎| 3998/14932 [05:41<15:32, 11.72it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -37400,8 +37369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 3999/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  27%|▎| 3999/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  27%|▎| 3999/14932 [05:41<15:33, 11.72it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  27%|▎| 3999/14932 [05:41<15:33, 11.72it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -37409,8 +37378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4000/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  27%|▎| 4000/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  27%|▎| 4000/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  27%|▎| 4000/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -37418,8 +37387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4001/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  27%|▎| 4001/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  27%|▎| 4001/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  27%|▎| 4001/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -37427,8 +37396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4002/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  27%|▎| 4002/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  27%|▎| 4002/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  27%|▎| 4002/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -37436,8 +37405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4003/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  27%|▎| 4003/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  27%|▎| 4003/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  27%|▎| 4003/14932 [05:41<15:33, 11.71it/s, v_num=ui8w, train/loss=1.36"
      ]
     },
     {
@@ -37445,8 +37414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4004/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  27%|▎| 4004/14932 [05:44<15:41, 11.61it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  27%|▎| 4004/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=1.36\r",
+      "Epoch 0:  27%|▎| 4004/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=1.86"
      ]
     },
     {
@@ -37454,8 +37423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4005/14932 [05:44<15:40, 11.61it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  27%|▎| 4005/14932 [05:44<15:40, 11.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  27%|▎| 4005/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=1.86\r",
+      "Epoch 0:  27%|▎| 4005/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -37463,8 +37432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4006/14932 [05:45<15:41, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  27%|▎| 4006/14932 [05:45<15:41, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  27%|▎| 4006/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  27%|▎| 4006/14932 [05:41<15:32, 11.71it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -37472,8 +37441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4007/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  27%|▎| 4007/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  27%|▎| 4007/14932 [05:42<15:32, 11.71it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  27%|▎| 4007/14932 [05:42<15:32, 11.71it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -37481,8 +37450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4008/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  27%|▎| 4008/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  27%|▎| 4008/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  27%|▎| 4008/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -37490,8 +37459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4009/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  27%|▎| 4009/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  27%|▎| 4009/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  27%|▎| 4009/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -37499,8 +37468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4010/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  27%|▎| 4010/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  27%|▎| 4010/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  27%|▎| 4010/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -37508,8 +37477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4011/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  27%|▎| 4011/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  27%|▎| 4011/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  27%|▎| 4011/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -37517,8 +37486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4012/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  27%|▎| 4012/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  27%|▎| 4012/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  27%|▎| 4012/14932 [05:42<15:32, 11.72it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -37526,8 +37495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4013/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  27%|▎| 4013/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  27%|▎| 4013/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  27%|▎| 4013/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -37535,8 +37504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4014/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  27%|▎| 4014/14932 [05:45<15:40, 11.61it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  27%|▎| 4014/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  27%|▎| 4014/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -37544,8 +37513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4015/14932 [05:45<15:39, 11.61it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  27%|▎| 4015/14932 [05:45<15:39, 11.61it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  27%|▎| 4015/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  27%|▎| 4015/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -37553,8 +37522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4016/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  27%|▎| 4016/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  27%|▎| 4016/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  27%|▎| 4016/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -37562,8 +37531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4017/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  27%|▎| 4017/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=1.17"
+      "Epoch 0:  27%|▎| 4017/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  27%|▎| 4017/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -37571,8 +37540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4018/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=1.17\r",
-      "Epoch 0:  27%|▎| 4018/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  27%|▎| 4018/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  27%|▎| 4018/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -37580,8 +37549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4019/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  27%|▎| 4019/14932 [05:45<15:39, 11.62it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  27%|▎| 4019/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  27%|▎| 4019/14932 [05:42<15:31, 11.72it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -37589,8 +37558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4020/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  27%|▎| 4020/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  27%|▎| 4020/14932 [05:43<15:31, 11.72it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  27%|▎| 4020/14932 [05:43<15:31, 11.72it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -37598,8 +37567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4021/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  27%|▎| 4021/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  27%|▎| 4021/14932 [05:43<15:31, 11.72it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  27%|▎| 4021/14932 [05:43<15:31, 11.72it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -37607,8 +37576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4022/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  27%|▎| 4022/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  27%|▎| 4022/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  27%|▎| 4022/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -37616,8 +37585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4023/14932 [05:46<15:39, 11.61it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  27%|▎| 4023/14932 [05:46<15:39, 11.61it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  27%|▎| 4023/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  27%|▎| 4023/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -37625,8 +37594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4024/14932 [05:46<15:39, 11.61it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  27%|▎| 4024/14932 [05:46<15:39, 11.61it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  27%|▎| 4024/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  27%|▎| 4024/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -37634,8 +37603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4025/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  27%|▎| 4025/14932 [05:46<15:39, 11.62it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  27%|▎| 4025/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  27%|▎| 4025/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -37643,8 +37612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4026/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  27%|▎| 4026/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  27%|▎| 4026/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  27%|▎| 4026/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -37652,8 +37621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4027/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  27%|▎| 4027/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  27%|▎| 4027/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  27%|▎| 4027/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -37661,8 +37630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4028/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  27%|▎| 4028/14932 [05:46<15:38, 11.62it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  27%|▎| 4028/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  27%|▎| 4028/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -37670,8 +37639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4029/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  27%|▎| 4029/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  27%|▎| 4029/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  27%|▎| 4029/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -37679,8 +37648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4030/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  27%|▎| 4030/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  27%|▎| 4030/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  27%|▎| 4030/14932 [05:43<15:30, 11.72it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -37688,8 +37657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4031/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  27%|▎| 4031/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  27%|▎| 4031/14932 [05:43<15:29, 11.72it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  27%|▎| 4031/14932 [05:43<15:29, 11.72it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -37697,8 +37666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4032/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  27%|▎| 4032/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  27%|▎| 4032/14932 [05:44<15:30, 11.72it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  27%|▎| 4032/14932 [05:44<15:30, 11.72it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -37706,8 +37675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4033/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  27%|▎| 4033/14932 [05:47<15:39, 11.61it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  27%|▎| 4033/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  27%|▎| 4033/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -37715,8 +37684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4034/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  27%|▎| 4034/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  27%|▎| 4034/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  27%|▎| 4034/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -37724,8 +37693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4035/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  27%|▎| 4035/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  27%|▎| 4035/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  27%|▎| 4035/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -37733,8 +37702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4036/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  27%|▎| 4036/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  27%|▎| 4036/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  27%|▎| 4036/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -37742,8 +37711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4037/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  27%|▎| 4037/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  27%|▎| 4037/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  27%|▎| 4037/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -37751,8 +37720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4038/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  27%|▎| 4038/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  27%|▎| 4038/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  27%|▎| 4038/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -37760,8 +37729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4039/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  27%|▎| 4039/14932 [05:47<15:38, 11.61it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  27%|▎| 4039/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  27%|▎| 4039/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -37769,8 +37738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4040/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  27%|▎| 4040/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  27%|▎| 4040/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  27%|▎| 4040/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -37778,8 +37747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4041/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  27%|▎| 4041/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  27%|▎| 4041/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  27%|▎| 4041/14932 [05:44<15:29, 11.72it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -37787,8 +37756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4042/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  27%|▎| 4042/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  27%|▎| 4042/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  27%|▎| 4042/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -37796,8 +37765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4043/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  27%|▎| 4043/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  27%|▎| 4043/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  27%|▎| 4043/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -37805,8 +37774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4044/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  27%|▎| 4044/14932 [05:48<15:38, 11.61it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  27%|▎| 4044/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  27%|▎| 4044/14932 [05:44<15:28, 11.72it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -37814,8 +37783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4045/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  27%|▎| 4045/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  27%|▎| 4045/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  27%|▎| 4045/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -37823,8 +37792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4046/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  27%|▎| 4046/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  27%|▎| 4046/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  27%|▎| 4046/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -37832,8 +37801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4047/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  27%|▎| 4047/14932 [05:48<15:38, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  27%|▎| 4047/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  27%|▎| 4047/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -37841,8 +37810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4048/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  27%|▎| 4048/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  27%|▎| 4048/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  27%|▎| 4048/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -37850,8 +37819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4049/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  27%|▎| 4049/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  27%|▎| 4049/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  27%|▎| 4049/14932 [05:45<15:28, 11.72it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -37859,8 +37828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4050/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  27%|▎| 4050/14932 [05:48<15:37, 11.60it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  27%|▎| 4050/14932 [05:45<15:28, 11.73it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  27%|▎| 4050/14932 [05:45<15:28, 11.73it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -37868,8 +37837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4051/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  27%|▎| 4051/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  27%|▎| 4051/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  27%|▎| 4051/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -37877,8 +37846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4052/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  27%|▎| 4052/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  27%|▎| 4052/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  27%|▎| 4052/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -37886,8 +37855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4053/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  27%|▎| 4053/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  27%|▎| 4053/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  27%|▎| 4053/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -37895,8 +37864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4054/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  27%|▎| 4054/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  27%|▎| 4054/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  27%|▎| 4054/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -37904,8 +37873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4055/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  27%|▎| 4055/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  27%|▎| 4055/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  27%|▎| 4055/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -37913,8 +37882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4056/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  27%|▎| 4056/14932 [05:49<15:37, 11.61it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  27%|▎| 4056/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  27%|▎| 4056/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -37922,8 +37891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4057/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  27%|▎| 4057/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  27%|▎| 4057/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  27%|▎| 4057/14932 [05:45<15:27, 11.73it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -37931,8 +37900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4058/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  27%|▎| 4058/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  27%|▎| 4058/14932 [05:46<15:27, 11.73it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  27%|▎| 4058/14932 [05:46<15:27, 11.73it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -37940,8 +37909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4059/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  27%|▎| 4059/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  27%|▎| 4059/14932 [05:46<15:27, 11.73it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  27%|▎| 4059/14932 [05:46<15:27, 11.73it/s, v_num=ui8w, train/loss=0.87"
      ]
     },
     {
@@ -37949,8 +37918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4060/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  27%|▎| 4060/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  27%|▎| 4060/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=0.87\r",
+      "Epoch 0:  27%|▎| 4060/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -37958,8 +37927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4061/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  27%|▎| 4061/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  27%|▎| 4061/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  27%|▎| 4061/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -37967,8 +37936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4062/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  27%|▎| 4062/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  27%|▎| 4062/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  27%|▎| 4062/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -37976,8 +37945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4063/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  27%|▎| 4063/14932 [05:49<15:36, 11.61it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  27%|▎| 4063/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  27%|▎| 4063/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -37985,8 +37954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4064/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  27%|▎| 4064/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  27%|▎| 4064/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  27%|▎| 4064/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -37994,8 +37963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4065/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  27%|▎| 4065/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  27%|▎| 4065/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  27%|▎| 4065/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -38003,8 +37972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4066/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  27%|▎| 4066/14932 [05:50<15:36, 11.61it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  27%|▎| 4066/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  27%|▎| 4066/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -38012,8 +37981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4067/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  27%|▎| 4067/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  27%|▎| 4067/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  27%|▎| 4067/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -38021,8 +37990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4068/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  27%|▎| 4068/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  27%|▎| 4068/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  27%|▎| 4068/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -38030,8 +37999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4069/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  27%|▎| 4069/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  27%|▎| 4069/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  27%|▎| 4069/14932 [05:46<15:26, 11.73it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -38039,8 +38008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4070/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  27%|▎| 4070/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  27%|▎| 4070/14932 [05:47<15:26, 11.73it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  27%|▎| 4070/14932 [05:47<15:26, 11.73it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -38048,8 +38017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4071/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  27%|▎| 4071/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  27%|▎| 4071/14932 [05:47<15:26, 11.73it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  27%|▎| 4071/14932 [05:47<15:26, 11.73it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -38057,8 +38026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4072/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  27%|▎| 4072/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  27%|▎| 4072/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  27%|▎| 4072/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -38066,8 +38035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4073/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  27%|▎| 4073/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  27%|▎| 4073/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  27%|▎| 4073/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -38075,8 +38044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4074/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  27%|▎| 4074/14932 [05:50<15:35, 11.61it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  27%|▎| 4074/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  27%|▎| 4074/14932 [05:47<15:26, 11.72it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -38084,8 +38053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4075/14932 [05:51<15:35, 11.61it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  27%|▎| 4075/14932 [05:51<15:35, 11.61it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  27%|▎| 4075/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  27%|▎| 4075/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -38093,8 +38062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4076/14932 [05:51<15:35, 11.61it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  27%|▎| 4076/14932 [05:51<15:35, 11.61it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  27%|▎| 4076/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  27%|▎| 4076/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -38102,8 +38071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4077/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  27%|▎| 4077/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  27%|▎| 4077/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  27%|▎| 4077/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -38111,8 +38080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4078/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  27%|▎| 4078/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  27%|▎| 4078/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  27%|▎| 4078/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -38120,8 +38089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4079/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  27%|▎| 4079/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  27%|▎| 4079/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  27%|▎| 4079/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -38129,8 +38098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4080/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  27%|▎| 4080/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  27%|▎| 4080/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  27%|▎| 4080/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -38138,8 +38107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4081/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  27%|▎| 4081/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  27%|▎| 4081/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  27%|▎| 4081/14932 [05:47<15:25, 11.73it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -38147,8 +38116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4082/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  27%|▎| 4082/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  27%|▎| 4082/14932 [05:48<15:25, 11.73it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  27%|▎| 4082/14932 [05:48<15:25, 11.73it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -38156,8 +38125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4083/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  27%|▎| 4083/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  27%|▎| 4083/14932 [05:48<15:25, 11.73it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  27%|▎| 4083/14932 [05:48<15:25, 11.73it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -38165,8 +38134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4084/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  27%|▎| 4084/14932 [05:51<15:34, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  27%|▎| 4084/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  27%|▎| 4084/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -38174,8 +38143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4085/14932 [05:51<15:33, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  27%|▎| 4085/14932 [05:51<15:33, 11.61it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  27%|▎| 4085/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  27%|▎| 4085/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -38183,8 +38152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4086/14932 [05:51<15:33, 11.61it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  27%|▎| 4086/14932 [05:51<15:33, 11.61it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  27%|▎| 4086/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  27%|▎| 4086/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -38192,8 +38161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4087/14932 [05:51<15:33, 11.62it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  27%|▎| 4087/14932 [05:51<15:33, 11.62it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  27%|▎| 4087/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  27%|▎| 4087/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=1.26"
      ]
     },
     {
@@ -38201,8 +38170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4088/14932 [05:51<15:33, 11.62it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  27%|▎| 4088/14932 [05:51<15:33, 11.62it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  27%|▎| 4088/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=1.26\r",
+      "Epoch 0:  27%|▎| 4088/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -38210,8 +38179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4089/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  27%|▎| 4089/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  27%|▎| 4089/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  27%|▎| 4089/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -38219,8 +38188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4090/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  27%|▎| 4090/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  27%|▎| 4090/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  27%|▎| 4090/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -38228,8 +38197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4091/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  27%|▎| 4091/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  27%|▎| 4091/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  27%|▎| 4091/14932 [05:48<15:24, 11.73it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -38237,8 +38206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4092/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  27%|▎| 4092/14932 [05:52<15:33, 11.62it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  27%|▎| 4092/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  27%|▎| 4092/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -38246,8 +38215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4093/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  27%|▎| 4093/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  27%|▎| 4093/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  27%|▎| 4093/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -38255,8 +38224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4094/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  27%|▎| 4094/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  27%|▎| 4094/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  27%|▎| 4094/14932 [05:48<15:23, 11.73it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -38264,8 +38233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4095/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  27%|▎| 4095/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  27%|▎| 4095/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  27%|▎| 4095/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -38273,8 +38242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4096/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  27%|▎| 4096/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  27%|▎| 4096/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  27%|▎| 4096/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -38282,8 +38251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4097/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  27%|▎| 4097/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  27%|▎| 4097/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  27%|▎| 4097/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -38291,8 +38260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4098/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  27%|▎| 4098/14932 [05:52<15:32, 11.62it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  27%|▎| 4098/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  27%|▎| 4098/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -38300,8 +38269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4099/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  27%|▎| 4099/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  27%|▎| 4099/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  27%|▎| 4099/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -38309,8 +38278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4100/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  27%|▎| 4100/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  27%|▎| 4100/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  27%|▎| 4100/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -38318,8 +38287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4101/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  27%|▎| 4101/14932 [05:53<15:33, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  27%|▎| 4101/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  27%|▎| 4101/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -38327,8 +38296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4102/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  27%|▎| 4102/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  27%|▎| 4102/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  27%|▎| 4102/14932 [05:49<15:23, 11.73it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -38336,8 +38305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4103/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  27%|▎| 4103/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  27%|▎| 4103/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  27%|▎| 4103/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -38345,8 +38314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4104/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  27%|▎| 4104/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  27%|▎| 4104/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  27%|▎| 4104/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -38354,8 +38323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4105/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  27%|▎| 4105/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  27%|▎| 4105/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  27%|▎| 4105/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -38363,8 +38332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  27%|▎| 4106/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  27%|▎| 4106/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  27%|▎| 4106/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  27%|▎| 4106/14932 [05:49<15:22, 11.73it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -38372,8 +38341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4107/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  28%|▎| 4107/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  28%|▎| 4107/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  28%|▎| 4107/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -38381,8 +38350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4108/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  28%|▎| 4108/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  28%|▎| 4108/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  28%|▎| 4108/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -38390,8 +38359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4109/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  28%|▎| 4109/14932 [05:53<15:32, 11.61it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  28%|▎| 4109/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  28%|▎| 4109/14932 [05:50<15:22, 11.73it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -38399,8 +38368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4110/14932 [05:53<15:31, 11.61it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  28%|▎| 4110/14932 [05:53<15:31, 11.61it/s, v_num=o30c, train/loss=1.44"
+      "Epoch 0:  28%|▎| 4110/14932 [05:50<15:22, 11.74it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  28%|▎| 4110/14932 [05:50<15:22, 11.74it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -38408,8 +38377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4111/14932 [05:53<15:31, 11.61it/s, v_num=o30c, train/loss=1.44\r",
-      "Epoch 0:  28%|▎| 4111/14932 [05:53<15:31, 11.61it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  28%|▎| 4111/14932 [05:50<15:22, 11.74it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  28%|▎| 4111/14932 [05:50<15:22, 11.74it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -38417,8 +38386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4112/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  28%|▎| 4112/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  28%|▎| 4112/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  28%|▎| 4112/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -38426,8 +38395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4113/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  28%|▎| 4113/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  28%|▎| 4113/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  28%|▎| 4113/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -38435,8 +38404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4114/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  28%|▎| 4114/14932 [05:54<15:31, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  28%|▎| 4114/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  28%|▎| 4114/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -38444,8 +38413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4115/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  28%|▎| 4115/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  28%|▎| 4115/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  28%|▎| 4115/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -38453,8 +38422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4116/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  28%|▎| 4116/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:  28%|▎| 4116/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  28%|▎| 4116/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -38462,8 +38431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4117/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:  28%|▎| 4117/14932 [05:54<15:31, 11.62it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  28%|▎| 4117/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  28%|▎| 4117/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -38471,8 +38440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4118/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  28%|▎| 4118/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  28%|▎| 4118/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  28%|▎| 4118/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -38480,8 +38449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4119/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  28%|▎| 4119/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  28%|▎| 4119/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  28%|▎| 4119/14932 [05:50<15:21, 11.74it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -38489,8 +38458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4120/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  28%|▎| 4120/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  28%|▎| 4120/14932 [05:51<15:21, 11.74it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  28%|▎| 4120/14932 [05:51<15:21, 11.74it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -38498,8 +38467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4121/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  28%|▎| 4121/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  28%|▎| 4121/14932 [05:51<15:21, 11.74it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  28%|▎| 4121/14932 [05:51<15:21, 11.74it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -38507,8 +38476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4122/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  28%|▎| 4122/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  28%|▎| 4122/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  28%|▎| 4122/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -38516,8 +38485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4123/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  28%|▎| 4123/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  28%|▎| 4123/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  28%|▎| 4123/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -38525,8 +38494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4124/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  28%|▎| 4124/14932 [05:54<15:30, 11.62it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  28%|▎| 4124/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  28%|▎| 4124/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -38534,8 +38503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4125/14932 [05:55<15:30, 11.62it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  28%|▎| 4125/14932 [05:55<15:30, 11.62it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  28%|▎| 4125/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  28%|▎| 4125/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -38543,8 +38512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4126/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  28%|▎| 4126/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  28%|▎| 4126/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  28%|▎| 4126/14932 [05:51<15:20, 11.74it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -38552,8 +38521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4127/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  28%|▎| 4127/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  28%|▎| 4127/14932 [05:51<15:21, 11.73it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  28%|▎| 4127/14932 [05:51<15:21, 11.73it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -38561,8 +38530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4128/14932 [05:55<15:30, 11.62it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  28%|▎| 4128/14932 [05:55<15:30, 11.62it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  28%|▎| 4128/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  28%|▎| 4128/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -38570,8 +38539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4129/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  28%|▎| 4129/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  28%|▎| 4129/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  28%|▎| 4129/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -38579,8 +38548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4130/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  28%|▎| 4130/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  28%|▎| 4130/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  28%|▎| 4130/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -38588,8 +38557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4131/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  28%|▎| 4131/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  28%|▎| 4131/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  28%|▎| 4131/14932 [05:52<15:21, 11.73it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -38597,8 +38566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4132/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  28%|▎| 4132/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  28%|▎| 4132/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  28%|▎| 4132/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -38606,8 +38575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4133/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  28%|▎| 4133/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  28%|▎| 4133/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  28%|▎| 4133/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -38615,8 +38584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4134/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  28%|▎| 4134/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  28%|▎| 4134/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  28%|▎| 4134/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -38624,8 +38593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4135/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  28%|▎| 4135/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  28%|▎| 4135/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  28%|▎| 4135/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -38633,8 +38602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4136/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  28%|▎| 4136/14932 [05:55<15:29, 11.62it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  28%|▎| 4136/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  28%|▎| 4136/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -38642,8 +38611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4137/14932 [05:56<15:29, 11.62it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  28%|▎| 4137/14932 [05:56<15:29, 11.62it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  28%|▎| 4137/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  28%|▎| 4137/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -38651,8 +38620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4138/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  28%|▎| 4138/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  28%|▎| 4138/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  28%|▎| 4138/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -38660,8 +38629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4139/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  28%|▎| 4139/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  28%|▎| 4139/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  28%|▎| 4139/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -38669,8 +38638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4140/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  28%|▎| 4140/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  28%|▎| 4140/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  28%|▎| 4140/14932 [05:52<15:20, 11.73it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -38678,8 +38647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4141/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  28%|▎| 4141/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  28%|▎| 4141/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  28%|▎| 4141/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -38687,8 +38656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4142/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  28%|▎| 4142/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  28%|▎| 4142/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  28%|▎| 4142/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -38696,8 +38665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4143/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  28%|▎| 4143/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  28%|▎| 4143/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  28%|▎| 4143/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -38705,8 +38674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4144/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  28%|▎| 4144/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  28%|▎| 4144/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  28%|▎| 4144/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -38714,8 +38683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4145/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  28%|▎| 4145/14932 [05:56<15:28, 11.62it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  28%|▎| 4145/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  28%|▎| 4145/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -38723,8 +38692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4146/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  28%|▎| 4146/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  28%|▎| 4146/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  28%|▎| 4146/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -38732,8 +38701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4147/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  28%|▎| 4147/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  28%|▎| 4147/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  28%|▎| 4147/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -38741,8 +38710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4148/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  28%|▎| 4148/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  28%|▎| 4148/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  28%|▎| 4148/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -38750,8 +38719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4149/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  28%|▎| 4149/14932 [05:57<15:29, 11.61it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  28%|▎| 4149/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  28%|▎| 4149/14932 [05:53<15:19, 11.73it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -38759,8 +38728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4150/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  28%|▎| 4150/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  28%|▎| 4150/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  28%|▎| 4150/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -38768,8 +38737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4151/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  28%|▎| 4151/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  28%|▎| 4151/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  28%|▎| 4151/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=5.59"
      ]
     },
     {
@@ -38777,8 +38746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4152/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  28%|▎| 4152/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  28%|▎| 4152/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=5.59\r",
+      "Epoch 0:  28%|▎| 4152/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -38786,8 +38755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4153/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  28%|▎| 4153/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  28%|▎| 4153/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  28%|▎| 4153/14932 [05:53<15:18, 11.73it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -38795,8 +38764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4154/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  28%|▎| 4154/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  28%|▎| 4154/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  28%|▎| 4154/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -38804,8 +38773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4155/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  28%|▎| 4155/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  28%|▎| 4155/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  28%|▎| 4155/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -38813,8 +38782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4156/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  28%|▎| 4156/14932 [05:57<15:28, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  28%|▎| 4156/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  28%|▎| 4156/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -38822,8 +38791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4157/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  28%|▎| 4157/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  28%|▎| 4157/14932 [05:54<15:18, 11.74it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  28%|▎| 4157/14932 [05:54<15:18, 11.74it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -38831,8 +38800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4158/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  28%|▎| 4158/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  28%|▎| 4158/14932 [05:54<15:18, 11.74it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  28%|▎| 4158/14932 [05:54<15:18, 11.74it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -38840,8 +38809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4159/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  28%|▎| 4159/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  28%|▎| 4159/14932 [05:54<15:17, 11.74it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  28%|▎| 4159/14932 [05:54<15:17, 11.74it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -38849,8 +38818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4160/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  28%|▎| 4160/14932 [05:58<15:28, 11.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  28%|▎| 4160/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  28%|▎| 4160/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -38858,8 +38827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4161/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  28%|▎| 4161/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  28%|▎| 4161/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  28%|▎| 4161/14932 [05:54<15:18, 11.73it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -38867,8 +38836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4162/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  28%|▎| 4162/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  28%|▎| 4162/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  28%|▎| 4162/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -38876,8 +38845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4163/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  28%|▎| 4163/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  28%|▎| 4163/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  28%|▎| 4163/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=0.92"
      ]
     },
     {
@@ -38885,8 +38854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4164/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  28%|▎| 4164/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  28%|▎| 4164/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=0.92\r",
+      "Epoch 0:  28%|▎| 4164/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -38894,8 +38863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4165/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  28%|▎| 4165/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  28%|▎| 4165/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  28%|▎| 4165/14932 [05:54<15:17, 11.73it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -38903,8 +38872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4166/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  28%|▎| 4166/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  28%|▎| 4166/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  28%|▎| 4166/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -38912,8 +38881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4167/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  28%|▎| 4167/14932 [05:58<15:27, 11.61it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  28%|▎| 4167/14932 [05:55<15:17, 11.74it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  28%|▎| 4167/14932 [05:55<15:17, 11.74it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -38921,8 +38890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4168/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  28%|▎| 4168/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  28%|▎| 4168/14932 [05:55<15:17, 11.74it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  28%|▎| 4168/14932 [05:55<15:17, 11.74it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -38930,8 +38899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4169/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  28%|▎| 4169/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  28%|▎| 4169/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  28%|▎| 4169/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -38939,8 +38908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4170/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  28%|▎| 4170/14932 [05:59<15:27, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  28%|▎| 4170/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  28%|▎| 4170/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -38948,8 +38917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4171/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  28%|▎| 4171/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  28%|▎| 4171/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  28%|▎| 4171/14932 [05:55<15:17, 11.73it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -38957,8 +38926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4172/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  28%|▎| 4172/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  28%|▎| 4172/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  28%|▎| 4172/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -38966,8 +38935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4173/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  28%|▎| 4173/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  28%|▎| 4173/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  28%|▎| 4173/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -38975,8 +38944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4174/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  28%|▎| 4174/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  28%|▎| 4174/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  28%|▎| 4174/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -38984,8 +38953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4175/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  28%|▎| 4175/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  28%|▎| 4175/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  28%|▎| 4175/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -38993,8 +38962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4176/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  28%|▎| 4176/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  28%|▎| 4176/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  28%|▎| 4176/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -39002,8 +38971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4177/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  28%|▎| 4177/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  28%|▎| 4177/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  28%|▎| 4177/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -39011,8 +38980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4178/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  28%|▎| 4178/14932 [05:59<15:26, 11.61it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  28%|▎| 4178/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  28%|▎| 4178/14932 [05:55<15:16, 11.74it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -39020,8 +38989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4179/14932 [05:59<15:25, 11.61it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  28%|▎| 4179/14932 [05:59<15:25, 11.61it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  28%|▎| 4179/14932 [05:56<15:16, 11.74it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  28%|▎| 4179/14932 [05:56<15:16, 11.74it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -39029,8 +38998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4180/14932 [05:59<15:25, 11.61it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  28%|▎| 4180/14932 [05:59<15:25, 11.61it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  28%|▎| 4180/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  28%|▎| 4180/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -39038,8 +39007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4181/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  28%|▎| 4181/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  28%|▎| 4181/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  28%|▎| 4181/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -39047,8 +39016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4182/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  28%|▎| 4182/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  28%|▎| 4182/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  28%|▎| 4182/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -39056,8 +39025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4183/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  28%|▎| 4183/14932 [06:00<15:25, 11.61it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  28%|▎| 4183/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  28%|▎| 4183/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -39065,8 +39034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4184/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  28%|▎| 4184/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  28%|▎| 4184/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  28%|▎| 4184/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -39074,8 +39043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4185/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  28%|▎| 4185/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  28%|▎| 4185/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  28%|▎| 4185/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -39083,8 +39052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4186/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  28%|▎| 4186/14932 [06:00<15:25, 11.62it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  28%|▎| 4186/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  28%|▎| 4186/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -39092,8 +39061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4187/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  28%|▎| 4187/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  28%|▎| 4187/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  28%|▎| 4187/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -39101,8 +39070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4188/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  28%|▎| 4188/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  28%|▎| 4188/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  28%|▎| 4188/14932 [05:56<15:15, 11.74it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -39110,8 +39079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4189/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  28%|▎| 4189/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  28%|▎| 4189/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  28%|▎| 4189/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -39119,8 +39088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4190/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  28%|▎| 4190/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  28%|▎| 4190/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  28%|▎| 4190/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -39128,8 +39097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4191/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  28%|▎| 4191/14932 [06:00<15:24, 11.62it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  28%|▎| 4191/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  28%|▎| 4191/14932 [05:56<15:14, 11.74it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -39137,8 +39106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4192/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  28%|▎| 4192/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  28%|▎| 4192/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  28%|▎| 4192/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -39146,8 +39115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4193/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  28%|▎| 4193/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  28%|▎| 4193/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  28%|▎| 4193/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -39155,8 +39124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4194/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  28%|▎| 4194/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  28%|▎| 4194/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  28%|▎| 4194/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -39164,8 +39133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4195/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  28%|▎| 4195/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  28%|▎| 4195/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  28%|▎| 4195/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -39173,8 +39142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4196/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  28%|▎| 4196/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  28%|▎| 4196/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  28%|▎| 4196/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -39182,8 +39151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4197/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  28%|▎| 4197/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  28%|▎| 4197/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  28%|▎| 4197/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -39191,8 +39160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4198/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  28%|▎| 4198/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  28%|▎| 4198/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  28%|▎| 4198/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -39200,8 +39169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4199/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  28%|▎| 4199/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  28%|▎| 4199/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  28%|▎| 4199/14932 [05:57<15:14, 11.74it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -39209,8 +39178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4200/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  28%|▎| 4200/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  28%|▎| 4200/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  28%|▎| 4200/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -39218,8 +39187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4201/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  28%|▎| 4201/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  28%|▎| 4201/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  28%|▎| 4201/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -39227,8 +39196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4202/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  28%|▎| 4202/14932 [06:01<15:24, 11.61it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  28%|▎| 4202/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  28%|▎| 4202/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -39236,8 +39205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4203/14932 [06:02<15:24, 11.61it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  28%|▎| 4203/14932 [06:02<15:24, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  28%|▎| 4203/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  28%|▎| 4203/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -39245,8 +39214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4204/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  28%|▎| 4204/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  28%|▎| 4204/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  28%|▎| 4204/14932 [05:57<15:13, 11.74it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -39254,8 +39223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4205/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  28%|▎| 4205/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  28%|▎| 4205/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  28%|▎| 4205/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -39263,8 +39232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4206/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  28%|▎| 4206/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  28%|▎| 4206/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  28%|▎| 4206/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -39272,8 +39241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4207/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  28%|▎| 4207/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  28%|▎| 4207/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  28%|▎| 4207/14932 [05:58<15:13, 11.74it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -39281,8 +39250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4208/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  28%|▎| 4208/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  28%|▎| 4208/14932 [05:58<15:13, 11.75it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  28%|▎| 4208/14932 [05:58<15:13, 11.75it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -39290,8 +39259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4209/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  28%|▎| 4209/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=5.06"
+      "Epoch 0:  28%|▎| 4209/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  28%|▎| 4209/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -39299,8 +39268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4210/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=5.06\r",
-      "Epoch 0:  28%|▎| 4210/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  28%|▎| 4210/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  28%|▎| 4210/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -39308,8 +39277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4211/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  28%|▎| 4211/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  28%|▎| 4211/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  28%|▎| 4211/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -39317,8 +39286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4212/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  28%|▎| 4212/14932 [06:02<15:23, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  28%|▎| 4212/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  28%|▎| 4212/14932 [05:58<15:12, 11.74it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -39326,8 +39295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4213/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  28%|▎| 4213/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  28%|▎| 4213/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  28%|▎| 4213/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -39335,8 +39304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4214/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  28%|▎| 4214/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  28%|▎| 4214/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  28%|▎| 4214/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -39344,8 +39313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4215/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  28%|▎| 4215/14932 [06:02<15:22, 11.61it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  28%|▎| 4215/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  28%|▎| 4215/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -39353,8 +39322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4216/14932 [06:02<15:22, 11.62it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  28%|▎| 4216/14932 [06:02<15:22, 11.62it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  28%|▎| 4216/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  28%|▎| 4216/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -39362,8 +39331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4217/14932 [06:03<15:22, 11.61it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  28%|▎| 4217/14932 [06:03<15:22, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  28%|▎| 4217/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  28%|▎| 4217/14932 [05:58<15:12, 11.75it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -39371,8 +39340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4218/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  28%|▎| 4218/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  28%|▎| 4218/14932 [05:59<15:12, 11.75it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  28%|▎| 4218/14932 [05:59<15:12, 11.75it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -39380,8 +39349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4219/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  28%|▎| 4219/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  28%|▎| 4219/14932 [05:59<15:12, 11.75it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  28%|▎| 4219/14932 [05:59<15:12, 11.75it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -39389,8 +39358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4220/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  28%|▎| 4220/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  28%|▎| 4220/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  28%|▎| 4220/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -39398,8 +39367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4221/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  28%|▎| 4221/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  28%|▎| 4221/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  28%|▎| 4221/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -39407,8 +39376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4222/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  28%|▎| 4222/14932 [06:03<15:23, 11.60it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  28%|▎| 4222/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  28%|▎| 4222/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -39416,8 +39385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4223/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  28%|▎| 4223/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=5.22"
+      "Epoch 0:  28%|▎| 4223/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  28%|▎| 4223/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -39425,8 +39394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4224/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=5.22\r",
-      "Epoch 0:  28%|▎| 4224/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  28%|▎| 4224/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  28%|▎| 4224/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -39434,8 +39403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4225/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  28%|▎| 4225/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  28%|▎| 4225/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  28%|▎| 4225/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -39443,8 +39412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4226/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  28%|▎| 4226/14932 [06:04<15:23, 11.60it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  28%|▎| 4226/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  28%|▎| 4226/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -39452,8 +39421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4227/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  28%|▎| 4227/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  28%|▎| 4227/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  28%|▎| 4227/14932 [05:59<15:11, 11.74it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -39461,8 +39430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4228/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  28%|▎| 4228/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  28%|▎| 4228/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  28%|▎| 4228/14932 [05:59<15:11, 11.75it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -39470,8 +39439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4229/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  28%|▎| 4229/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  28%|▎| 4229/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  28%|▎| 4229/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -39479,8 +39448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4230/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  28%|▎| 4230/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  28%|▎| 4230/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  28%|▎| 4230/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -39488,8 +39457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4231/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  28%|▎| 4231/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  28%|▎| 4231/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  28%|▎| 4231/14932 [06:00<15:11, 11.75it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -39497,8 +39466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4232/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  28%|▎| 4232/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  28%|▎| 4232/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  28%|▎| 4232/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -39506,8 +39475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4233/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  28%|▎| 4233/14932 [06:04<15:22, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  28%|▎| 4233/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  28%|▎| 4233/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -39515,8 +39484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4234/14932 [06:05<15:22, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  28%|▎| 4234/14932 [06:05<15:22, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  28%|▎| 4234/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  28%|▎| 4234/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -39524,8 +39493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4235/14932 [06:05<15:22, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  28%|▎| 4235/14932 [06:05<15:22, 11.60it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  28%|▎| 4235/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  28%|▎| 4235/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -39533,8 +39502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4236/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  28%|▎| 4236/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  28%|▎| 4236/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  28%|▎| 4236/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -39542,8 +39511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4237/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  28%|▎| 4237/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  28%|▎| 4237/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  28%|▎| 4237/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -39551,8 +39520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4238/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  28%|▎| 4238/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  28%|▎| 4238/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  28%|▎| 4238/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -39560,8 +39529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4239/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  28%|▎| 4239/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  28%|▎| 4239/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  28%|▎| 4239/14932 [06:00<15:10, 11.75it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -39569,8 +39538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4240/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  28%|▎| 4240/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  28%|▎| 4240/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  28%|▎| 4240/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -39578,8 +39547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4241/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  28%|▎| 4241/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  28%|▎| 4241/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  28%|▎| 4241/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -39587,8 +39556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4242/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  28%|▎| 4242/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  28%|▎| 4242/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  28%|▎| 4242/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -39596,8 +39565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4243/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  28%|▎| 4243/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  28%|▎| 4243/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  28%|▎| 4243/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -39605,8 +39574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4244/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  28%|▎| 4244/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  28%|▎| 4244/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  28%|▎| 4244/14932 [06:01<15:10, 11.74it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -39614,8 +39583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4245/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  28%|▎| 4245/14932 [06:05<15:21, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  28%|▎| 4245/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  28%|▎| 4245/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -39623,8 +39592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4246/14932 [06:06<15:21, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  28%|▎| 4246/14932 [06:06<15:21, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  28%|▎| 4246/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  28%|▎| 4246/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -39632,8 +39601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4247/14932 [06:06<15:21, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  28%|▎| 4247/14932 [06:06<15:21, 11.60it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  28%|▎| 4247/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  28%|▎| 4247/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -39641,8 +39610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4248/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  28%|▎| 4248/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  28%|▎| 4248/14932 [06:01<15:09, 11.74it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  28%|▎| 4248/14932 [06:01<15:09, 11.74it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -39650,8 +39619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4249/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  28%|▎| 4249/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  28%|▎| 4249/14932 [06:01<15:09, 11.74it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  28%|▎| 4249/14932 [06:01<15:09, 11.74it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -39659,8 +39628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4250/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  28%|▎| 4250/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  28%|▎| 4250/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  28%|▎| 4250/14932 [06:01<15:09, 11.74it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -39668,8 +39637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4251/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  28%|▎| 4251/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  28%|▎| 4251/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  28%|▎| 4251/14932 [06:01<15:09, 11.75it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -39677,8 +39646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4252/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  28%|▎| 4252/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  28%|▎| 4252/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  28%|▎| 4252/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -39686,8 +39655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4253/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  28%|▎| 4253/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  28%|▎| 4253/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  28%|▎| 4253/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -39695,8 +39664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4254/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  28%|▎| 4254/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  28%|▎| 4254/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  28%|▎| 4254/14932 [06:02<15:09, 11.75it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -39704,8 +39673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  28%|▎| 4255/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  28%|▎| 4255/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  28%|▎| 4255/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  28%|▎| 4255/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -39713,8 +39682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4256/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  29%|▎| 4256/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  29%|▎| 4256/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  29%|▎| 4256/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -39722,8 +39691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4257/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  29%|▎| 4257/14932 [06:06<15:20, 11.60it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  29%|▎| 4257/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  29%|▎| 4257/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -39731,8 +39700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4258/14932 [06:06<15:19, 11.60it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  29%|▎| 4258/14932 [06:06<15:19, 11.60it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  29%|▎| 4258/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  29%|▎| 4258/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -39740,8 +39709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4259/14932 [06:07<15:20, 11.60it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  29%|▎| 4259/14932 [06:07<15:20, 11.60it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  29%|▎| 4259/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  29%|▎| 4259/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -39749,8 +39718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4260/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  29%|▎| 4260/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  29%|▎| 4260/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  29%|▎| 4260/14932 [06:02<15:09, 11.74it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -39758,8 +39727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4261/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  29%|▎| 4261/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  29%|▎| 4261/14932 [06:02<15:08, 11.74it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  29%|▎| 4261/14932 [06:02<15:08, 11.74it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -39767,8 +39736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4262/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  29%|▎| 4262/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  29%|▎| 4262/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  29%|▎| 4262/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -39776,8 +39745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4263/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  29%|▎| 4263/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  29%|▎| 4263/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  29%|▎| 4263/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -39785,8 +39754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4264/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  29%|▎| 4264/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  29%|▎| 4264/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  29%|▎| 4264/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -39794,8 +39763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4265/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  29%|▎| 4265/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  29%|▎| 4265/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  29%|▎| 4265/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -39803,8 +39772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4266/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  29%|▎| 4266/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  29%|▎| 4266/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  29%|▎| 4266/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -39812,8 +39781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4267/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  29%|▎| 4267/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  29%|▎| 4267/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  29%|▎| 4267/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -39821,8 +39790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4268/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  29%|▎| 4268/14932 [06:07<15:19, 11.60it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  29%|▎| 4268/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  29%|▎| 4268/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -39830,8 +39799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4269/14932 [06:07<15:18, 11.60it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  29%|▎| 4269/14932 [06:07<15:18, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  29%|▎| 4269/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  29%|▎| 4269/14932 [06:03<15:08, 11.74it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -39839,8 +39808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4270/14932 [06:07<15:18, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  29%|▎| 4270/14932 [06:07<15:18, 11.60it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  29%|▎| 4270/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  29%|▎| 4270/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -39848,8 +39817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4271/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  29%|▎| 4271/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  29%|▎| 4271/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  29%|▎| 4271/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -39857,8 +39826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4272/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  29%|▎| 4272/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  29%|▎| 4272/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  29%|▎| 4272/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -39866,8 +39835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4273/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  29%|▎| 4273/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  29%|▎| 4273/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=1.61\r",
+      "Epoch 0:  29%|▎| 4273/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=0.65"
      ]
     },
     {
@@ -39875,8 +39844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4274/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  29%|▎| 4274/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  29%|▎| 4274/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=0.65\r",
+      "Epoch 0:  29%|▎| 4274/14932 [06:03<15:07, 11.74it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -39884,8 +39853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4275/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  29%|▎| 4275/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  29%|▎| 4275/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  29%|▎| 4275/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -39893,8 +39862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4276/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  29%|▎| 4276/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  29%|▎| 4276/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4276/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -39902,8 +39871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4277/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  29%|▎| 4277/14932 [06:08<15:18, 11.60it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  29%|▎| 4277/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  29%|▎| 4277/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -39911,8 +39880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4278/14932 [06:08<15:18, 11.61it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  29%|▎| 4278/14932 [06:08<15:18, 11.61it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  29%|▎| 4278/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  29%|▎| 4278/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -39920,8 +39889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4279/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  29%|▎| 4279/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  29%|▎| 4279/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  29%|▎| 4279/14932 [06:04<15:07, 11.74it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -39929,8 +39898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4280/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  29%|▎| 4280/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  29%|▎| 4280/14932 [06:04<15:06, 11.74it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  29%|▎| 4280/14932 [06:04<15:06, 11.74it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -39938,8 +39907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4281/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  29%|▎| 4281/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  29%|▎| 4281/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  29%|▎| 4281/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -39947,8 +39916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4282/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  29%|▎| 4282/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  29%|▎| 4282/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  29%|▎| 4282/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -39956,8 +39925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4283/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  29%|▎| 4283/14932 [06:08<15:17, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  29%|▎| 4283/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  29%|▎| 4283/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -39965,8 +39934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4284/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  29%|▎| 4284/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  29%|▎| 4284/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  29%|▎| 4284/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -39974,8 +39943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4285/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  29%|▎| 4285/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  29%|▎| 4285/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  29%|▎| 4285/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -39983,8 +39952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4286/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  29%|▎| 4286/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  29%|▎| 4286/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  29%|▎| 4286/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -39992,8 +39961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4287/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  29%|▎| 4287/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  29%|▎| 4287/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  29%|▎| 4287/14932 [06:04<15:06, 11.75it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -40001,8 +39970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4288/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  29%|▎| 4288/14932 [06:09<15:17, 11.61it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  29%|▎| 4288/14932 [06:05<15:06, 11.74it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  29%|▎| 4288/14932 [06:05<15:06, 11.74it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -40010,8 +39979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4289/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  29%|▎| 4289/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  29%|▎| 4289/14932 [06:05<15:06, 11.74it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  29%|▎| 4289/14932 [06:05<15:06, 11.74it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -40019,8 +39988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4290/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  29%|▎| 4290/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  29%|▎| 4290/14932 [06:05<15:06, 11.75it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  29%|▎| 4290/14932 [06:05<15:06, 11.75it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -40028,8 +39997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4291/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  29%|▎| 4291/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  29%|▎| 4291/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  29%|▎| 4291/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -40037,8 +40006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4292/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  29%|▎| 4292/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  29%|▎| 4292/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  29%|▎| 4292/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -40046,7 +40015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4293/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  29%|▎| 4293/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  29%|▎| 4293/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -40054,7 +40024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4293/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  29%|▎| 4294/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  29%|▎| 4294/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -40062,8 +40033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4294/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  29%|▎| 4294/14932 [06:09<15:16, 11.61it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  29%|▎| 4295/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  29%|▎| 4295/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -40071,8 +40042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4295/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  29%|▎| 4295/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  29%|▎| 4296/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4296/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -40080,8 +40051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4296/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  29%|▎| 4296/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  29%|▎| 4297/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  29%|▎| 4297/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -40089,8 +40060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4297/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  29%|▎| 4297/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  29%|▎| 4298/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  29%|▎| 4298/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -40098,8 +40069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4298/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  29%|▎| 4298/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  29%|▎| 4299/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  29%|▎| 4299/14932 [06:05<15:05, 11.75it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -40107,8 +40078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4299/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  29%|▎| 4299/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  29%|▎| 4300/14932 [06:06<15:05, 11.75it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  29%|▎| 4300/14932 [06:06<15:05, 11.75it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -40116,8 +40087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4300/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  29%|▎| 4300/14932 [06:10<15:16, 11.61it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  29%|▎| 4301/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  29%|▎| 4301/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -40125,8 +40096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4301/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  29%|▎| 4301/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  29%|▎| 4302/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  29%|▎| 4302/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -40134,8 +40105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4302/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  29%|▎| 4302/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  29%|▎| 4303/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  29%|▎| 4303/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -40143,8 +40114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4303/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  29%|▎| 4303/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  29%|▎| 4304/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  29%|▎| 4304/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -40152,8 +40123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4304/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  29%|▎| 4304/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  29%|▎| 4305/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  29%|▎| 4305/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -40161,8 +40132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4305/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  29%|▎| 4305/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  29%|▎| 4306/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  29%|▎| 4306/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -40170,8 +40141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4306/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  29%|▎| 4306/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  29%|▎| 4307/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  29%|▎| 4307/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -40179,8 +40150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4307/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  29%|▎| 4307/14932 [06:10<15:15, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  29%|▎| 4308/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  29%|▎| 4308/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -40188,8 +40159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4308/14932 [06:11<15:15, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  29%|▎| 4308/14932 [06:11<15:15, 11.61it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  29%|▎| 4309/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  29%|▎| 4309/14932 [06:06<15:04, 11.75it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -40197,8 +40168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4309/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  29%|▎| 4309/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  29%|▎| 4310/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  29%|▎| 4310/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -40206,8 +40177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4310/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  29%|▎| 4310/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  29%|▎| 4311/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  29%|▎| 4311/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -40215,8 +40186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4311/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  29%|▎| 4311/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  29%|▎| 4312/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  29%|▎| 4312/14932 [06:06<15:03, 11.75it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -40224,8 +40195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4312/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  29%|▎| 4312/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  29%|▎| 4313/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  29%|▎| 4313/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -40233,8 +40204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4313/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  29%|▎| 4313/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  29%|▎| 4314/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  29%|▎| 4314/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -40242,8 +40213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4314/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  29%|▎| 4314/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  29%|▎| 4315/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  29%|▎| 4315/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -40251,8 +40222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4315/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  29%|▎| 4315/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  29%|▎| 4316/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  29%|▎| 4316/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -40260,8 +40231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4316/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  29%|▎| 4316/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  29%|▎| 4317/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  29%|▎| 4317/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -40269,8 +40240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4317/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  29%|▎| 4317/14932 [06:11<15:14, 11.61it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  29%|▎| 4318/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  29%|▎| 4318/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -40278,8 +40249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4318/14932 [06:11<15:13, 11.61it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  29%|▎| 4318/14932 [06:11<15:13, 11.61it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  29%|▎| 4319/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  29%|▎| 4319/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -40287,8 +40258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4319/14932 [06:11<15:13, 11.61it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  29%|▎| 4319/14932 [06:11<15:13, 11.61it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  29%|▎| 4320/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  29%|▎| 4320/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -40296,8 +40267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4320/14932 [06:12<15:14, 11.61it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  29%|▎| 4320/14932 [06:12<15:14, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  29%|▎| 4321/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4321/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -40305,7 +40276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4321/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  29%|▎| 4322/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  29%|▎| 4322/14932 [06:07<15:03, 11.75it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -40313,7 +40285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4321/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  29%|▎| 4323/14932 [06:07<15:02, 11.75it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  29%|▎| 4323/14932 [06:07<15:02, 11.75it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -40321,8 +40294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4322/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  29%|▎| 4322/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  29%|▎| 4324/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  29%|▎| 4324/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -40330,8 +40303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4323/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  29%|▎| 4323/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  29%|▎| 4325/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  29%|▎| 4325/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -40339,8 +40312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4324/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  29%|▎| 4324/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  29%|▎| 4326/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  29%|▎| 4326/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -40348,8 +40321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4325/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  29%|▎| 4325/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  29%|▎| 4327/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  29%|▎| 4327/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -40357,8 +40330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4326/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  29%|▎| 4326/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  29%|▎| 4328/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  29%|▎| 4328/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -40366,8 +40339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4327/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  29%|▎| 4327/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  29%|▎| 4329/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  29%|▎| 4329/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -40375,8 +40348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4328/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  29%|▎| 4328/14932 [06:12<15:13, 11.61it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  29%|▎| 4330/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  29%|▎| 4330/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -40384,8 +40357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4329/14932 [06:12<15:12, 11.61it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  29%|▎| 4329/14932 [06:12<15:12, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  29%|▎| 4331/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  29%|▎| 4331/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -40393,8 +40366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4330/14932 [06:12<15:12, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  29%|▎| 4330/14932 [06:12<15:12, 11.61it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  29%|▎| 4332/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4332/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -40402,8 +40375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4331/14932 [06:12<15:12, 11.62it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  29%|▎| 4331/14932 [06:12<15:12, 11.62it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  29%|▎| 4333/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  29%|▎| 4333/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -40411,8 +40384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4332/14932 [06:12<15:12, 11.62it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  29%|▎| 4332/14932 [06:12<15:12, 11.62it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  29%|▎| 4334/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  29%|▎| 4334/14932 [06:08<15:02, 11.75it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -40420,8 +40393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4333/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  29%|▎| 4333/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  29%|▎| 4335/14932 [06:08<15:01, 11.75it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  29%|▎| 4335/14932 [06:08<15:01, 11.75it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -40429,8 +40402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4334/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  29%|▎| 4334/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  29%|▎| 4336/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  29%|▎| 4336/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -40438,8 +40411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4335/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  29%|▎| 4335/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  29%|▎| 4337/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  29%|▎| 4337/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -40447,8 +40420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4336/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  29%|▎| 4336/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  29%|▎| 4338/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  29%|▎| 4338/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -40456,8 +40429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4337/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  29%|▎| 4337/14932 [06:13<15:12, 11.62it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  29%|▎| 4339/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  29%|▎| 4339/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -40465,8 +40438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4338/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  29%|▎| 4338/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  29%|▎| 4340/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  29%|▎| 4340/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -40474,8 +40447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4339/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  29%|▎| 4339/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  29%|▎| 4341/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  29%|▎| 4341/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -40483,8 +40456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4340/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  29%|▎| 4340/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  29%|▎| 4342/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  29%|▎| 4342/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -40492,8 +40465,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4341/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  29%|▎| 4341/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  29%|▎| 4343/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -40501,8 +40473,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4342/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  29%|▎| 4342/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  29%|▎| 4343/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -40510,8 +40481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4343/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  29%|▎| 4343/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  29%|▎| 4344/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4344/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -40519,8 +40490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4344/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  29%|▎| 4344/14932 [06:13<15:11, 11.62it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  29%|▎| 4345/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  29%|▎| 4345/14932 [06:09<15:01, 11.75it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -40528,8 +40499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4345/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  29%|▎| 4345/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  29%|▎| 4346/14932 [06:09<15:00, 11.75it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  29%|▎| 4346/14932 [06:09<15:00, 11.75it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -40537,8 +40508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4346/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  29%|▎| 4346/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  29%|▎| 4347/14932 [06:09<15:00, 11.75it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  29%|▎| 4347/14932 [06:09<15:00, 11.75it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -40546,8 +40517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4347/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  29%|▎| 4347/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  29%|▎| 4348/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  29%|▎| 4348/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -40555,8 +40526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4348/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  29%|▎| 4348/14932 [06:14<15:11, 11.62it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  29%|▎| 4349/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  29%|▎| 4349/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -40564,8 +40535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4349/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  29%|▎| 4349/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  29%|▎| 4350/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  29%|▎| 4350/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -40573,8 +40544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4350/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  29%|▎| 4350/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  29%|▎| 4351/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  29%|▎| 4351/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -40582,8 +40553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4351/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  29%|▎| 4351/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  29%|▎| 4352/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  29%|▎| 4352/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=5.38"
      ]
     },
     {
@@ -40591,8 +40562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4352/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  29%|▎| 4352/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  29%|▎| 4353/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=5.38\r",
+      "Epoch 0:  29%|▎| 4353/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -40600,8 +40571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4353/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  29%|▎| 4353/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  29%|▎| 4354/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  29%|▎| 4354/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -40609,8 +40580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4354/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  29%|▎| 4354/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  29%|▎| 4355/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  29%|▎| 4355/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -40618,8 +40589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4355/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  29%|▎| 4355/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  29%|▎| 4356/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  29%|▎| 4356/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -40627,8 +40598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4356/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  29%|▎| 4356/14932 [06:14<15:10, 11.62it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  29%|▎| 4357/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  29%|▎| 4357/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -40636,8 +40607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4357/14932 [06:15<15:10, 11.62it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  29%|▎| 4357/14932 [06:15<15:10, 11.62it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  29%|▎| 4358/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  29%|▎| 4358/14932 [06:10<15:00, 11.75it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -40645,8 +40616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4358/14932 [06:15<15:10, 11.62it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  29%|▎| 4358/14932 [06:15<15:10, 11.62it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  29%|▎| 4359/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  29%|▎| 4359/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -40654,8 +40625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4359/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  29%|▎| 4359/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  29%|▎| 4360/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  29%|▎| 4360/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -40663,8 +40634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4360/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  29%|▎| 4360/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  29%|▎| 4361/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  29%|▎| 4361/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -40672,8 +40643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4361/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  29%|▎| 4361/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  29%|▎| 4362/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  29%|▎| 4362/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -40681,8 +40652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4362/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  29%|▎| 4362/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  29%|▎| 4363/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  29%|▎| 4363/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -40690,8 +40661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4363/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  29%|▎| 4363/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  29%|▎| 4364/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  29%|▎| 4364/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -40699,8 +40670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4364/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  29%|▎| 4364/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  29%|▎| 4365/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  29%|▎| 4365/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -40708,8 +40679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4365/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  29%|▎| 4365/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  29%|▎| 4366/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  29%|▎| 4366/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -40717,8 +40688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4366/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  29%|▎| 4366/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  29%|▎| 4367/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  29%|▎| 4367/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -40726,8 +40697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4367/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  29%|▎| 4367/14932 [06:15<15:09, 11.62it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  29%|▎| 4368/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  29%|▎| 4368/14932 [06:11<14:59, 11.75it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -40735,8 +40706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4368/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  29%|▎| 4368/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  29%|▎| 4369/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  29%|▎| 4369/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -40744,8 +40715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4369/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  29%|▎| 4369/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  29%|▎| 4370/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  29%|▎| 4370/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -40753,8 +40724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4370/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  29%|▎| 4370/14932 [06:15<15:08, 11.62it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  29%|▎| 4371/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  29%|▎| 4371/14932 [06:11<14:58, 11.75it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -40762,8 +40733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4371/14932 [06:16<15:08, 11.62it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  29%|▎| 4371/14932 [06:16<15:08, 11.62it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  29%|▎| 4372/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  29%|▎| 4372/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -40771,8 +40742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4372/14932 [06:16<15:08, 11.62it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  29%|▎| 4372/14932 [06:16<15:08, 11.62it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  29%|▎| 4373/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  29%|▎| 4373/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -40780,8 +40751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4373/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  29%|▎| 4373/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  29%|▎| 4374/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  29%|▎| 4374/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -40789,8 +40760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4374/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  29%|▎| 4374/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  29%|▎| 4375/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  29%|▎| 4375/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -40798,8 +40769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4375/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  29%|▎| 4375/14932 [06:16<15:08, 11.63it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  29%|▎| 4376/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  29%|▎| 4376/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -40807,8 +40778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4376/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  29%|▎| 4376/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  29%|▎| 4377/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  29%|▎| 4377/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -40816,8 +40787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4377/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  29%|▎| 4377/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  29%|▎| 4378/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  29%|▎| 4378/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -40825,8 +40796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4378/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  29%|▎| 4378/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  29%|▎| 4379/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  29%|▎| 4379/14932 [06:12<14:58, 11.75it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -40834,7 +40805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4379/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  29%|▎| 4380/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  29%|▎| 4380/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -40842,7 +40814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4379/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  29%|▎| 4381/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  29%|▎| 4381/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -40850,8 +40823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4380/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  29%|▎| 4380/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  29%|▎| 4382/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  29%|▎| 4382/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -40859,8 +40832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4381/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  29%|▎| 4381/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  29%|▎| 4383/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  29%|▎| 4383/14932 [06:12<14:57, 11.75it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -40868,8 +40841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4382/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  29%|▎| 4382/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  29%|▎| 4384/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  29%|▎| 4384/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -40877,8 +40850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4383/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  29%|▎| 4383/14932 [06:16<15:07, 11.63it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  29%|▎| 4385/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  29%|▎| 4385/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -40886,8 +40859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4384/14932 [06:17<15:07, 11.63it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  29%|▎| 4384/14932 [06:17<15:07, 11.63it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  29%|▎| 4386/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  29%|▎| 4386/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -40895,8 +40868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4385/14932 [06:17<15:07, 11.63it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  29%|▎| 4385/14932 [06:17<15:07, 11.63it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  29%|▎| 4387/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  29%|▎| 4387/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -40904,8 +40877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4386/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  29%|▎| 4386/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  29%|▎| 4388/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  29%|▎| 4388/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -40913,8 +40886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4387/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  29%|▎| 4387/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  29%|▎| 4389/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  29%|▎| 4389/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -40922,8 +40895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4388/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  29%|▎| 4388/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  29%|▎| 4390/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  29%|▎| 4390/14932 [06:13<14:57, 11.75it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -40931,8 +40904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4389/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  29%|▎| 4389/14932 [06:17<15:07, 11.62it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  29%|▎| 4391/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  29%|▎| 4391/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -40940,8 +40913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4390/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  29%|▎| 4390/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  29%|▎| 4392/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  29%|▎| 4392/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -40949,8 +40922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4391/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  29%|▎| 4391/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  29%|▎| 4393/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  29%|▎| 4393/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -40958,8 +40931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4392/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  29%|▎| 4392/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  29%|▎| 4394/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  29%|▎| 4394/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -40967,8 +40940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4393/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  29%|▎| 4393/14932 [06:17<15:06, 11.62it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  29%|▎| 4395/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  29%|▎| 4395/14932 [06:13<14:56, 11.75it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -40976,8 +40949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4394/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  29%|▎| 4394/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  29%|▎| 4396/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  29%|▎| 4396/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -40985,8 +40958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4395/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  29%|▎| 4395/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=5.22"
+      "Epoch 0:  29%|▎| 4397/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  29%|▎| 4397/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=1.60"
      ]
     },
     {
@@ -40994,8 +40967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4396/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=5.22\r",
-      "Epoch 0:  29%|▎| 4396/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  29%|▎| 4398/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=1.60\r",
+      "Epoch 0:  29%|▎| 4398/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -41003,8 +40976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4397/14932 [06:18<15:06, 11.63it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  29%|▎| 4397/14932 [06:18<15:06, 11.63it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  29%|▎| 4399/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  29%|▎| 4399/14932 [06:14<14:56, 11.75it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -41012,8 +40985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4398/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  29%|▎| 4398/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  29%|▎| 4400/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  29%|▎| 4400/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -41021,8 +40994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4399/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  29%|▎| 4399/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  29%|▎| 4401/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  29%|▎| 4401/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -41030,8 +41003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4400/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  29%|▎| 4400/14932 [06:18<15:06, 11.62it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  29%|▎| 4402/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  29%|▎| 4402/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -41039,8 +41012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4401/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  29%|▎| 4401/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  29%|▎| 4403/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  29%|▎| 4403/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -41048,8 +41021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|��| 4402/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  29%|▎| 4402/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  29%|▎| 4404/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  29%|▎| 4404/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -41057,8 +41030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4403/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  29%|▎| 4403/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  30%|▎| 4405/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  30%|▎| 4405/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -41066,8 +41039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  29%|▎| 4404/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  29%|▎| 4404/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  30%|▎| 4406/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  30%|▎| 4406/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -41075,8 +41048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4405/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  30%|▎| 4405/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  30%|▎| 4407/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  30%|▎| 4407/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -41084,8 +41057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4406/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  30%|▎| 4406/14932 [06:18<15:05, 11.63it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  30%|▎| 4408/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  30%|▎| 4408/14932 [06:14<14:55, 11.76it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -41093,8 +41066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4407/14932 [06:19<15:05, 11.63it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  30%|▎| 4407/14932 [06:19<15:05, 11.63it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  30%|▎| 4409/14932 [06:15<14:55, 11.76it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  30%|▎| 4409/14932 [06:15<14:55, 11.76it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -41102,8 +41075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4408/14932 [06:19<15:05, 11.63it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  30%|▎| 4408/14932 [06:19<15:05, 11.63it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  30%|▎| 4410/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  30%|▎| 4410/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -41111,8 +41084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4409/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  30%|▎| 4409/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  30%|▎| 4411/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  30%|▎| 4411/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -41120,8 +41093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4410/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  30%|▎| 4410/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  30%|▎| 4412/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  30%|▎| 4412/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -41129,8 +41102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4411/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  30%|▎| 4411/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  30%|▎| 4413/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  30%|▎| 4413/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -41138,8 +41111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4412/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  30%|▎| 4412/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  30%|▎| 4414/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  30%|▎| 4414/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -41147,8 +41120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4413/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  30%|▎| 4413/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  30%|▎| 4415/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  30%|▎| 4415/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -41156,8 +41129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4414/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  30%|▎| 4414/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  30%|▎| 4416/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  30%|▎| 4416/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -41165,8 +41138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4415/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  30%|▎| 4415/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  30%|▎| 4417/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  30%|▎| 4417/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -41174,8 +41147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4416/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  30%|▎| 4416/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  30%|▎| 4418/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  30%|▎| 4418/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -41183,8 +41156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4417/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  30%|▎| 4417/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  30%|▎| 4419/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  30%|▎| 4419/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=5.06"
      ]
     },
     {
@@ -41192,8 +41165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4418/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  30%|▎| 4418/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  30%|▎| 4420/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=5.06\r",
+      "Epoch 0:  30%|▎| 4420/14932 [06:15<14:54, 11.76it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -41201,8 +41174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4419/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  30%|▎| 4419/14932 [06:19<15:04, 11.63it/s, v_num=o30c, train/loss=1.69"
+      "Epoch 0:  30%|▎| 4421/14932 [06:16<14:54, 11.76it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  30%|▎| 4421/14932 [06:16<14:54, 11.76it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -41210,8 +41183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4420/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=1.69\r",
-      "Epoch 0:  30%|▎| 4420/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  30%|▎| 4422/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  30%|▎| 4422/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -41219,8 +41192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4421/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  30%|▎| 4421/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=1.25"
+      "Epoch 0:  30%|▎| 4423/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  30%|▎| 4423/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -41228,8 +41201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4422/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=1.25\r",
-      "Epoch 0:  30%|▎| 4422/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  30%|▎| 4424/14932 [06:16<14:54, 11.75it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  30%|▎| 4424/14932 [06:16<14:54, 11.75it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -41237,8 +41210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4423/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  30%|▎| 4423/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  30%|▎| 4425/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  30%|▎| 4425/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -41246,8 +41219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4424/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  30%|▎| 4424/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  30%|▎| 4426/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  30%|▎| 4426/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -41255,8 +41228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4425/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  30%|▎| 4425/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  30%|▎| 4427/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  30%|▎| 4427/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -41264,8 +41237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4426/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  30%|▎| 4426/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  30%|▎| 4428/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  30%|▎| 4428/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -41273,8 +41246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4427/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  30%|▎| 4427/14932 [06:20<15:03, 11.63it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  30%|▎| 4429/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  30%|▎| 4429/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -41282,8 +41255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4428/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  30%|▎| 4428/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  30%|▎| 4430/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  30%|▎| 4430/14932 [06:16<14:53, 11.75it/s, v_num=ui8w, train/loss=1.22"
      ]
     },
     {
@@ -41291,8 +41264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4429/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  30%|▎| 4429/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  30%|▎| 4431/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=1.22\r",
+      "Epoch 0:  30%|▎| 4431/14932 [06:16<14:53, 11.76it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -41300,8 +41273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4430/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  30%|▎| 4430/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  30%|▎| 4432/14932 [06:17<14:53, 11.76it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  30%|▎| 4432/14932 [06:17<14:53, 11.76it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -41309,8 +41282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4431/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  30%|▎| 4431/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  30%|▎| 4433/14932 [06:17<14:53, 11.76it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  30%|▎| 4433/14932 [06:17<14:53, 11.76it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -41318,8 +41291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4432/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  30%|▎| 4432/14932 [06:20<15:02, 11.63it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  30%|▎| 4434/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  30%|▎| 4434/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -41327,8 +41300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4433/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  30%|▎| 4433/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  30%|▎| 4435/14932 [06:17<14:53, 11.75it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  30%|▎| 4435/14932 [06:17<14:53, 11.75it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -41336,8 +41309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4434/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  30%|▎| 4434/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  30%|▎| 4436/14932 [06:17<14:53, 11.75it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  30%|▎| 4436/14932 [06:17<14:53, 11.75it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -41345,8 +41318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4435/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  30%|▎| 4435/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  30%|▎| 4437/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  30%|▎| 4437/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -41354,8 +41327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4436/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  30%|▎| 4436/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  30%|▎| 4438/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  30%|▎| 4438/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -41363,8 +41336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4437/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  30%|▎| 4437/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  30%|▎| 4439/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  30%|▎| 4439/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -41372,8 +41345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4438/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  30%|▎| 4438/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  30%|▎| 4440/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  30%|▎| 4440/14932 [06:17<14:52, 11.75it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -41381,8 +41354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4439/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  30%|▎| 4439/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  30%|▎| 4441/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  30%|▎| 4441/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -41390,8 +41363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4440/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  30%|▎| 4440/14932 [06:21<15:02, 11.63it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  30%|▎| 4442/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  30%|▎| 4442/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -41399,8 +41372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4441/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  30%|▎| 4441/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  30%|▎| 4443/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  30%|▎| 4443/14932 [06:17<14:52, 11.76it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -41408,8 +41381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4442/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  30%|▎| 4442/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  30%|▎| 4444/14932 [06:18<14:52, 11.76it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  30%|▎| 4444/14932 [06:18<14:52, 11.76it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -41417,8 +41390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4443/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  30%|▎| 4443/14932 [06:21<15:01, 11.63it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  30%|▎| 4445/14932 [06:18<14:52, 11.76it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  30%|▎| 4445/14932 [06:18<14:52, 11.76it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -41426,8 +41399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4444/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  30%|▎| 4444/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  30%|▎| 4446/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  30%|▎| 4446/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -41435,8 +41408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4445/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  30%|▎| 4445/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  30%|▎| 4447/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  30%|▎| 4447/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -41444,8 +41417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4446/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  30%|▎| 4446/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  30%|▎| 4448/14932 [06:18<14:52, 11.75it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  30%|▎| 4448/14932 [06:18<14:52, 11.75it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -41453,8 +41426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4447/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  30%|▎| 4447/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  30%|▎| 4449/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  30%|▎| 4449/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -41462,8 +41435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4448/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  30%|▎| 4448/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  30%|▎| 4450/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  30%|▎| 4450/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -41471,8 +41444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4449/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  30%|▎| 4449/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  30%|▎| 4451/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  30%|▎| 4451/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -41480,8 +41453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4450/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  30%|▎| 4450/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  30%|▎| 4452/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  30%|▎| 4452/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -41489,8 +41462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4451/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  30%|▎| 4451/14932 [06:22<15:01, 11.63it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  30%|▎| 4453/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  30%|▎| 4453/14932 [06:18<14:51, 11.75it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -41498,8 +41471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4452/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  30%|▎| 4452/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  30%|▎| 4454/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  30%|▎| 4454/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -41507,8 +41480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4453/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  30%|▎| 4453/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  30%|▎| 4455/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  30%|▎| 4455/14932 [06:18<14:51, 11.76it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -41516,8 +41489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4454/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  30%|▎| 4454/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  30%|▎| 4456/14932 [06:19<14:51, 11.76it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  30%|▎| 4456/14932 [06:19<14:51, 11.76it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -41525,8 +41498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4455/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  30%|▎| 4455/14932 [06:22<15:00, 11.63it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  30%|▎| 4457/14932 [06:19<14:51, 11.76it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  30%|▎| 4457/14932 [06:19<14:51, 11.76it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -41534,8 +41507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4456/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  30%|▎| 4456/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  30%|▎| 4458/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  30%|▎| 4458/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -41543,8 +41516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4457/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  30%|▎| 4457/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  30%|▎| 4459/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  30%|▎| 4459/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -41552,8 +41525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4458/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  30%|▎| 4458/14932 [06:23<15:00, 11.63it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  30%|▎| 4460/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  30%|▎| 4460/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -41561,8 +41534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4459/14932 [06:23<15:00, 11.64it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  30%|▎| 4459/14932 [06:23<15:00, 11.64it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  30%|▎| 4461/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  30%|▎| 4461/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -41570,8 +41543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4460/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  30%|▎| 4460/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  30%|▎| 4462/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  30%|▎| 4462/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -41579,8 +41552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4461/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  30%|▎| 4461/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  30%|▎| 4463/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  30%|▎| 4463/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -41588,8 +41561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4462/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  30%|▎| 4462/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  30%|▎| 4464/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  30%|▎| 4464/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -41597,8 +41570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4463/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  30%|▎| 4463/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  30%|▎| 4465/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  30%|▎| 4465/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -41606,8 +41579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4464/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  30%|▎| 4464/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  30%|▎| 4466/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  30%|▎| 4466/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -41615,8 +41588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4465/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  30%|▎| 4465/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  30%|▎| 4467/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  30%|▎| 4467/14932 [06:19<14:50, 11.76it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -41624,8 +41597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4466/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  30%|▎| 4466/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  30%|▎| 4468/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  30%|▎| 4468/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -41633,8 +41606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4467/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  30%|▎| 4467/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  30%|▎| 4469/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  30%|▎| 4469/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -41642,8 +41615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4468/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  30%|▎| 4468/14932 [06:23<14:59, 11.64it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  30%|▎| 4470/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  30%|▎| 4470/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -41651,8 +41624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4469/14932 [06:23<14:58, 11.64it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  30%|▎| 4469/14932 [06:23<14:58, 11.64it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  30%|▎| 4471/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  30%|▎| 4471/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -41660,8 +41633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4470/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  30%|▎| 4470/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.56"
+      "Epoch 0:  30%|▎| 4472/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  30%|▎| 4472/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -41669,8 +41642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4471/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.56\r",
-      "Epoch 0:  30%|▎| 4471/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  30%|▎| 4473/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  30%|▎| 4473/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -41678,8 +41651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4472/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  30%|▎| 4472/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  30%|▎| 4474/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  30%|▎| 4474/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -41687,8 +41660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4473/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  30%|▎| 4473/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.57"
+      "Epoch 0:  30%|▎| 4475/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  30%|▎| 4475/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -41696,8 +41669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4474/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.57\r",
-      "Epoch 0:  30%|▎| 4474/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  30%|▎| 4476/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  30%|▎| 4476/14932 [06:20<14:49, 11.76it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -41705,8 +41678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4475/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  30%|▎| 4475/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  30%|▎| 4477/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  30%|▎| 4477/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -41714,8 +41687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4476/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  30%|▎| 4476/14932 [06:24<14:58, 11.64it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  30%|▎| 4478/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  30%|▎| 4478/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -41723,8 +41696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4477/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  30%|▎| 4477/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  30%|▎| 4479/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  30%|▎| 4479/14932 [06:20<14:48, 11.76it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -41732,8 +41705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4478/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  30%|▎| 4478/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  30%|▎| 4480/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  30%|▎| 4480/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -41741,8 +41714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4479/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  30%|▎| 4479/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  30%|▎| 4481/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  30%|▎| 4481/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -41750,8 +41723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4480/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  30%|▎| 4480/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  30%|▎| 4482/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  30%|▎| 4482/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -41759,8 +41732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4481/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  30%|▎| 4481/14932 [06:24<14:57, 11.64it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  30%|▎| 4483/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  30%|▎| 4483/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -41768,8 +41741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4482/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  30%|▎| 4482/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  30%|▎| 4484/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  30%|▎| 4484/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -41777,8 +41750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4483/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  30%|▎| 4483/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  30%|▎| 4485/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  30%|▎| 4485/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -41786,8 +41759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4484/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  30%|▎| 4484/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  30%|▎| 4486/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  30%|▎| 4486/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -41795,8 +41768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4485/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  30%|▎| 4485/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  30%|▎| 4487/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  30%|▎| 4487/14932 [06:21<14:48, 11.76it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -41804,8 +41777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4486/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  30%|▎| 4486/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  30%|▎| 4488/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  30%|▎| 4488/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -41813,8 +41786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4487/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  30%|▎| 4487/14932 [06:25<14:57, 11.64it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  30%|▎| 4489/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  30%|▎| 4489/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -41822,8 +41795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4488/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  30%|▎| 4488/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  30%|▎| 4490/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  30%|▎| 4490/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -41831,8 +41804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4489/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  30%|▎| 4489/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  30%|▎| 4491/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  30%|▎| 4491/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -41840,8 +41813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4490/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  30%|▎| 4490/14932 [06:25<14:56, 11.64it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  30%|▎| 4492/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  30%|▎| 4492/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -41849,8 +41822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4491/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  30%|▎| 4491/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  30%|▎| 4493/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  30%|▎| 4493/14932 [06:21<14:47, 11.76it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -41858,8 +41831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4492/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  30%|▎| 4492/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  30%|▎| 4494/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  30%|▎| 4494/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -41867,8 +41840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4493/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  30%|▎| 4493/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  30%|▎| 4495/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  30%|▎| 4495/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -41876,8 +41849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4494/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  30%|▎| 4494/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  30%|▎| 4496/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  30%|▎| 4496/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -41885,8 +41858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4495/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  30%|▎| 4495/14932 [06:25<14:56, 11.65it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  30%|▎| 4497/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  30%|▎| 4497/14932 [06:22<14:47, 11.76it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -41894,8 +41867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4496/14932 [06:26<14:56, 11.65it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  30%|▎| 4496/14932 [06:26<14:56, 11.65it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  30%|▎| 4498/14932 [06:22<14:46, 11.76it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  30%|▎| 4498/14932 [06:22<14:46, 11.76it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -41903,8 +41876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4497/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  30%|▎| 4497/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  30%|▎| 4499/14932 [06:22<14:46, 11.76it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  30%|▎| 4499/14932 [06:22<14:46, 11.76it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -41912,8 +41885,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4498/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  30%|▎| 4498/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=5.06"
+      "Epoch 0:  30%|▎| 4500/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -41921,8 +41893,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4499/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=5.06\r",
-      "Epoch 0:  30%|▎| 4499/14932 [06:26<14:55, 11.65it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  30%|▎| 4500/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -41930,8 +41901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4500/14932 [06:26<14:56, 11.64it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  30%|▎| 4500/14932 [06:26<14:56, 11.64it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  30%|▎| 4501/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  30%|▎| 4501/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -41939,8 +41910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4501/14932 [06:26<14:56, 11.64it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  30%|▎| 4501/14932 [06:26<14:56, 11.64it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  30%|▎| 4502/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  30%|▎| 4502/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -41948,8 +41919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4502/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  30%|▎| 4502/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  30%|▎| 4503/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  30%|▎| 4503/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -41957,8 +41928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4503/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  30%|▎| 4503/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  30%|▎| 4504/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  30%|▎| 4504/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -41966,8 +41937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4504/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  30%|▎| 4504/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  30%|▎| 4505/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  30%|▎| 4505/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -41975,8 +41946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4505/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  30%|▎| 4505/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  30%|▎| 4506/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  30%|▎| 4506/14932 [06:22<14:46, 11.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -41984,8 +41955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4506/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  30%|▎| 4506/14932 [06:26<14:55, 11.64it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  30%|▎| 4507/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  30%|▎| 4507/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -41993,8 +41964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4507/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  30%|▎| 4507/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  30%|▎| 4508/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  30%|▎| 4508/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -42002,8 +41973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4508/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  30%|▎| 4508/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  30%|▎| 4509/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  30%|▎| 4509/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -42011,8 +41982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4509/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  30%|▎| 4509/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  30%|▎| 4510/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  30%|▎| 4510/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -42020,8 +41991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4510/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  30%|▎| 4510/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  30%|▎| 4511/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  30%|▎| 4511/14932 [06:23<14:45, 11.77it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -42029,8 +42000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4511/14932 [06:27<14:54, 11.65it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  30%|▎| 4511/14932 [06:27<14:54, 11.65it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  30%|▎| 4512/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  30%|▎| 4512/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -42038,8 +42009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4512/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  30%|▎| 4512/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  30%|▎| 4513/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  30%|▎| 4513/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -42047,8 +42018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4513/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  30%|▎| 4513/14932 [06:27<14:55, 11.64it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  30%|▎| 4514/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  30%|▎| 4514/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -42056,8 +42027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4514/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  30%|▎| 4514/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  30%|▎| 4515/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  30%|▎| 4515/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -42065,8 +42036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4515/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  30%|▎| 4515/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  30%|▎| 4516/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  30%|▎| 4516/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -42074,8 +42045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4516/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  30%|▎| 4516/14932 [06:27<14:54, 11.64it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  30%|▎| 4517/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  30%|▎| 4517/14932 [06:23<14:45, 11.76it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -42083,7 +42054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4517/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  30%|▎| 4518/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  30%|▎| 4518/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -42091,7 +42063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4517/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  30%|▎| 4519/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  30%|▎| 4519/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -42099,8 +42072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4518/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  30%|▎| 4518/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=0.79"
+      "Epoch 0:  30%|▎| 4520/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  30%|▎| 4520/14932 [06:24<14:45, 11.76it/s, v_num=ui8w, train/loss=1.05"
      ]
     },
     {
@@ -42108,8 +42081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4519/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=0.79\r",
-      "Epoch 0:  30%|▎| 4519/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  30%|▎| 4521/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=1.05\r",
+      "Epoch 0:  30%|▎| 4521/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -42117,8 +42090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4520/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  30%|▎| 4520/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  30%|▎| 4522/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  30%|▎| 4522/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -42126,8 +42099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4521/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  30%|▎| 4521/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  30%|▎| 4523/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  30%|▎| 4523/14932 [06:24<14:44, 11.76it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -42135,8 +42108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4522/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  30%|▎| 4522/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  30%|▎| 4524/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  30%|▎| 4524/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -42144,8 +42117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4523/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  30%|▎| 4523/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  30%|▎| 4525/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  30%|▎| 4525/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=0.84"
      ]
     },
     {
@@ -42153,8 +42126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4524/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  30%|▎| 4524/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  30%|▎| 4526/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=0.84\r",
+      "Epoch 0:  30%|▎| 4526/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -42162,8 +42135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4525/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  30%|▎| 4525/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  30%|▎| 4527/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  30%|▎| 4527/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -42171,8 +42144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4526/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  30%|▎| 4526/14932 [06:28<14:54, 11.64it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  30%|▎| 4528/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  30%|▎| 4528/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -42180,8 +42153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4527/14932 [06:28<14:53, 11.64it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  30%|▎| 4527/14932 [06:28<14:53, 11.64it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  30%|▎| 4529/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  30%|▎| 4529/14932 [06:24<14:44, 11.77it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -42189,8 +42162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4528/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  30%|▎| 4528/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:  30%|▎| 4530/14932 [06:24<14:43, 11.77it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  30%|▎| 4530/14932 [06:24<14:43, 11.77it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -42198,8 +42171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4529/14932 [06:29<14:54, 11.63it/s, v_num=o30c, train/loss=4.94\r",
-      "Epoch 0:  30%|▎| 4529/14932 [06:29<14:54, 11.63it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  30%|▎| 4531/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  30%|▎| 4531/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -42207,8 +42180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4530/14932 [06:29<14:54, 11.64it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  30%|▎| 4530/14932 [06:29<14:54, 11.64it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  30%|▎| 4532/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  30%|▎| 4532/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -42216,8 +42189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4531/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  30%|▎| 4531/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  30%|▎| 4533/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  30%|▎| 4533/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -42225,8 +42198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4532/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  30%|▎| 4532/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  30%|▎| 4534/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  30%|▎| 4534/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -42234,8 +42207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4533/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  30%|▎| 4533/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  30%|▎| 4535/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  30%|▎| 4535/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -42243,8 +42216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4534/14932 [06:29<14:53, 11.63it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  30%|▎| 4534/14932 [06:29<14:53, 11.63it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  30%|▎| 4536/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  30%|▎| 4536/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -42252,8 +42225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4535/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  30%|▎| 4535/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  30%|▎| 4537/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  30%|▎| 4537/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -42261,8 +42234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4536/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  30%|▎| 4536/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  30%|▎| 4538/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  30%|▎| 4538/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -42270,8 +42243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4537/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  30%|▎| 4537/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  30%|▎| 4539/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  30%|▎| 4539/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -42279,8 +42252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4538/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  30%|▎| 4538/14932 [06:29<14:53, 11.64it/s, v_num=o30c, train/loss=1.00"
+      "Epoch 0:  30%|▎| 4540/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  30%|▎| 4540/14932 [06:25<14:43, 11.77it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -42288,8 +42261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4539/14932 [06:30<14:53, 11.64it/s, v_num=o30c, train/loss=1.00\r",
-      "Epoch 0:  30%|▎| 4539/14932 [06:30<14:53, 11.64it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  30%|▎| 4541/14932 [06:25<14:42, 11.77it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  30%|▎| 4541/14932 [06:25<14:42, 11.77it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -42297,8 +42270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4540/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  30%|▎| 4540/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=0.96"
+      "Epoch 0:  30%|▎| 4542/14932 [06:25<14:42, 11.77it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  30%|▎| 4542/14932 [06:25<14:42, 11.77it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -42306,8 +42279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4541/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=0.96\r",
-      "Epoch 0:  30%|▎| 4541/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  30%|▎| 4543/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  30%|▎| 4543/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -42315,8 +42288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4542/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  30%|▎| 4542/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  30%|▎| 4544/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  30%|▎| 4544/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -42324,8 +42297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4543/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  30%|▎| 4543/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  30%|▎| 4545/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  30%|▎| 4545/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -42333,8 +42306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4544/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  30%|▎| 4544/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  30%|▎| 4546/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  30%|▎| 4546/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -42342,8 +42315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4545/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  30%|▎| 4545/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  30%|▎| 4547/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  30%|▎| 4547/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -42351,8 +42324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4546/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  30%|▎| 4546/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  30%|▎| 4548/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  30%|▎| 4548/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -42360,8 +42333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4547/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  30%|▎| 4547/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  30%|▎| 4549/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  30%|▎| 4549/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -42369,8 +42342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4548/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  30%|▎| 4548/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  30%|▎| 4550/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  30%|▎| 4550/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -42378,8 +42351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4549/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  30%|▎| 4549/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  30%|▎| 4551/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  30%|▎| 4551/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -42387,8 +42360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4550/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  30%|▎| 4550/14932 [06:30<14:52, 11.64it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  30%|▎| 4552/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  30%|▎| 4552/14932 [06:26<14:42, 11.77it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -42396,8 +42369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4551/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  30%|▎| 4551/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  30%|▎| 4553/14932 [06:26<14:41, 11.77it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  30%|▎| 4553/14932 [06:26<14:41, 11.77it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -42405,8 +42378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4552/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  30%|▎| 4552/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  30%|▎| 4554/14932 [06:26<14:41, 11.77it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  30%|▎| 4554/14932 [06:26<14:41, 11.77it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -42414,8 +42387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4553/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  30%|▎| 4553/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  31%|▎| 4555/14932 [06:27<14:41, 11.77it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  31%|▎| 4555/14932 [06:27<14:41, 11.77it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -42423,8 +42396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  30%|▎| 4554/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  30%|▎| 4554/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  31%|▎| 4556/14932 [06:27<14:42, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  31%|▎| 4556/14932 [06:27<14:42, 11.76it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -42432,8 +42405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4555/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  31%|▎| 4555/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  31%|▎| 4557/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  31%|▎| 4557/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -42441,8 +42414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4556/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  31%|▎| 4556/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  31%|▎| 4558/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  31%|▎| 4558/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -42450,8 +42423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4557/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  31%|▎| 4557/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  31%|▎| 4559/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  31%|▎| 4559/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -42459,8 +42432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4558/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  31%|▎| 4558/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  31%|▎| 4560/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  31%|▎| 4560/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -42468,8 +42441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4559/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  31%|▎| 4559/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  31%|▎| 4561/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  31%|▎| 4561/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -42477,8 +42450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4560/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  31%|▎| 4560/14932 [06:31<14:51, 11.64it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  31%|▎| 4562/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  31%|▎| 4562/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -42486,8 +42459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4561/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  31%|▎| 4561/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  31%|▎| 4563/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  31%|▎| 4563/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -42495,8 +42468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4562/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  31%|▎| 4562/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  31%|▎| 4564/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  31%|▎| 4564/14932 [06:27<14:41, 11.76it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -42504,8 +42477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4563/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  31%|▎| 4563/14932 [06:31<14:50, 11.64it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  31%|▎| 4565/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  31%|▎| 4565/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -42513,8 +42486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4564/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  31%|▎| 4564/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  31%|▎| 4566/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  31%|▎| 4566/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -42522,8 +42495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4565/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  31%|▎| 4565/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  31%|▎| 4567/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  31%|▎| 4567/14932 [06:28<14:41, 11.76it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -42531,8 +42504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4566/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  31%|▎| 4566/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  31%|▎| 4568/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  31%|▎| 4568/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -42540,8 +42513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4567/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  31%|▎| 4567/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  31%|▎| 4569/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  31%|▎| 4569/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -42549,8 +42522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4568/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  31%|▎| 4568/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  31%|▎| 4570/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  31%|▎| 4570/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -42558,8 +42531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4569/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  31%|▎| 4569/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  31%|▎| 4571/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  31%|▎| 4571/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -42567,8 +42540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4570/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  31%|▎| 4570/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  31%|▎| 4572/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  31%|▎| 4572/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -42576,8 +42549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4571/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  31%|▎| 4571/14932 [06:32<14:50, 11.64it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  31%|▎| 4573/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  31%|▎| 4573/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -42585,8 +42558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4572/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  31%|▎| 4572/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  31%|▎| 4574/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  31%|▎| 4574/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -42594,8 +42567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4573/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  31%|▎| 4573/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  31%|▎| 4575/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  31%|▎| 4575/14932 [06:28<14:40, 11.77it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -42603,8 +42576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4574/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  31%|▎| 4574/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  31%|▎| 4576/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  31%|▎| 4576/14932 [06:28<14:40, 11.76it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -42612,8 +42585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4575/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  31%|▎| 4575/14932 [06:32<14:49, 11.64it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  31%|▎| 4577/14932 [06:29<14:40, 11.76it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  31%|▎| 4577/14932 [06:29<14:40, 11.76it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -42621,8 +42594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4576/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  31%|▎| 4576/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  31%|▎| 4578/14932 [06:29<14:40, 11.76it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  31%|▎| 4578/14932 [06:29<14:40, 11.76it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -42630,8 +42603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4577/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  31%|▎| 4577/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  31%|▎| 4579/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  31%|▎| 4579/14932 [06:29<14:39, 11.76it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -42639,8 +42612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4578/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  31%|▎| 4578/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:  31%|▎| 4580/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  31%|▎| 4580/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -42648,8 +42621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4579/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:  31%|▎| 4579/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  31%|▎| 4581/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  31%|▎| 4581/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -42657,8 +42630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4580/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  31%|▎| 4580/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  31%|▎| 4582/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  31%|▎| 4582/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -42666,8 +42639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4581/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  31%|▎| 4581/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  31%|▎| 4583/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  31%|▎| 4583/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -42675,8 +42648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4582/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  31%|▎| 4582/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  31%|▎| 4584/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  31%|▎| 4584/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -42684,8 +42657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4583/14932 [06:33<14:48, 11.64it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  31%|▎| 4583/14932 [06:33<14:48, 11.64it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  31%|▎| 4585/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  31%|▎| 4585/14932 [06:29<14:39, 11.77it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -42693,8 +42666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4584/14932 [06:33<14:48, 11.64it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  31%|▎| 4584/14932 [06:33<14:48, 11.64it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  31%|▎| 4586/14932 [06:29<14:39, 11.76it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  31%|▎| 4586/14932 [06:29<14:39, 11.76it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -42702,8 +42675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4585/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  31%|▎| 4585/14932 [06:33<14:49, 11.64it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  31%|▎| 4587/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  31%|▎| 4587/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -42711,8 +42684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4586/14932 [06:34<14:49, 11.64it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  31%|▎| 4586/14932 [06:34<14:49, 11.64it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  31%|▎| 4588/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  31%|▎| 4588/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -42720,8 +42693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4587/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  31%|▎| 4587/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  31%|▎| 4589/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  31%|▎| 4589/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -42729,8 +42702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4588/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  31%|▎| 4588/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  31%|▎| 4590/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  31%|▎| 4590/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -42738,8 +42711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4589/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  31%|▎| 4589/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  31%|▎| 4591/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  31%|▎| 4591/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -42747,8 +42720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4590/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  31%|▎| 4590/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  31%|▎| 4592/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  31%|▎| 4592/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -42756,8 +42729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4591/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  31%|▎| 4591/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  31%|▎| 4593/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  31%|▎| 4593/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -42765,8 +42738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4592/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  31%|▎| 4592/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  31%|▎| 4594/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  31%|▎| 4594/14932 [06:30<14:39, 11.76it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -42774,8 +42747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4593/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  31%|▎| 4593/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  31%|▎| 4595/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  31%|▎| 4595/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -42783,8 +42756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4594/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  31%|▎| 4594/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  31%|▎| 4596/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  31%|▎| 4596/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -42792,8 +42765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4595/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  31%|▎| 4595/14932 [06:34<14:48, 11.64it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  31%|▎| 4597/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  31%|▎| 4597/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -42801,8 +42774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4596/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  31%|▎| 4596/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  31%|▎| 4598/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  31%|▎| 4598/14932 [06:30<14:38, 11.76it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -42810,8 +42783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4597/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  31%|▎| 4597/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  31%|▎| 4599/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  31%|▎| 4599/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -42819,8 +42792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4598/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  31%|▎| 4598/14932 [06:34<14:47, 11.64it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  31%|▎| 4600/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  31%|▎| 4600/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -42828,8 +42801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4599/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  31%|▎| 4599/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  31%|▎| 4601/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  31%|▎| 4601/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -42837,8 +42810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4600/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  31%|▎| 4600/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  31%|▎| 4602/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  31%|▎| 4602/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -42846,8 +42819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4601/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  31%|▎| 4601/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  31%|▎| 4603/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  31%|▎| 4603/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -42855,8 +42828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4602/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  31%|▎| 4602/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  31%|▎| 4604/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  31%|▎| 4604/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -42864,8 +42837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4603/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  31%|▎| 4603/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  31%|▎| 4605/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  31%|▎| 4605/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -42873,8 +42846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4604/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  31%|▎| 4604/14932 [06:35<14:47, 11.64it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  31%|▎| 4606/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  31%|▎| 4606/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -42882,8 +42855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4605/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  31%|▎| 4605/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  31%|▎| 4607/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  31%|▎| 4607/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -42891,8 +42864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4606/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  31%|▎| 4606/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  31%|▎| 4608/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  31%|▎| 4608/14932 [06:31<14:38, 11.76it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -42900,8 +42873,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4607/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  31%|▎| 4607/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  31%|▎| 4609/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -42909,8 +42881,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4608/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  31%|▎| 4608/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  31%|▎| 4609/14932 [06:31<14:37, 11.76it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -42918,8 +42889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4609/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  31%|▎| 4609/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  31%|▎| 4610/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  31%|▎| 4610/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -42927,8 +42898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4610/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  31%|▎| 4610/14932 [06:35<14:46, 11.64it/s, v_num=o30c, train/loss=0.91"
+      "Epoch 0:  31%|▎| 4611/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  31%|▎| 4611/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -42936,8 +42907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4611/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=0.91\r",
-      "Epoch 0:  31%|▎| 4611/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  31%|▎| 4612/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  31%|▎| 4612/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -42945,8 +42916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4612/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  31%|▎| 4612/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  31%|▎| 4613/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  31%|▎| 4613/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -42954,8 +42925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4613/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  31%|▎| 4613/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  31%|▎| 4614/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  31%|▎| 4614/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -42963,8 +42934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4614/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  31%|▎| 4614/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  31%|▎| 4615/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  31%|▎| 4615/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -42972,8 +42943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4615/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  31%|▎| 4615/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  31%|▎| 4616/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  31%|▎| 4616/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -42981,8 +42952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4616/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  31%|▎| 4616/14932 [06:36<14:46, 11.64it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  31%|▎| 4617/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  31%|▎| 4617/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -42990,8 +42961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4617/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  31%|▎| 4617/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  31%|▎| 4618/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  31%|▎| 4618/14932 [06:32<14:37, 11.76it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -42999,8 +42970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4618/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  31%|▎| 4618/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  31%|▎| 4619/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  31%|▎| 4619/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -43008,8 +42979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4619/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  31%|▎| 4619/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  31%|▎| 4620/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  31%|▎| 4620/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -43017,8 +42988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4620/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  31%|▎| 4620/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  31%|▎| 4621/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  31%|▎| 4621/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -43026,8 +42997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4621/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  31%|▎| 4621/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  31%|▎| 4622/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  31%|▎| 4622/14932 [06:32<14:36, 11.76it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -43035,8 +43006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4622/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  31%|▎| 4622/14932 [06:36<14:45, 11.64it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  31%|▎| 4623/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  31%|▎| 4623/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -43044,8 +43015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4623/14932 [06:37<14:45, 11.64it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  31%|▎| 4623/14932 [06:37<14:45, 11.64it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  31%|▎| 4624/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  31%|▎| 4624/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -43053,8 +43024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4624/14932 [06:37<14:45, 11.65it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  31%|▎| 4624/14932 [06:37<14:45, 11.65it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  31%|▎| 4625/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  31%|▎| 4625/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -43062,8 +43033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4625/14932 [06:37<14:45, 11.65it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  31%|▎| 4625/14932 [06:37<14:45, 11.65it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  31%|▎| 4626/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:  31%|▎| 4626/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -43071,8 +43042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4626/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  31%|▎| 4626/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  31%|▎| 4627/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  31%|▎| 4627/14932 [06:33<14:36, 11.76it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -43080,8 +43051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4627/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  31%|▎| 4627/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  31%|▎| 4628/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  31%|▎| 4628/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -43089,8 +43060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4628/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  31%|▎| 4628/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  31%|▎| 4629/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  31%|▎| 4629/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -43098,8 +43069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4629/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  31%|▎| 4629/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  31%|▎| 4630/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  31%|▎| 4630/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -43107,8 +43078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4630/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  31%|▎| 4630/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  31%|▎| 4631/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  31%|▎| 4631/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -43116,8 +43087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4631/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  31%|▎| 4631/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  31%|▎| 4632/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  31%|▎| 4632/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -43125,8 +43096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4632/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  31%|▎| 4632/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  31%|▎| 4633/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  31%|▎| 4633/14932 [06:33<14:35, 11.76it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -43134,8 +43105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4633/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  31%|▎| 4633/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  31%|▎| 4634/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  31%|▎| 4634/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -43143,8 +43114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4634/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  31%|▎| 4634/14932 [06:37<14:44, 11.65it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  31%|▎| 4635/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  31%|▎| 4635/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -43152,8 +43123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4635/14932 [06:37<14:43, 11.65it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  31%|▎| 4635/14932 [06:37<14:43, 11.65it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  31%|▎| 4636/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  31%|▎| 4636/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -43161,8 +43132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4636/14932 [06:37<14:43, 11.65it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  31%|▎| 4636/14932 [06:37<14:43, 11.65it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  31%|▎| 4637/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  31%|▎| 4637/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -43170,8 +43141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4637/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  31%|▎| 4637/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  31%|▎| 4638/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  31%|▎| 4638/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -43179,8 +43150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4638/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  31%|▎| 4638/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  31%|▎| 4639/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  31%|▎| 4639/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -43188,8 +43159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4639/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  31%|▎| 4639/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  31%|▎| 4640/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  31%|▎| 4640/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -43197,8 +43168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4640/14932 [06:38<14:43, 11.64it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  31%|▎| 4640/14932 [06:38<14:43, 11.64it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  31%|▎| 4641/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  31%|▎| 4641/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -43206,8 +43177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4641/14932 [06:38<14:43, 11.64it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  31%|▎| 4641/14932 [06:38<14:43, 11.64it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  31%|▎| 4642/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  31%|▎| 4642/14932 [06:34<14:35, 11.76it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -43215,8 +43186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4642/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  31%|▎| 4642/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  31%|▎| 4643/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  31%|▎| 4643/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -43224,8 +43195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4643/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  31%|▎| 4643/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  31%|▎| 4644/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  31%|▎| 4644/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -43233,8 +43204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4644/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  31%|▎| 4644/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  31%|▎| 4645/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  31%|▎| 4645/14932 [06:34<14:34, 11.76it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -43242,8 +43213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4645/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  31%|▎| 4645/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  31%|▎| 4646/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  31%|▎| 4646/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -43251,8 +43222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4646/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  31%|▎| 4646/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  31%|▎| 4647/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  31%|▎| 4647/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -43260,8 +43231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4647/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  31%|▎| 4647/14932 [06:38<14:43, 11.65it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  31%|▎| 4648/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  31%|▎| 4648/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -43269,8 +43240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4648/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  31%|▎| 4648/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  31%|▎| 4649/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  31%|▎| 4649/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -43278,8 +43249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4649/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  31%|▎| 4649/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  31%|▎| 4650/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  31%|▎| 4650/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -43287,8 +43258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4650/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  31%|▎| 4650/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  31%|▎| 4651/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  31%|▎| 4651/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -43296,8 +43267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4651/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  31%|▎| 4651/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  31%|▎| 4652/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  31%|▎| 4652/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -43305,8 +43276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4652/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  31%|▎| 4652/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  31%|▎| 4653/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  31%|▎| 4653/14932 [06:35<14:34, 11.76it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -43314,8 +43285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4653/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  31%|▎| 4653/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  31%|▎| 4654/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  31%|▎| 4654/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -43323,8 +43294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4654/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  31%|▎| 4654/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  31%|▎| 4655/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  31%|▎| 4655/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -43332,8 +43303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4655/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  31%|▎| 4655/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  31%|▎| 4656/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  31%|▎| 4656/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -43341,8 +43312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4656/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  31%|▎| 4656/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=1.01"
+      "Epoch 0:  31%|▎| 4657/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  31%|▎| 4657/14932 [06:35<14:33, 11.76it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -43350,8 +43321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4657/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=1.01\r",
-      "Epoch 0:  31%|▎| 4657/14932 [06:39<14:42, 11.65it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  31%|▎| 4658/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  31%|▎| 4658/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -43359,8 +43330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4658/14932 [06:39<14:41, 11.65it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  31%|▎| 4658/14932 [06:39<14:41, 11.65it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  31%|▎| 4659/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  31%|▎| 4659/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -43368,8 +43339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4659/14932 [06:39<14:41, 11.65it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  31%|▎| 4659/14932 [06:39<14:41, 11.65it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  31%|▎| 4660/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  31%|▎| 4660/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -43377,8 +43348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4660/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  31%|▎| 4660/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  31%|▎| 4661/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  31%|▎| 4661/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -43386,8 +43357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4661/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  31%|▎| 4661/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  31%|▎| 4662/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  31%|▎| 4662/14932 [06:36<14:33, 11.76it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -43395,8 +43366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4662/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  31%|▎| 4662/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  31%|▎| 4663/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  31%|▎| 4663/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -43404,8 +43375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4663/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  31%|▎| 4663/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  31%|▎| 4664/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  31%|▎| 4664/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -43413,8 +43384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4664/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  31%|▎| 4664/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  31%|▎| 4665/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  31%|▎| 4665/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -43422,8 +43393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4665/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  31%|▎| 4665/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  31%|▎| 4666/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  31%|▎| 4666/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -43431,8 +43402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4666/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  31%|▎| 4666/14932 [06:40<14:41, 11.65it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  31%|▎| 4667/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  31%|▎| 4667/14932 [06:36<14:32, 11.76it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -43440,8 +43411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4667/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  31%|▎| 4667/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  31%|▎| 4668/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  31%|▎| 4668/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -43449,8 +43420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4668/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  31%|▎| 4668/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  31%|▎| 4669/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  31%|▎| 4669/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -43458,8 +43429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4669/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  31%|▎| 4669/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  31%|▎| 4670/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  31%|▎| 4670/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -43467,8 +43438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4670/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  31%|▎| 4670/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  31%|▎| 4671/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  31%|▎| 4671/14932 [06:36<14:32, 11.77it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -43476,8 +43447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4671/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  31%|▎| 4671/14932 [06:40<14:40, 11.65it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  31%|▎| 4672/14932 [06:37<14:32, 11.76it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  31%|▎| 4672/14932 [06:37<14:32, 11.76it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -43485,8 +43456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4672/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  31%|▎| 4672/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  31%|▎| 4673/14932 [06:37<14:32, 11.76it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  31%|▎| 4673/14932 [06:37<14:32, 11.76it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -43494,8 +43465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4673/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  31%|▎| 4673/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  31%|▎| 4674/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  31%|▎| 4674/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -43503,8 +43474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4674/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  31%|▎| 4674/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  31%|▎| 4675/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  31%|▎| 4675/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -43512,8 +43483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4675/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  31%|▎| 4675/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  31%|▎| 4676/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  31%|▎| 4676/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -43521,8 +43492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4676/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  31%|▎| 4676/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  31%|▎| 4677/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  31%|▎| 4677/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -43530,8 +43501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4677/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  31%|▎| 4677/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  31%|▎| 4678/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  31%|▎| 4678/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -43539,8 +43510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4678/14932 [06:41<14:40, 11.64it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  31%|▎| 4678/14932 [06:41<14:40, 11.64it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  31%|▎| 4679/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  31%|▎| 4679/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -43548,8 +43519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4679/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  31%|▎| 4679/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  31%|▎| 4680/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  31%|▎| 4680/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -43557,8 +43528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4680/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  31%|▎| 4680/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  31%|▎| 4681/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  31%|▎| 4681/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -43566,8 +43537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4681/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  31%|▎| 4681/14932 [06:41<14:40, 11.65it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  31%|▎| 4682/14932 [06:37<14:31, 11.77it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  31%|▎| 4682/14932 [06:37<14:31, 11.76it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -43575,8 +43546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4682/14932 [06:42<14:40, 11.65it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  31%|▎| 4682/14932 [06:42<14:40, 11.65it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  31%|▎| 4683/14932 [06:38<14:31, 11.77it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  31%|▎| 4683/14932 [06:38<14:31, 11.77it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -43584,8 +43555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4683/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  31%|▎| 4683/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  31%|▎| 4684/14932 [06:38<14:31, 11.77it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  31%|▎| 4684/14932 [06:38<14:31, 11.77it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -43593,8 +43564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4684/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  31%|▎| 4684/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  31%|▎| 4685/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  31%|▎| 4685/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -43602,8 +43573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4685/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  31%|▎| 4685/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  31%|▎| 4686/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  31%|▎| 4686/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -43611,8 +43582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4686/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  31%|▎| 4686/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  31%|▎| 4687/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  31%|▎| 4687/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -43620,8 +43591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4687/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  31%|▎| 4687/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  31%|▎| 4688/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  31%|▎| 4688/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -43629,8 +43600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4688/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  31%|▎| 4688/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  31%|▎| 4689/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  31%|▎| 4689/14932 [06:38<14:30, 11.76it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -43638,8 +43609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4689/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  31%|▎| 4689/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  31%|▎| 4690/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  31%|��| 4690/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -43647,8 +43618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4690/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  31%|▎| 4690/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  31%|▎| 4691/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  31%|▎| 4691/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -43656,8 +43627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4691/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  31%|▎| 4691/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  31%|▎| 4692/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  31%|▎| 4692/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=1.86"
      ]
     },
     {
@@ -43665,8 +43636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4692/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  31%|▎| 4692/14932 [06:42<14:39, 11.65it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  31%|▎| 4693/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=1.86\r",
+      "Epoch 0:  31%|▎| 4693/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -43674,8 +43645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4693/14932 [06:42<14:38, 11.65it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  31%|▎| 4693/14932 [06:42<14:38, 11.65it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  31%|▎| 4694/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  31%|▎| 4694/14932 [06:38<14:30, 11.77it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -43683,8 +43654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4694/14932 [06:42<14:38, 11.65it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  31%|▎| 4694/14932 [06:42<14:38, 11.65it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  31%|▎| 4695/14932 [06:38<14:29, 11.77it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  31%|▎| 4695/14932 [06:38<14:29, 11.77it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -43692,8 +43663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4695/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  31%|▎| 4695/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  31%|▎| 4696/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  31%|▎| 4696/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -43701,8 +43672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4696/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  31%|▎| 4696/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  31%|▎| 4697/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  31%|▎| 4697/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -43710,8 +43681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4697/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  31%|▎| 4697/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  31%|▎| 4698/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  31%|▎| 4698/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -43719,8 +43690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4698/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  31%|▎| 4698/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  31%|▎| 4699/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  31%|▎| 4699/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -43728,8 +43699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4699/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  31%|▎| 4699/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  31%|▎| 4700/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  31%|▎| 4700/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -43737,8 +43708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4700/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  31%|▎| 4700/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  31%|▎| 4701/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  31%|▎| 4701/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -43746,8 +43717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4701/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  31%|▎| 4701/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  31%|▎| 4702/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  31%|▎| 4702/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -43755,8 +43726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4702/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  31%|▎| 4702/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  31%|▎| 4703/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  31%|▎| 4703/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -43764,8 +43735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  31%|▎| 4703/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  31%|▎| 4703/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  32%|▎| 4704/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  32%|▎| 4704/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -43773,8 +43744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4704/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  32%|▎| 4704/14932 [06:43<14:38, 11.65it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  32%|▎| 4705/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  32%|▎| 4705/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -43782,8 +43753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4705/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  32%|▎| 4705/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  32%|▎| 4706/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  32%|▎| 4706/14932 [06:39<14:29, 11.77it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -43791,8 +43762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4706/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  32%|▎| 4706/14932 [06:43<14:37, 11.65it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  32%|▎| 4707/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  32%|▎| 4707/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -43800,8 +43771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4707/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  32%|▎| 4707/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  32%|▎| 4708/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  32%|▎| 4708/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -43809,8 +43780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4708/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  32%|▎| 4708/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  32%|▎| 4709/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  32%|▎| 4709/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -43818,8 +43789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4709/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  32%|▎| 4709/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  32%|▎| 4710/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  32%|▎| 4710/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=5.16"
      ]
     },
     {
@@ -43827,8 +43798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4710/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  32%|▎| 4710/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  32%|▎| 4711/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=5.16\r",
+      "Epoch 0:  32%|▎| 4711/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -43836,8 +43807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4711/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  32%|▎| 4711/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  32%|▎| 4712/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  32%|▎| 4712/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -43845,8 +43816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4712/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  32%|▎| 4712/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  32%|▎| 4713/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  32%|▎| 4713/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -43854,8 +43825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4713/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  32%|▎| 4713/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  32%|▎| 4714/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  32%|▎| 4714/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -43863,8 +43834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4714/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  32%|▎| 4714/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  32%|▎| 4715/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  32%|▎| 4715/14932 [06:40<14:28, 11.77it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -43872,8 +43843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4715/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  32%|▎| 4715/14932 [06:44<14:37, 11.65it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  32%|▎| 4716/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  32%|▎| 4716/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -43881,8 +43852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4716/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  32%|▎| 4716/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  32%|▎| 4717/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  32%|▎| 4717/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -43890,8 +43861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4717/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  32%|▎| 4717/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  32%|▎| 4718/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  32%|▎| 4718/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -43899,8 +43870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4718/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  32%|▎| 4718/14932 [06:44<14:36, 11.65it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  32%|▎| 4719/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  32%|▎| 4719/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -43908,8 +43879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4719/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  32%|▎| 4719/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=5.31"
+      "Epoch 0:  32%|▎| 4720/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  32%|▎| 4720/14932 [06:40<14:27, 11.77it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -43917,8 +43888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4720/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=5.31\r",
-      "Epoch 0:  32%|▎| 4720/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  32%|▎| 4721/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  32%|▎| 4721/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=5.19"
      ]
     },
     {
@@ -43926,8 +43897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4721/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  32%|▎| 4721/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  32%|▎| 4722/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=5.19\r",
+      "Epoch 0:  32%|▎| 4722/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -43935,8 +43906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4722/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  32%|▎| 4722/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  32%|▎| 4723/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  32%|▎| 4723/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -43944,8 +43915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4723/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  32%|▎| 4723/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  32%|▎| 4724/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  32%|▎| 4724/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -43953,8 +43924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4724/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  32%|▎| 4724/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  32%|▎| 4725/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  32%|▎| 4725/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -43962,7 +43933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4725/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  32%|▎| 4726/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  32%|▎| 4726/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -43970,7 +43942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4725/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  32%|▎| 4727/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  32%|▎| 4727/14932 [06:41<14:27, 11.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -43978,8 +43951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4726/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  32%|▎| 4726/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  32%|▎| 4728/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  32%|▎| 4728/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -43987,8 +43960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4727/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  32%|▎| 4727/14932 [06:45<14:36, 11.65it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  32%|▎| 4729/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  32%|▎| 4729/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -43996,8 +43969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4728/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  32%|▎| 4728/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  32%|▎| 4730/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  32%|▎| 4730/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -44005,8 +43978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4729/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  32%|▎| 4729/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  32%|▎| 4731/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  32%|▎| 4731/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -44014,8 +43987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4730/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  32%|▎| 4730/14932 [06:45<14:35, 11.65it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  32%|▎| 4732/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  32%|▎| 4732/14932 [06:41<14:26, 11.77it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -44023,8 +43996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4731/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  32%|▎| 4731/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  32%|▎| 4733/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  32%|▎| 4733/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -44032,8 +44005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4732/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  32%|▎| 4732/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  32%|▎| 4734/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  32%|▎| 4734/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -44041,8 +44014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4733/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  32%|▎| 4733/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  32%|▎| 4735/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  32%|▎| 4735/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -44050,8 +44023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4734/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  32%|▎| 4734/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  32%|▎| 4736/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  32%|▎| 4736/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -44059,8 +44032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4735/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  32%|▎| 4735/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  32%|▎| 4737/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  32%|▎| 4737/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -44068,8 +44041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4736/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  32%|▎| 4736/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  32%|▎| 4738/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  32%|▎| 4738/14932 [06:42<14:26, 11.77it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -44077,8 +44050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4737/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  32%|▎| 4737/14932 [06:46<14:35, 11.65it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  32%|▎| 4739/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  32%|▎| 4739/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -44086,8 +44059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4738/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  32%|▎| 4738/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  32%|▎| 4740/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  32%|▎| 4740/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -44095,8 +44068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4739/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  32%|▎| 4739/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  32%|▎| 4741/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  32%|▎| 4741/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -44104,8 +44077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4740/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  32%|▎| 4740/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  32%|▎| 4742/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  32%|▎| 4742/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -44113,8 +44086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4741/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  32%|▎| 4741/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  32%|▎| 4743/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  32%|▎| 4743/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -44122,8 +44095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4742/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  32%|▎| 4742/14932 [06:46<14:34, 11.65it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  32%|▎| 4744/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  32%|▎| 4744/14932 [06:42<14:25, 11.77it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -44131,8 +44104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4743/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  32%|▎| 4743/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  32%|▎| 4745/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  32%|▎| 4745/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -44140,8 +44113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4744/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  32%|▎| 4744/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  32%|▎| 4746/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  32%|▎| 4746/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -44149,8 +44122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4745/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  32%|▎| 4745/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  32%|▎| 4747/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  32%|▎| 4747/14932 [06:43<14:25, 11.77it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -44158,8 +44131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4746/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  32%|▎| 4746/14932 [06:47<14:34, 11.65it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  32%|▎| 4748/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  32%|▎| 4748/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -44167,8 +44140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4747/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  32%|▎| 4747/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  32%|▎| 4749/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  32%|▎| 4749/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -44176,8 +44149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4748/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  32%|▎| 4748/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  32%|▎| 4750/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  32%|▎| 4750/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -44185,8 +44158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4749/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  32%|▎| 4749/14932 [06:47<14:33, 11.65it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  32%|▎| 4751/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  32%|▎| 4751/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -44194,8 +44167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4750/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  32%|▎| 4750/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  32%|▎| 4752/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  32%|▎| 4752/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -44203,8 +44176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4751/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  32%|▎| 4751/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  32%|▎| 4753/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  32%|▎| 4753/14932 [06:43<14:24, 11.77it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -44212,8 +44185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4752/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  32%|▎| 4752/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  32%|▎| 4754/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  32%|▎| 4754/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -44221,8 +44194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4753/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  32%|▎| 4753/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  32%|▎| 4755/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  32%|▎| 4755/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -44230,8 +44203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4754/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  32%|▎| 4754/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  32%|▎| 4756/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  32%|▎| 4756/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -44239,8 +44212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4755/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  32%|▎| 4755/14932 [06:47<14:33, 11.66it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  32%|▎| 4757/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  32%|▎| 4757/14932 [06:43<14:24, 11.78it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -44248,8 +44221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4756/14932 [06:47<14:32, 11.66it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  32%|▎| 4756/14932 [06:47<14:32, 11.66it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  32%|▎| 4758/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  32%|▎| 4758/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -44257,8 +44230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4757/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  32%|▎| 4757/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  32%|▎| 4759/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  32%|▎| 4759/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -44266,8 +44239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4758/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  32%|▎| 4758/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  32%|▎| 4760/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  32%|▎| 4760/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -44275,8 +44248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4759/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  32%|▎| 4759/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  32%|▎| 4761/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  32%|▎| 4761/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -44284,8 +44257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4760/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  32%|▎| 4760/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  32%|▎| 4762/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  32%|▎| 4762/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -44293,8 +44266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4761/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  32%|▎| 4761/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  32%|▎| 4763/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  32%|▎| 4763/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -44302,8 +44275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4762/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  32%|▎| 4762/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.56"
+      "Epoch 0:  32%|▎| 4764/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  32%|▎| 4764/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -44311,8 +44284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4763/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=1.56\r",
-      "Epoch 0:  32%|▎| 4763/14932 [06:48<14:32, 11.66it/s, v_num=o30c, train/loss=5.31"
+      "Epoch 0:  32%|▎| 4765/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  32%|▎| 4765/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -44320,8 +44293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4764/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=5.31\r",
-      "Epoch 0:  32%|▎| 4764/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  32%|▎| 4766/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  32%|▎| 4766/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -44329,8 +44302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4765/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  32%|▎| 4765/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  32%|▎| 4767/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  32%|▎| 4767/14932 [06:44<14:23, 11.78it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -44338,8 +44311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4766/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  32%|▎| 4766/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  32%|▎| 4768/14932 [06:44<14:23, 11.77it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  32%|▎| 4768/14932 [06:44<14:23, 11.77it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -44347,8 +44320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4767/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  32%|▎| 4767/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  32%|▎| 4769/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  32%|▎| 4769/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -44356,8 +44329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4768/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  32%|▎| 4768/14932 [06:48<14:31, 11.66it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  32%|▎| 4770/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  32%|▎| 4770/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -44365,8 +44338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4769/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  32%|▎| 4769/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  32%|▎| 4771/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  32%|▎| 4771/14932 [06:45<14:23, 11.77it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -44374,8 +44347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4770/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  32%|▎| 4770/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  32%|▎| 4772/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  32%|▎| 4772/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -44383,8 +44356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4771/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  32%|▎| 4771/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  32%|▎| 4773/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  32%|▎| 4773/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -44392,8 +44365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4772/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  32%|▎| 4772/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  32%|▎| 4774/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  32%|▎| 4774/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -44401,8 +44374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4773/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  32%|▎| 4773/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  32%|▎| 4775/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  32%|▎| 4775/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -44410,8 +44383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4774/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  32%|▎| 4774/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  32%|▎| 4776/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  32%|▎| 4776/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -44419,8 +44392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4775/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  32%|▎| 4775/14932 [06:49<14:31, 11.66it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  32%|▎| 4777/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  32%|▎| 4777/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -44428,8 +44401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4776/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  32%|▎| 4776/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  32%|▎| 4778/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  32%|▎| 4778/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -44437,8 +44410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4777/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  32%|▎| 4777/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  32%|▎| 4779/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  32%|▎| 4779/14932 [06:45<14:22, 11.77it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -44446,8 +44419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4778/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  32%|▎| 4778/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  32%|▎| 4780/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  32%|▎| 4780/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -44455,8 +44428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4779/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  32%|▎| 4779/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  32%|▎| 4781/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  32%|▎| 4781/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -44464,8 +44437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4780/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  32%|▎| 4780/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  32%|▎| 4782/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  32%|▎| 4782/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -44473,8 +44446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4781/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  32%|▎| 4781/14932 [06:49<14:30, 11.66it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  32%|▎| 4783/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  32%|▎| 4783/14932 [06:46<14:22, 11.77it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -44482,8 +44455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4782/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  32%|▎| 4782/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  32%|▎| 4784/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  32%|▎| 4784/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -44491,8 +44464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4783/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  32%|▎| 4783/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  32%|▎| 4785/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  32%|▎| 4785/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -44500,8 +44473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4784/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  32%|▎| 4784/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  32%|▎| 4786/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  32%|▎| 4786/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -44509,8 +44482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4785/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  32%|▎| 4785/14932 [06:50<14:30, 11.66it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  32%|▎| 4787/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  32%|▎| 4787/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -44518,8 +44491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4786/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  32%|▎| 4786/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  32%|▎| 4788/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  32%|▎| 4788/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -44527,8 +44500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4787/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  32%|▎| 4787/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  32%|▎| 4789/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  32%|▎| 4789/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -44536,8 +44509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4788/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  32%|▎| 4788/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  32%|▎| 4790/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  32%|▎| 4790/14932 [06:46<14:21, 11.77it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -44545,8 +44518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4789/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  32%|▎| 4789/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  32%|▎| 4791/14932 [06:46<14:21, 11.78it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  32%|▎| 4791/14932 [06:46<14:21, 11.78it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -44554,8 +44527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4790/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  32%|▎| 4790/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  32%|▎| 4792/14932 [06:46<14:21, 11.78it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  32%|▎| 4792/14932 [06:46<14:21, 11.78it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -44563,8 +44536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4791/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  32%|▎| 4791/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  32%|▎| 4793/14932 [06:47<14:21, 11.78it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  32%|▎| 4793/14932 [06:47<14:21, 11.78it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -44572,8 +44545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4792/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  32%|▎| 4792/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  32%|▎| 4794/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  32%|▎| 4794/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -44581,8 +44554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4793/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  32%|▎| 4793/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  32%|▎| 4795/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  32%|▎| 4795/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -44590,8 +44563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4794/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  32%|▎| 4794/14932 [06:50<14:29, 11.66it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  32%|▎| 4796/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  32%|▎| 4796/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -44599,8 +44572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4795/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  32%|▎| 4795/14932 [06:51<14:29, 11.67it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  32%|▎| 4797/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  32%|▎| 4797/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -44608,8 +44581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4796/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  32%|▎| 4796/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  32%|▎| 4798/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  32%|▎| 4798/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -44617,8 +44590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4797/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  32%|▎| 4797/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  32%|▎| 4799/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  32%|▎| 4799/14932 [06:47<14:20, 11.78it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -44626,8 +44599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4798/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  32%|▎| 4798/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  32%|▎| 4800/14932 [06:47<14:20, 11.77it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  32%|▎| 4800/14932 [06:47<14:20, 11.77it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -44635,8 +44608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4799/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  32%|▎| 4799/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  32%|▎| 4801/14932 [06:47<14:20, 11.77it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  32%|▎| 4801/14932 [06:47<14:20, 11.77it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -44644,8 +44617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4800/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  32%|▎| 4800/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  32%|▎| 4802/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  32%|▎| 4802/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -44653,8 +44626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4801/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  32%|▎| 4801/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  32%|▎| 4803/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  32%|▎| 4803/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -44662,8 +44635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4802/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  32%|▎| 4802/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  32%|▎| 4804/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  32%|▎| 4804/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -44671,8 +44644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4803/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  32%|▎| 4803/14932 [06:51<14:28, 11.66it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  32%|▎| 4805/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  32%|▎| 4805/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -44680,8 +44653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4804/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  32%|▎| 4804/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  32%|▎| 4806/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  32%|▎| 4806/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -44689,8 +44662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4805/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  32%|▎| 4805/14932 [06:51<14:28, 11.67it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  32%|▎| 4807/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  32%|▎| 4807/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -44698,8 +44671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4806/14932 [06:51<14:27, 11.67it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  32%|▎| 4806/14932 [06:51<14:27, 11.67it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  32%|▎| 4808/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  32%|▎| 4808/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -44707,8 +44680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4807/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  32%|▎| 4807/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  32%|▎| 4809/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  32%|▎| 4809/14932 [06:48<14:20, 11.77it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -44716,8 +44689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4808/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  32%|▎| 4808/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  32%|▎| 4810/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  32%|▎| 4810/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -44725,8 +44698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4809/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  32%|▎| 4809/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  32%|▎| 4811/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  32%|▎| 4811/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -44734,8 +44707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4810/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  32%|▎| 4810/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  32%|▎| 4812/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  32%|▎| 4812/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -44743,8 +44716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4811/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  32%|▎| 4811/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  32%|▎| 4813/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  32%|▎| 4813/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -44752,8 +44725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4812/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  32%|▎| 4812/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  32%|▎| 4814/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  32%|▎| 4814/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -44761,8 +44734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4813/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  32%|▎| 4813/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  32%|▎| 4815/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  32%|▎| 4815/14932 [06:48<14:19, 11.77it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -44770,8 +44743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4814/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  32%|▎| 4814/14932 [06:52<14:27, 11.67it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  32%|▎| 4816/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  32%|▎| 4816/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -44779,8 +44752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4815/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  32%|▎| 4815/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  32%|▎| 4817/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  32%|▎| 4817/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -44788,8 +44761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4816/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  32%|▎| 4816/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  32%|▎| 4818/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  32%|▎| 4818/14932 [06:49<14:19, 11.77it/s, v_num=ui8w, train/loss=0.85"
      ]
     },
     {
@@ -44797,8 +44770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4817/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  32%|▎| 4817/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  32%|▎| 4819/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=0.85\r",
+      "Epoch 0:  32%|▎| 4819/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -44806,8 +44779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4818/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  32%|▎| 4818/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  32%|▎| 4820/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  32%|▎| 4820/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -44815,8 +44788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4819/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  32%|▎| 4819/14932 [06:52<14:26, 11.67it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  32%|▎| 4821/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  32%|▎| 4821/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -44824,8 +44797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4820/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  32%|▎| 4820/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  32%|▎| 4822/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  32%|▎| 4822/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -44833,8 +44806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4821/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  32%|▎| 4821/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  32%|▎| 4823/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  32%|▎| 4823/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -44842,8 +44815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4822/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  32%|▎| 4822/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  32%|▎| 4824/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  32%|▎| 4824/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -44851,8 +44824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4823/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  32%|▎| 4823/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  32%|▎| 4825/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  32%|▎| 4825/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -44860,8 +44833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4824/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  32%|▎| 4824/14932 [06:53<14:26, 11.67it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  32%|▎| 4826/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  32%|▎| 4826/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -44869,8 +44842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4825/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  32%|▎| 4825/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  32%|▎| 4827/14932 [06:49<14:18, 11.78it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  32%|▎| 4827/14932 [06:49<14:18, 11.77it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -44878,8 +44851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4826/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  32%|▎| 4826/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=0.92"
+      "Epoch 0:  32%|▎| 4828/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  32%|▎| 4828/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -44887,8 +44860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4827/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=0.92\r",
-      "Epoch 0:  32%|▎| 4827/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  32%|▎| 4829/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  32%|▎| 4829/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -44896,8 +44869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4828/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  32%|▎| 4828/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  32%|▎| 4830/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  32%|▎| 4830/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -44905,8 +44878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4829/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  32%|▎| 4829/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  32%|▎| 4831/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  32%|▎| 4831/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -44914,8 +44887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4830/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  32%|▎| 4830/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  32%|▎| 4832/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  32%|▎| 4832/14932 [06:50<14:18, 11.77it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -44923,8 +44896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4831/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  32%|▎| 4831/14932 [06:53<14:25, 11.67it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  32%|▎| 4833/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  32%|▎| 4833/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -44932,8 +44905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4832/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  32%|▎| 4832/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  32%|▎| 4834/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  32%|▎| 4834/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -44941,8 +44914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4833/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  32%|▎| 4833/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  32%|▎| 4835/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  32%|▎| 4835/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -44950,8 +44923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4834/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  32%|▎| 4834/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  32%|▎| 4836/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  32%|▎| 4836/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -44959,8 +44932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4835/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  32%|▎| 4835/14932 [06:54<14:25, 11.67it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  32%|▎| 4837/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  32%|▎| 4837/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -44968,8 +44941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4836/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  32%|▎| 4836/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  32%|▎| 4838/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  32%|▎| 4838/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -44977,8 +44950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4837/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  32%|▎| 4837/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  32%|▎| 4839/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  32%|▎| 4839/14932 [06:50<14:17, 11.77it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -44986,8 +44959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4838/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  32%|▎| 4838/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  32%|▎| 4840/14932 [06:51<14:17, 11.77it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  32%|▎| 4840/14932 [06:51<14:17, 11.77it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -44995,8 +44968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4839/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  32%|▎| 4839/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  32%|▎| 4841/14932 [06:51<14:17, 11.77it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  32%|▎| 4841/14932 [06:51<14:17, 11.77it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -45004,8 +44977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4840/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  32%|▎| 4840/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  32%|▎| 4842/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  32%|▎| 4842/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -45013,8 +44986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4841/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  32%|▎| 4841/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  32%|▎| 4843/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  32%|▎| 4843/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -45022,8 +44995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4842/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  32%|▎| 4842/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  32%|▎| 4844/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=1.61\r",
+      "Epoch 0:  32%|▎| 4844/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -45031,8 +45004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4843/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  32%|▎| 4843/14932 [06:54<14:24, 11.67it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  32%|▎| 4845/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  32%|▎| 4845/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -45040,8 +45013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4844/14932 [06:54<14:24, 11.68it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  32%|▎| 4844/14932 [06:54<14:24, 11.68it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  32%|▎| 4846/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  32%|▎| 4846/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -45049,8 +45022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4845/14932 [06:54<14:23, 11.68it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  32%|▎| 4845/14932 [06:54<14:23, 11.68it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  32%|▎| 4847/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  32%|▎| 4847/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -45058,8 +45031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4846/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  32%|▎| 4846/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  32%|▎| 4848/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  32%|▎| 4848/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -45067,8 +45040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4847/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  32%|▎| 4847/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  32%|▎| 4849/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  32%|▎| 4849/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -45076,8 +45049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4848/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  32%|▎| 4848/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  32%|▎| 4850/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  32%|▎| 4850/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -45085,8 +45058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4849/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  32%|▎| 4849/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  32%|▎| 4851/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  32%|▎| 4851/14932 [06:51<14:16, 11.78it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -45094,8 +45067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4850/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  32%|▎| 4850/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  32%|▎| 4852/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  32%|▎| 4852/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -45103,8 +45076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4851/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  32%|▎| 4851/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  33%|▎| 4853/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  33%|▎| 4853/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -45112,8 +45085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  32%|▎| 4852/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  32%|▎| 4852/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  33%|▎| 4854/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  33%|▎| 4854/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -45121,8 +45094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4853/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  33%|▎| 4853/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  33%|▎| 4855/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  33%|▎| 4855/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -45130,8 +45103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4854/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  33%|▎| 4854/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  33%|▎| 4856/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  33%|▎| 4856/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -45139,8 +45112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4855/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  33%|▎| 4855/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  33%|▎| 4857/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  33%|▎| 4857/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -45148,8 +45121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4856/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  33%|▎| 4856/14932 [06:55<14:23, 11.68it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  33%|▎| 4858/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  33%|▎| 4858/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -45157,8 +45130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4857/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  33%|▎| 4857/14932 [06:55<14:22, 11.68it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  33%|▎| 4859/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  33%|▎| 4859/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -45166,8 +45139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4858/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  33%|▎| 4858/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  33%|▎| 4860/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  33%|▎| 4860/14932 [06:52<14:15, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -45175,8 +45148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4859/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  33%|▎| 4859/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  33%|▎| 4861/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4861/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -45184,8 +45157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4860/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  33%|▎| 4860/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  33%|▎| 4862/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  33%|▎| 4862/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -45193,8 +45166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4861/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  33%|▎| 4861/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  33%|▎| 4863/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  33%|▎| 4863/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -45202,8 +45175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4862/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  33%|▎| 4862/14932 [06:56<14:22, 11.68it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  33%|▎| 4864/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  33%|▎| 4864/14932 [06:52<14:14, 11.78it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -45211,8 +45184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4863/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  33%|▎| 4863/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  33%|▎| 4865/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  33%|▎| 4865/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -45220,8 +45193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4864/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  33%|▎| 4864/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  33%|▎| 4866/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  33%|▎| 4866/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -45229,8 +45202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4865/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  33%|▎| 4865/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  33%|▎| 4867/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  33%|▎| 4867/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -45238,8 +45211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4866/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  33%|▎| 4866/14932 [06:56<14:22, 11.67it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  33%|▎| 4868/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  33%|▎| 4868/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -45247,8 +45220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4867/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  33%|▎| 4867/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  33%|▎| 4869/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  33%|▎| 4869/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -45256,8 +45229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4868/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  33%|▎| 4868/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  33%|▎| 4870/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  33%|▎| 4870/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -45265,8 +45238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4869/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  33%|▎| 4869/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  33%|▎| 4871/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4871/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -45274,8 +45247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4870/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  33%|▎| 4870/14932 [06:57<14:22, 11.67it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  33%|▎| 4872/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  33%|▎| 4872/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -45283,8 +45256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4871/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  33%|▎| 4871/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  33%|▎| 4873/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  33%|▎| 4873/14932 [06:53<14:14, 11.78it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -45292,8 +45265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4872/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  33%|▎| 4872/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  33%|▎| 4874/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  33%|▎| 4874/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -45301,8 +45274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4873/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  33%|▎| 4873/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  33%|▎| 4875/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  33%|▎| 4875/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -45310,8 +45283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4874/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  33%|▎| 4874/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  33%|▎| 4876/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  33%|▎| 4876/14932 [06:53<14:13, 11.78it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -45319,8 +45292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4875/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  33%|▎| 4875/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  33%|▎| 4877/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  33%|▎| 4877/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -45328,8 +45301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4876/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  33%|▎| 4876/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  33%|▎| 4878/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  33%|▎| 4878/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -45337,8 +45310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4877/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  33%|▎| 4877/14932 [06:57<14:21, 11.67it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  33%|▎| 4879/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  33%|▎| 4879/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -45346,8 +45319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4878/14932 [06:57<14:21, 11.68it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  33%|▎| 4878/14932 [06:57<14:21, 11.68it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  33%|▎| 4880/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  33%|▎| 4880/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -45355,8 +45328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4879/14932 [06:57<14:21, 11.68it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  33%|▎| 4879/14932 [06:57<14:21, 11.68it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  33%|▎| 4881/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  33%|▎| 4881/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -45364,8 +45337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4880/14932 [06:57<14:20, 11.68it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  33%|▎| 4880/14932 [06:57<14:20, 11.68it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  33%|▎| 4882/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  33%|▎| 4882/14932 [06:54<14:13, 11.78it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -45373,8 +45346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4881/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  33%|▎| 4881/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  33%|▎| 4883/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  33%|▎| 4883/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -45382,8 +45355,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4882/14932 [06:58<14:21, 11.67it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  33%|▎| 4882/14932 [06:58<14:21, 11.67it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  33%|▎| 4884/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -45391,8 +45363,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4883/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  33%|▎| 4883/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  33%|▎| 4884/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -45400,8 +45371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4884/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  33%|▎| 4884/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  33%|▎| 4885/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  33%|▎| 4885/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -45409,8 +45380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4885/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  33%|▎| 4885/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  33%|▎| 4886/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4886/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -45418,8 +45389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4886/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  33%|▎| 4886/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  33%|▎| 4887/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  33%|▎| 4887/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -45427,8 +45398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4887/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  33%|▎| 4887/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  33%|▎| 4888/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  33%|▎| 4888/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -45436,8 +45407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4888/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  33%|▎| 4888/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  33%|▎| 4889/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  33%|▎| 4889/14932 [06:54<14:12, 11.78it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -45445,8 +45416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4889/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  33%|▎| 4889/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  33%|▎| 4890/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  33%|▎| 4890/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -45454,8 +45425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4890/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  33%|▎| 4890/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  33%|▎| 4891/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  33%|▎| 4891/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -45463,8 +45434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4891/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  33%|▎| 4891/14932 [06:58<14:20, 11.67it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  33%|▎| 4892/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  33%|▎| 4892/14932 [06:55<14:12, 11.78it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -45472,8 +45443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4892/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  33%|▎| 4892/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  33%|▎| 4893/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  33%|▎| 4893/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -45481,8 +45452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4893/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  33%|▎| 4893/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  33%|▎| 4894/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  33%|▎| 4894/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -45490,8 +45461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4894/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  33%|▎| 4894/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  33%|▎| 4895/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  33%|▎| 4895/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -45499,8 +45470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4895/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  33%|▎| 4895/14932 [06:59<14:19, 11.68it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  33%|▎| 4896/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  33%|▎| 4896/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -45508,8 +45479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4896/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  33%|▎| 4896/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  33%|▎| 4897/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  33%|▎| 4897/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -45517,8 +45488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4897/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  33%|▎| 4897/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  33%|▎| 4898/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  33%|▎| 4898/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=5.34"
      ]
     },
     {
@@ -45526,8 +45497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4898/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  33%|▎| 4898/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  33%|▎| 4899/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=5.34\r",
+      "Epoch 0:  33%|▎| 4899/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -45535,8 +45506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4899/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  33%|▎| 4899/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  33%|▎| 4900/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  33%|▎| 4900/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -45544,8 +45515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4900/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  33%|▎| 4900/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  33%|▎| 4901/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  33%|▎| 4901/14932 [06:55<14:11, 11.78it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -45553,8 +45524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4901/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  33%|▎| 4901/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  33%|▎| 4902/14932 [06:56<14:11, 11.78it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  33%|▎| 4902/14932 [06:56<14:11, 11.78it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -45562,8 +45533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4902/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  33%|▎| 4902/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  33%|▎| 4903/14932 [06:56<14:11, 11.78it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  33%|▎| 4903/14932 [06:56<14:11, 11.78it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -45571,8 +45542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4903/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  33%|▎| 4903/14932 [06:59<14:19, 11.67it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  33%|▎| 4904/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  33%|▎| 4904/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -45580,8 +45551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4904/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  33%|▎| 4904/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  33%|▎| 4905/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  33%|▎| 4905/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -45589,8 +45560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4905/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  33%|▎| 4905/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  33%|▎| 4906/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  33%|▎| 4906/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -45598,8 +45569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4906/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  33%|▎| 4906/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  33%|▎| 4907/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  33%|▎| 4907/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -45607,8 +45578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4907/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  33%|▎| 4907/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  33%|▎| 4908/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  33%|▎| 4908/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -45616,8 +45587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4908/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  33%|▎| 4908/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  33%|▎| 4909/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  33%|▎| 4909/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -45625,8 +45596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4909/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  33%|▎| 4909/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  33%|▎| 4910/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  33%|▎| 4910/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -45634,8 +45605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4910/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  33%|▎| 4910/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  33%|▎| 4911/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  33%|▎| 4911/14932 [06:56<14:10, 11.79it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -45643,8 +45614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4911/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  33%|▎| 4911/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  33%|▎| 4912/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  33%|▎| 4912/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -45652,8 +45623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4912/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  33%|▎| 4912/14932 [07:00<14:18, 11.68it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  33%|▎| 4913/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  33%|▎| 4913/14932 [06:56<14:10, 11.78it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -45661,8 +45632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4913/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  33%|▎| 4913/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  33%|▎| 4914/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  33%|▎| 4914/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -45670,8 +45641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4914/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  33%|▎| 4914/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  33%|▎| 4915/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  33%|▎| 4915/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -45679,8 +45650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4915/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  33%|▎| 4915/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  33%|▎| 4916/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  33%|▎| 4916/14932 [06:57<14:10, 11.78it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -45688,8 +45659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4916/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  33%|▎| 4916/14932 [07:00<14:17, 11.68it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  33%|▎| 4917/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  33%|▎| 4917/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -45697,8 +45668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4917/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  33%|▎| 4917/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  33%|▎| 4918/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  33%|▎| 4918/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -45706,8 +45677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4918/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  33%|▎| 4918/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  33%|▎| 4919/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  33%|▎| 4919/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -45715,8 +45686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4919/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  33%|▎| 4919/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  33%|▎| 4920/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  33%|▎| 4920/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -45724,7 +45695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4920/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  33%|▎| 4921/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:  33%|▎| 4921/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -45732,7 +45704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4920/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  33%|▎| 4922/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  33%|▎| 4922/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -45740,8 +45713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4921/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  33%|▎| 4921/14932 [07:01<14:17, 11.68it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  33%|▎| 4923/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  33%|▎| 4923/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -45749,8 +45722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4922/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  33%|▎| 4922/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  33%|▎| 4924/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  33%|▎| 4924/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -45758,8 +45731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4923/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  33%|▎| 4923/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  33%|▎| 4925/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  33%|▎| 4925/14932 [06:57<14:09, 11.78it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -45767,8 +45740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4924/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  33%|▎| 4924/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  33%|▎| 4926/14932 [06:58<14:09, 11.78it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  33%|▎| 4926/14932 [06:58<14:09, 11.78it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -45776,8 +45749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4925/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  33%|▎| 4925/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  33%|▎| 4927/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  33%|▎| 4927/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -45785,8 +45758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4926/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  33%|▎| 4926/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  33%|▎| 4928/14932 [06:58<14:09, 11.78it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  33%|▎| 4928/14932 [06:58<14:09, 11.78it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -45794,8 +45767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4927/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  33%|▎| 4927/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  33%|▎| 4929/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  33%|▎| 4929/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -45803,8 +45776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4928/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  33%|▎| 4928/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  33%|▎| 4930/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  33%|▎| 4930/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -45812,8 +45785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4929/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  33%|▎| 4929/14932 [07:01<14:16, 11.68it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  33%|▎| 4931/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  33%|▎| 4931/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -45821,8 +45794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4930/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  33%|▎| 4930/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  33%|▎| 4932/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  33%|▎| 4932/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -45830,8 +45803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4931/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  33%|▎| 4931/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  33%|▎| 4933/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  33%|▎| 4933/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -45839,8 +45812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4932/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  33%|▎| 4932/14932 [07:02<14:16, 11.68it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  33%|▎| 4934/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4934/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -45848,7 +45821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4933/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  33%|▎| 4935/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  33%|▎| 4935/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -45856,7 +45830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4933/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  33%|▎| 4936/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  33%|▎| 4936/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -45864,8 +45839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4934/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  33%|▎| 4934/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  33%|▎| 4937/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  33%|▎| 4937/14932 [06:58<14:08, 11.78it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -45873,8 +45848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4935/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  33%|▎| 4935/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  33%|▎| 4938/14932 [06:59<14:08, 11.79it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  33%|▎| 4938/14932 [06:59<14:08, 11.79it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -45882,8 +45857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4936/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  33%|▎| 4936/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  33%|▎| 4939/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  33%|▎| 4939/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -45891,8 +45866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4937/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  33%|▎| 4937/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  33%|▎| 4940/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  33%|▎| 4940/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -45900,7 +45875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4938/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  33%|▎| 4941/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  33%|▎| 4941/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -45908,7 +45884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4938/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  33%|▎| 4942/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  33%|▎| 4942/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -45916,8 +45893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4939/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  33%|▎| 4939/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  33%|▎| 4943/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  33%|▎| 4943/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -45925,8 +45902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4940/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  33%|▎| 4940/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  33%|▎| 4944/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  33%|▎| 4944/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -45934,8 +45911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4941/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  33%|▎| 4941/14932 [07:02<14:15, 11.68it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  33%|▎| 4945/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  33%|▎| 4945/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -45943,8 +45920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4942/14932 [07:02<14:14, 11.69it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  33%|▎| 4942/14932 [07:02<14:14, 11.69it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  33%|▎| 4946/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  33%|▎| 4946/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -45952,8 +45929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4943/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  33%|▎| 4943/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  33%|▎| 4947/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  33%|▎| 4947/14932 [06:59<14:07, 11.78it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -45961,8 +45938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4944/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  33%|▎| 4944/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  33%|▎| 4948/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  33%|▎| 4948/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -45970,8 +45947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4945/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  33%|▎| 4945/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  33%|▎| 4949/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  33%|▎| 4949/14932 [06:59<14:07, 11.79it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -45979,8 +45956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4946/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  33%|▎| 4946/14932 [07:03<14:14, 11.68it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  33%|▎| 4950/14932 [06:59<14:06, 11.79it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  33%|▎| 4950/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -45988,8 +45965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4947/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  33%|▎| 4947/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  33%|▎| 4951/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  33%|▎| 4951/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -45997,8 +45974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4948/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  33%|▎| 4948/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  33%|▎| 4952/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  33%|▎| 4952/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -46006,8 +45983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4949/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  33%|▎| 4949/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  33%|▎| 4953/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  33%|▎| 4953/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -46015,8 +45992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4950/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  33%|▎| 4950/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  33%|▎| 4954/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  33%|▎| 4954/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -46024,8 +46001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4951/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  33%|▎| 4951/14932 [07:03<14:14, 11.69it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  33%|▎| 4955/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  33%|▎| 4955/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -46033,8 +46010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4952/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  33%|▎| 4952/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  33%|▎| 4956/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  33%|▎| 4956/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -46042,8 +46019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4953/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  33%|▎| 4953/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  33%|▎| 4957/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  33%|▎| 4957/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -46051,8 +46028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4954/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  33%|▎| 4954/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  33%|▎| 4958/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  33%|▎| 4958/14932 [07:00<14:06, 11.79it/s, v_num=ui8w, train/loss=1.26"
      ]
     },
     {
@@ -46060,8 +46037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4955/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  33%|▎| 4955/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  33%|▎| 4959/14932 [07:00<14:05, 11.79it/s, v_num=ui8w, train/loss=1.26\r",
+      "Epoch 0:  33%|▎| 4959/14932 [07:00<14:05, 11.79it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -46069,8 +46046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4956/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  33%|▎| 4956/14932 [07:03<14:13, 11.69it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  33%|▎| 4960/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  33%|▎| 4960/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -46078,8 +46055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4957/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  33%|▎| 4957/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  33%|▎| 4961/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  33%|▎| 4961/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -46087,8 +46064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4958/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  33%|▎| 4958/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  33%|▎| 4962/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  33%|▎| 4962/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -46096,8 +46073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4959/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  33%|▎| 4959/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  33%|▎| 4963/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  33%|▎| 4963/14932 [07:01<14:06, 11.78it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -46105,8 +46082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4960/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  33%|▎| 4960/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  33%|▎| 4964/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  33%|▎| 4964/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -46114,8 +46091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4961/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  33%|▎| 4961/14932 [07:04<14:13, 11.69it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  33%|▎| 4965/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  33%|▎| 4965/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -46123,8 +46100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4962/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  33%|▎| 4962/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  33%|▎| 4966/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  33%|▎| 4966/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -46132,8 +46109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4963/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  33%|▎| 4963/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  33%|▎| 4967/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  33%|▎| 4967/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -46141,8 +46118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4964/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  33%|▎| 4964/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  33%|▎| 4968/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  33%|▎| 4968/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -46150,8 +46127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4965/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  33%|▎| 4965/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  33%|▎| 4969/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4969/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -46159,8 +46136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4966/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  33%|▎| 4966/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  33%|▎| 4970/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  33%|▎| 4970/14932 [07:01<14:05, 11.78it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -46168,8 +46145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4967/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  33%|▎| 4967/14932 [07:04<14:12, 11.69it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  33%|▎| 4971/14932 [07:01<14:05, 11.79it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  33%|▎| 4971/14932 [07:01<14:05, 11.79it/s, v_num=ui8w, train/loss=1.10"
      ]
     },
     {
@@ -46177,8 +46154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4968/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  33%|▎| 4968/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  33%|▎| 4972/14932 [07:01<14:05, 11.79it/s, v_num=ui8w, train/loss=1.10\r",
+      "Epoch 0:  33%|▎| 4972/14932 [07:01<14:05, 11.79it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -46186,8 +46163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4969/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  33%|▎| 4969/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  33%|▎| 4973/14932 [07:01<14:04, 11.79it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  33%|▎| 4973/14932 [07:01<14:04, 11.79it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -46195,8 +46172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4970/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  33%|▎| 4970/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  33%|▎| 4974/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  33%|▎| 4974/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -46204,8 +46181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4971/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  33%|▎| 4971/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  33%|▎| 4975/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  33%|▎| 4975/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -46213,8 +46190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4972/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  33%|▎| 4972/14932 [07:05<14:12, 11.69it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  33%|▎| 4976/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  33%|▎| 4976/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -46222,8 +46199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4973/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  33%|▎| 4973/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  33%|▎| 4977/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  33%|▎| 4977/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -46231,8 +46208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4974/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  33%|▎| 4974/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  33%|▎| 4978/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  33%|▎| 4978/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -46240,8 +46217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4975/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  33%|▎| 4975/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  33%|▎| 4979/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  33%|▎| 4979/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -46249,8 +46226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4976/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  33%|▎| 4976/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  33%|▎| 4980/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  33%|▎| 4980/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -46258,8 +46235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4977/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  33%|▎| 4977/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=0.75"
+      "Epoch 0:  33%|▎| 4981/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  33%|▎| 4981/14932 [07:02<14:04, 11.79it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -46267,8 +46244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4978/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=0.75\r",
-      "Epoch 0:  33%|▎| 4978/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  33%|▎| 4982/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  33%|▎| 4982/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -46276,8 +46253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4979/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  33%|▎| 4979/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  33%|▎| 4983/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  33%|▎| 4983/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -46285,8 +46262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4980/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  33%|▎| 4980/14932 [07:05<14:11, 11.69it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  33%|▎| 4984/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  33%|▎| 4984/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -46294,8 +46271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4981/14932 [07:06<14:11, 11.69it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  33%|▎| 4981/14932 [07:06<14:11, 11.69it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  33%|▎| 4985/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  33%|▎| 4985/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -46303,8 +46280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4982/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  33%|▎| 4982/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  33%|▎| 4986/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  33%|▎| 4986/14932 [07:02<14:03, 11.79it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -46312,8 +46289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4983/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  33%|▎| 4983/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  33%|▎| 4987/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  33%|▎| 4987/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -46321,8 +46298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4984/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  33%|▎| 4984/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  33%|▎| 4988/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  33%|▎| 4988/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -46330,8 +46307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4985/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  33%|▎| 4985/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  33%|▎| 4989/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  33%|▎| 4989/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -46339,8 +46316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4986/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  33%|▎| 4986/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  33%|▎| 4990/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  33%|▎| 4990/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -46348,8 +46325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4987/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  33%|▎| 4987/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  33%|▎| 4991/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  33%|▎| 4991/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -46357,8 +46334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4988/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  33%|▎| 4988/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  33%|▎| 4992/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  33%|▎| 4992/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -46366,8 +46343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4989/14932 [07:06<14:10, 11.70it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  33%|▎| 4989/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  33%|▎| 4993/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  33%|▎| 4993/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -46375,8 +46352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4990/14932 [07:06<14:10, 11.70it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  33%|▎| 4990/14932 [07:06<14:10, 11.70it/s, v_num=o30c, train/loss=0.87"
+      "Epoch 0:  33%|▎| 4994/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  33%|▎| 4994/14932 [07:03<14:03, 11.79it/s, v_num=ui8w, train/loss=1.40"
      ]
     },
     {
@@ -46384,8 +46361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4991/14932 [07:06<14:09, 11.70it/s, v_num=o30c, train/loss=0.87\r",
-      "Epoch 0:  33%|▎| 4991/14932 [07:06<14:09, 11.70it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  33%|▎| 4995/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=1.40\r",
+      "Epoch 0:  33%|▎| 4995/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -46393,8 +46370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4992/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  33%|▎| 4992/14932 [07:06<14:10, 11.69it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  33%|▎| 4996/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  33%|▎| 4996/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -46402,8 +46379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4993/14932 [07:06<14:09, 11.69it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  33%|▎| 4993/14932 [07:06<14:09, 11.69it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  33%|▎| 4997/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  33%|▎| 4997/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -46411,8 +46388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4994/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  33%|▎| 4994/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  33%|▎| 4998/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  33%|▎| 4998/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -46420,8 +46397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4995/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  33%|▎| 4995/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  33%|▎| 4999/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  33%|▎| 4999/14932 [07:03<14:02, 11.79it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -46429,8 +46406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4996/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  33%|▎| 4996/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  33%|▎| 5000/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  33%|▎| 5000/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=1.02"
      ]
     },
     {
@@ -46438,8 +46415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4997/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  33%|▎| 4997/14932 [07:07<14:10, 11.69it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  33%|▎| 5001/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=1.02\r",
+      "Epoch 0:  33%|▎| 5001/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -46447,8 +46424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4998/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  33%|▎| 4998/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  33%|▎| 5002/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  33%|▎| 5002/14932 [07:04<14:02, 11.79it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -46456,8 +46433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 4999/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  33%|▎| 4999/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  34%|▎| 5003/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  34%|▎| 5003/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -46465,8 +46442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 5000/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  33%|▎| 5000/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  34%|▎| 5004/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  34%|▎| 5004/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -46474,8 +46451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 5001/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  33%|▎| 5001/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  34%|▎| 5005/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  34%|▎| 5005/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -46483,8 +46460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  33%|▎| 5002/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  33%|▎| 5002/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  34%|▎| 5006/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  34%|▎| 5006/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -46492,8 +46469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5003/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  34%|▎| 5003/14932 [07:07<14:09, 11.69it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  34%|▎| 5007/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  34%|▎| 5007/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -46501,8 +46478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5004/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  34%|▎| 5004/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  34%|▎| 5008/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  34%|▎| 5008/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -46510,8 +46487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5005/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  34%|▎| 5005/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  34%|▎| 5009/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  34%|▎| 5009/14932 [07:04<14:01, 11.79it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -46519,8 +46496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5006/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  34%|▎| 5006/14932 [07:08<14:09, 11.69it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  34%|▎| 5010/14932 [07:04<14:01, 11.80it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  34%|▎| 5010/14932 [07:04<14:01, 11.80it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -46528,8 +46505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5007/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  34%|▎| 5007/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  34%|▎| 5011/14932 [07:04<14:01, 11.80it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  34%|▎| 5011/14932 [07:04<14:01, 11.80it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -46537,8 +46514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5008/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  34%|▎| 5008/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  34%|▎| 5012/14932 [07:04<14:00, 11.80it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  34%|▎| 5012/14932 [07:04<14:00, 11.80it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -46546,8 +46523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5009/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  34%|▎| 5009/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  34%|▎| 5013/14932 [07:04<14:00, 11.80it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  34%|▎| 5013/14932 [07:04<14:00, 11.80it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -46555,8 +46532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5010/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  34%|▎| 5010/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  34%|▎| 5014/14932 [07:05<14:01, 11.79it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  34%|▎| 5014/14932 [07:05<14:01, 11.79it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -46564,8 +46541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5011/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  34%|▎| 5011/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  34%|▎| 5015/14932 [07:05<14:01, 11.79it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  34%|▎| 5015/14932 [07:05<14:01, 11.79it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -46573,8 +46550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5012/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  34%|▎| 5012/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  34%|▎| 5016/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  34%|▎| 5016/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -46582,8 +46559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5013/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  34%|▎| 5013/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  34%|▎| 5017/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  34%|▎| 5017/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -46591,8 +46568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5014/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  34%|▎| 5014/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  34%|▎| 5018/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  34%|▎| 5018/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -46600,8 +46577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5015/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  34%|▎| 5015/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  34%|▎| 5019/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  34%|▎| 5019/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -46609,8 +46586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5016/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  34%|▎| 5016/14932 [07:08<14:08, 11.69it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  34%|▎| 5020/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  34%|▎| 5020/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -46618,8 +46595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5017/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  34%|▎| 5017/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  34%|▎| 5021/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  34%|▎| 5021/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -46627,8 +46604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5018/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  34%|▎| 5018/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  34%|▎| 5022/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  34%|▎| 5022/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -46636,8 +46613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5019/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  34%|▎| 5019/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  34%|▎| 5023/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  34%|▎| 5023/14932 [07:05<14:00, 11.79it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -46645,8 +46622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5020/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  34%|▎| 5020/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  34%|▎| 5024/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  34%|▎| 5024/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -46654,8 +46631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5021/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  34%|▎| 5021/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  34%|▎| 5025/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  34%|▎| 5025/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -46663,8 +46640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5022/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  34%|▎| 5022/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  34%|▎| 5026/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  34%|▎| 5026/14932 [07:06<14:00, 11.79it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -46672,8 +46649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5023/14932 [07:09<14:07, 11.70it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  34%|▎| 5023/14932 [07:09<14:07, 11.70it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  34%|▎| 5027/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  34%|▎| 5027/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -46681,8 +46658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5024/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  34%|▎| 5024/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  34%|▎| 5028/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  34%|▎| 5028/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -46690,8 +46667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5025/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  34%|▎| 5025/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  34%|▎| 5029/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  34%|▎| 5029/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -46699,8 +46676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5026/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  34%|▎| 5026/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  34%|▎| 5030/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  34%|▎| 5030/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -46708,8 +46685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5027/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  34%|▎| 5027/14932 [07:09<14:07, 11.69it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  34%|▎| 5031/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  34%|▎| 5031/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -46717,8 +46694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5028/14932 [07:10<14:07, 11.69it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  34%|▎| 5028/14932 [07:10<14:07, 11.69it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  34%|▎| 5032/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  34%|▎| 5032/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -46726,8 +46703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5029/14932 [07:10<14:07, 11.69it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  34%|▎| 5029/14932 [07:10<14:07, 11.69it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  34%|▎| 5033/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  34%|▎| 5033/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -46735,8 +46712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5030/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  34%|▎| 5030/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  34%|▎| 5034/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  34%|▎| 5034/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -46744,8 +46721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5031/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  34%|▎| 5031/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  34%|▎| 5035/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  34%|▎| 5035/14932 [07:06<13:59, 11.79it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -46753,8 +46730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5032/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  34%|▎| 5032/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  34%|▎| 5036/14932 [07:07<13:59, 11.79it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  34%|▎| 5036/14932 [07:07<13:59, 11.79it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -46762,8 +46739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5033/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  34%|▎| 5033/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=0.78"
+      "Epoch 0:  34%|▎| 5037/14932 [07:07<13:59, 11.79it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  34%|▎| 5037/14932 [07:07<13:59, 11.79it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -46771,8 +46748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5034/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=0.78\r",
-      "Epoch 0:  34%|▎| 5034/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  34%|▎| 5038/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  34%|▎| 5038/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -46780,8 +46757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5035/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  34%|▎| 5035/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  34%|▎| 5039/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  34%|▎| 5039/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -46789,8 +46766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5036/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  34%|▎| 5036/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=5.09"
+      "Epoch 0:  34%|▎| 5040/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  34%|▎| 5040/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -46798,8 +46775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5037/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=5.09\r",
-      "Epoch 0:  34%|▎| 5037/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  34%|▎| 5041/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  34%|▎| 5041/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -46807,8 +46784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5038/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  34%|▎| 5038/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  34%|▎| 5042/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  34%|▎| 5042/14932 [07:07<13:58, 11.79it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -46816,8 +46793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5039/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  34%|▎| 5039/14932 [07:10<14:06, 11.69it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  34%|▎| 5043/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  34%|▎| 5043/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -46825,8 +46802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5040/14932 [07:11<14:06, 11.69it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  34%|▎| 5040/14932 [07:11<14:06, 11.69it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  34%|▎| 5044/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  34%|▎| 5044/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -46834,8 +46811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5041/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  34%|▎| 5041/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  34%|▎| 5045/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  34%|▎| 5045/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -46843,8 +46820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5042/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  34%|▎| 5042/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  34%|▎| 5046/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  34%|▎| 5046/14932 [07:07<13:58, 11.80it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -46852,8 +46829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5043/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  34%|▎| 5043/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  34%|▎| 5047/14932 [07:07<13:57, 11.80it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  34%|▎| 5047/14932 [07:07<13:57, 11.80it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -46861,8 +46838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5044/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  34%|▎| 5044/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  34%|▎| 5048/14932 [07:07<13:57, 11.79it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  34%|▎| 5048/14932 [07:07<13:57, 11.79it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -46870,8 +46847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5045/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  34%|▎| 5045/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  34%|▎| 5049/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  34%|▎| 5049/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -46879,8 +46856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5046/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  34%|▎| 5046/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  34%|▎| 5050/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  34%|▎| 5050/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -46888,8 +46865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5047/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  34%|▎| 5047/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  34%|▎| 5051/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  34%|▎| 5051/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -46897,8 +46874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5048/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  34%|▎| 5048/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  34%|▎| 5052/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  34%|▎| 5052/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -46906,8 +46883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5049/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  34%|▎| 5049/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  34%|▎| 5053/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  34%|▎| 5053/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -46915,8 +46892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5050/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  34%|▎| 5050/14932 [07:11<14:05, 11.69it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  34%|▎| 5054/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  34%|▎| 5054/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -46924,8 +46901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5051/14932 [07:11<14:04, 11.69it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  34%|▎| 5051/14932 [07:11<14:04, 11.69it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  34%|▎| 5055/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  34%|▎| 5055/14932 [07:08<13:57, 11.80it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -46933,8 +46910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5052/14932 [07:11<14:04, 11.70it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  34%|▎| 5052/14932 [07:11<14:04, 11.70it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  34%|▎| 5056/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  34%|▎| 5056/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -46942,8 +46919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5053/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  34%|▎| 5053/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  34%|▎| 5057/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  34%|▎| 5057/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -46951,8 +46928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5054/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  34%|▎| 5054/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  34%|▎| 5058/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  34%|▎| 5058/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -46960,8 +46937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5055/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  34%|▎| 5055/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  34%|▎| 5059/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  34%|▎| 5059/14932 [07:08<13:57, 11.79it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -46969,8 +46946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5056/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  34%|▎| 5056/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  34%|▎| 5060/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  34%|▎| 5060/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -46978,8 +46955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5057/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  34%|▎| 5057/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  34%|▎| 5061/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  34%|▎| 5061/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -46987,8 +46964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5058/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  34%|▎| 5058/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  34%|▎| 5062/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  34%|▎| 5062/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -46996,8 +46973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5059/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  34%|▎| 5059/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  34%|▎| 5063/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  34%|▎| 5063/14932 [07:09<13:56, 11.79it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -47005,8 +46982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5060/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  34%|▎| 5060/14932 [07:12<14:04, 11.69it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  34%|▎| 5064/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  34%|▎| 5064/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -47014,8 +46991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5061/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  34%|▎| 5061/14932 [07:12<14:04, 11.70it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  34%|▎| 5065/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  34%|▎| 5065/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -47023,8 +47000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5062/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  34%|▎| 5062/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  34%|▎| 5066/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  34%|▎| 5066/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -47032,8 +47009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5063/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  34%|▎| 5063/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  34%|▎| 5067/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  34%|▎| 5067/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -47041,8 +47018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5064/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  34%|▎| 5064/14932 [07:12<14:03, 11.70it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  34%|▎| 5068/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  34%|▎| 5068/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -47050,8 +47027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5065/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  34%|▎| 5065/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  34%|▎| 5069/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  34%|▎| 5069/14932 [07:09<13:56, 11.80it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -47059,8 +47036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5066/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  34%|▎| 5066/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  34%|▎| 5070/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  34%|▎| 5070/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -47068,8 +47045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5067/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  34%|▎| 5067/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  34%|▎| 5071/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  34%|▎| 5071/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -47077,8 +47054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5068/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  34%|▎| 5068/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  34%|▎| 5072/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  34%|▎| 5072/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -47086,8 +47063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5069/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  34%|▎| 5069/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  34%|▎| 5073/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  34%|▎| 5073/14932 [07:09<13:55, 11.80it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -47095,8 +47072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5070/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  34%|▎| 5070/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  34%|▎| 5074/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  34%|▎| 5074/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -47104,8 +47081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5071/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  34%|▎| 5071/14932 [07:13<14:03, 11.70it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  34%|▎| 5075/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  34%|▎| 5075/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -47113,8 +47090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5072/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  34%|▎| 5072/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  34%|▎| 5076/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  34%|▎| 5076/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -47122,8 +47099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5073/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  34%|▎| 5073/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  34%|▎| 5077/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  34%|▎| 5077/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -47131,8 +47108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5074/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  34%|▎| 5074/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  34%|▎| 5078/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  34%|▎| 5078/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -47140,8 +47117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5075/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  34%|▎| 5075/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  34%|▎| 5079/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  34%|▎| 5079/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -47149,8 +47126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5076/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  34%|▎| 5076/14932 [07:13<14:02, 11.70it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  34%|▎| 5080/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  34%|▎| 5080/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -47158,8 +47135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5077/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  34%|▎| 5077/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  34%|▎| 5081/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  34%|▎| 5081/14932 [07:10<13:55, 11.80it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -47167,8 +47144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5078/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  34%|▎| 5078/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  34%|▎| 5082/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  34%|▎| 5082/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -47176,8 +47153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5079/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  34%|▎| 5079/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  34%|▎| 5083/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  34%|▎| 5083/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -47185,8 +47162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5080/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  34%|▎| 5080/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  34%|▎| 5084/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  34%|▎| 5084/14932 [07:10<13:54, 11.80it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -47194,8 +47171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5081/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  34%|▎| 5081/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  34%|▎| 5085/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  34%|▎| 5085/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -47203,8 +47180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5082/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  34%|▎| 5082/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  34%|▎| 5086/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  34%|▎| 5086/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -47212,8 +47189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5083/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  34%|▎| 5083/14932 [07:14<14:02, 11.70it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  34%|▎| 5087/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  34%|▎| 5087/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -47221,8 +47198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5084/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  34%|▎| 5084/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  34%|▎| 5088/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  34%|▎| 5088/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -47230,8 +47207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5085/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  34%|▎| 5085/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  34%|▎| 5089/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  34%|▎| 5089/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -47239,8 +47216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5086/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  34%|▎| 5086/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  34%|▎| 5090/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  34%|▎| 5090/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -47248,8 +47225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5087/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  34%|▎| 5087/14932 [07:14<14:01, 11.70it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  34%|▎| 5091/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  34%|▎| 5091/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -47257,8 +47234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5088/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  34%|▎| 5088/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  34%|▎| 5092/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  34%|▎| 5092/14932 [07:11<13:54, 11.80it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -47266,8 +47243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5089/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  34%|▎| 5089/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  34%|▎| 5093/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  34%|▎| 5093/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -47275,8 +47252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5090/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  34%|▎| 5090/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  34%|▎| 5094/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  34%|▎| 5094/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -47284,8 +47261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5091/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  34%|▎| 5091/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  34%|▎| 5095/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  34%|▎| 5095/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -47293,8 +47270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5092/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  34%|▎| 5092/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  34%|▎| 5096/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  34%|▎| 5096/14932 [07:11<13:53, 11.80it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -47302,8 +47279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5093/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  34%|▎| 5093/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  34%|▎| 5097/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  34%|▎| 5097/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=4.78"
      ]
     },
     {
@@ -47311,8 +47288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5094/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  34%|▎| 5094/14932 [07:15<14:01, 11.70it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  34%|▎| 5098/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=4.78\r",
+      "Epoch 0:  34%|▎| 5098/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -47320,8 +47297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5095/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  34%|▎| 5095/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  34%|▎| 5099/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  34%|▎| 5099/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -47329,8 +47306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5096/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  34%|▎| 5096/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  34%|▎| 5100/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  34%|▎| 5100/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -47338,8 +47315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5097/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  34%|▎| 5097/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  34%|▎| 5101/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  34%|▎| 5101/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -47347,8 +47324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5098/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  34%|▎| 5098/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  34%|▎| 5102/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  34%|▎| 5102/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -47356,8 +47333,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5099/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  34%|▎| 5099/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  34%|▎| 5103/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -47365,8 +47341,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5100/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  34%|▎| 5100/14932 [07:15<14:00, 11.70it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  34%|▎| 5103/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -47374,8 +47349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5101/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  34%|▎| 5101/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  34%|▎| 5104/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  34%|▎| 5104/14932 [07:12<13:53, 11.80it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -47383,8 +47358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5102/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  34%|▎| 5102/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  34%|▎| 5105/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  34%|▎| 5105/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=1.19"
      ]
     },
     {
@@ -47392,8 +47367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5103/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  34%|▎| 5103/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  34%|▎| 5106/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=1.19\r",
+      "Epoch 0:  34%|▎| 5106/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -47401,8 +47376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5104/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  34%|▎| 5104/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  34%|▎| 5107/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  34%|▎| 5107/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -47410,8 +47385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5105/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  34%|▎| 5105/14932 [07:16<14:00, 11.70it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  34%|▎| 5108/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  34%|▎| 5108/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -47419,8 +47394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5106/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  34%|▎| 5106/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  34%|▎| 5109/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  34%|▎| 5109/14932 [07:12<13:52, 11.80it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -47428,8 +47403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5107/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  34%|▎| 5107/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  34%|▎| 5110/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  34%|▎| 5110/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -47437,8 +47412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5108/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  34%|▎| 5108/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  34%|▎| 5111/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  34%|▎| 5111/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -47446,8 +47421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5109/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  34%|▎| 5109/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  34%|▎| 5112/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  34%|▎| 5112/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -47455,8 +47430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5110/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  34%|▎| 5110/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  34%|▎| 5113/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  34%|▎| 5113/14932 [07:13<13:52, 11.80it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -47464,8 +47439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5111/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  34%|▎| 5111/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  34%|▎| 5114/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  34%|▎| 5114/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -47473,8 +47448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5112/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  34%|▎| 5112/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  34%|▎| 5115/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  34%|▎| 5115/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -47482,8 +47457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5113/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  34%|▎| 5113/14932 [07:16<13:59, 11.70it/s, v_num=o30c, train/loss=0.74"
+      "Epoch 0:  34%|▎| 5116/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  34%|▎| 5116/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -47491,8 +47466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5114/14932 [07:17<13:59, 11.70it/s, v_num=o30c, train/loss=0.74\r",
-      "Epoch 0:  34%|▎| 5114/14932 [07:17<13:59, 11.70it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  34%|▎| 5117/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  34%|▎| 5117/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -47500,8 +47475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5115/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  34%|▎| 5115/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  34%|▎| 5118/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  34%|▎| 5118/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -47509,8 +47484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5116/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  34%|▎| 5116/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  34%|▎| 5119/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  34%|▎| 5119/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -47518,8 +47493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5117/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  34%|▎| 5117/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  34%|▎| 5120/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  34%|▎| 5120/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -47527,8 +47502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5118/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  34%|▎| 5118/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  34%|▎| 5121/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  34%|▎| 5121/14932 [07:13<13:51, 11.80it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -47536,8 +47511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5119/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  34%|▎| 5119/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  34%|▎| 5122/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  34%|▎| 5122/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -47545,8 +47520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5120/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  34%|▎| 5120/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  34%|▎| 5123/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  34%|▎| 5123/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -47554,8 +47529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5121/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  34%|▎| 5121/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  34%|▎| 5124/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  34%|▎| 5124/14932 [07:14<13:51, 11.80it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -47563,8 +47538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5122/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  34%|▎| 5122/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  34%|▎| 5125/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  34%|▎| 5125/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -47572,8 +47547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5123/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  34%|▎| 5123/14932 [07:17<13:58, 11.70it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  34%|▎| 5126/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  34%|▎| 5126/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -47581,8 +47556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5124/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  34%|▎| 5124/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  34%|▎| 5127/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  34%|▎| 5127/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -47590,8 +47565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5125/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  34%|▎| 5125/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  34%|▎| 5128/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  34%|▎| 5128/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -47599,8 +47574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5126/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  34%|▎| 5126/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  34%|▎| 5129/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  34%|▎| 5129/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -47608,8 +47583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5127/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  34%|▎| 5127/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  34%|▎| 5130/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  34%|▎| 5130/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -47617,8 +47592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5128/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  34%|▎| 5128/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  34%|▎| 5131/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  34%|▎| 5131/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -47626,8 +47601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5129/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  34%|▎| 5129/14932 [07:18<13:58, 11.70it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  34%|▎| 5132/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  34%|▎| 5132/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -47635,8 +47610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5130/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  34%|▎| 5130/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  34%|▎| 5133/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  34%|▎| 5133/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -47644,8 +47619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5131/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  34%|▎| 5131/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  34%|▎| 5134/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  34%|▎| 5134/14932 [07:14<13:50, 11.80it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -47653,8 +47628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5132/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  34%|▎| 5132/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  34%|▎| 5135/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  34%|▎| 5135/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -47662,8 +47637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5133/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  34%|▎| 5133/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  34%|▎| 5136/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  34%|▎| 5136/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -47671,8 +47646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5134/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  34%|▎| 5134/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  34%|▎| 5137/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  34%|▎| 5137/14932 [07:15<13:50, 11.80it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -47680,8 +47655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5135/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  34%|▎| 5135/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  34%|▎| 5138/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  34%|▎| 5138/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -47689,8 +47664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5136/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  34%|▎| 5136/14932 [07:18<13:57, 11.70it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  34%|▎| 5139/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  34%|▎| 5139/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -47698,8 +47673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5137/14932 [07:19<13:57, 11.70it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  34%|▎| 5137/14932 [07:19<13:57, 11.70it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  34%|▎| 5140/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  34%|▎| 5140/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -47707,8 +47682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5138/14932 [07:19<13:57, 11.70it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  34%|▎| 5138/14932 [07:19<13:57, 11.70it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  34%|▎| 5141/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  34%|▎| 5141/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -47716,8 +47691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5139/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  34%|▎| 5139/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  34%|▎| 5142/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  34%|▎| 5142/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -47725,8 +47700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5140/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  34%|▎| 5140/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  34%|▎| 5143/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  34%|▎| 5143/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -47734,8 +47709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5141/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  34%|▎| 5141/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  34%|▎| 5144/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  34%|▎| 5144/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -47743,8 +47718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5142/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  34%|▎| 5142/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  34%|▎| 5145/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  34%|▎| 5145/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -47752,8 +47727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5143/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  34%|▎| 5143/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  34%|▎| 5146/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  34%|▎| 5146/14932 [07:15<13:49, 11.80it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -47761,8 +47736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5144/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  34%|▎| 5144/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  34%|▎| 5147/14932 [07:16<13:49, 11.80it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  34%|▎| 5147/14932 [07:16<13:49, 11.80it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -47770,8 +47745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5145/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  34%|▎| 5145/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  34%|▎| 5148/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  34%|▎| 5148/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -47779,8 +47754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5146/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  34%|▎| 5146/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  34%|▎| 5149/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  34%|▎| 5149/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -47788,8 +47763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5147/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  34%|▎| 5147/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  34%|▎| 5150/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  34%|▎| 5150/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -47797,8 +47772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5148/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  34%|▎| 5148/14932 [07:19<13:56, 11.70it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  34%|▎| 5151/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  34%|▎| 5151/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -47806,8 +47781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5149/14932 [07:19<13:55, 11.70it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  34%|▎| 5149/14932 [07:19<13:55, 11.70it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  35%|▎| 5152/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  35%|▎| 5152/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -47815,8 +47790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5150/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  34%|▎| 5150/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  35%|▎| 5153/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  35%|▎| 5153/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -47824,8 +47799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  34%|▎| 5151/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  34%|▎| 5151/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  35%|▎| 5154/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  35%|▎| 5154/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -47833,8 +47808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5152/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  35%|▎| 5152/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  35%|▎| 5155/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  35%|▎| 5155/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -47842,8 +47817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5153/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  35%|▎| 5153/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  35%|▎| 5156/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  35%|▎| 5156/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -47851,8 +47826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5154/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  35%|▎| 5154/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  35%|▎| 5157/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  35%|▎| 5157/14932 [07:16<13:48, 11.80it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -47860,8 +47835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5155/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  35%|▎| 5155/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  35%|▎| 5158/14932 [07:17<13:48, 11.80it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  35%|▎| 5158/14932 [07:17<13:48, 11.80it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -47869,8 +47844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5156/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  35%|▎| 5156/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  35%|▎| 5159/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  35%|▎| 5159/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -47878,8 +47853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5157/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  35%|▎| 5157/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  35%|▎| 5160/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  35%|▎| 5160/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -47887,8 +47862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5158/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  35%|▎| 5158/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  35%|▎| 5161/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  35%|▎| 5161/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -47896,8 +47871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5159/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  35%|▎| 5159/14932 [07:20<13:55, 11.70it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  35%|▎| 5162/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  35%|▎| 5162/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -47905,8 +47880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5160/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  35%|▎| 5160/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  35%|▎| 5163/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  35%|▎| 5163/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -47914,8 +47889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5161/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  35%|▎| 5161/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  35%|▎| 5164/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  35%|▎| 5164/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -47923,8 +47898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5162/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  35%|▎| 5162/14932 [07:21<13:55, 11.70it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  35%|▎| 5165/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  35%|▎| 5165/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -47932,8 +47907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5163/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  35%|▎| 5163/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  35%|▎| 5166/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  35%|▎| 5166/14932 [07:17<13:47, 11.80it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -47941,8 +47916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5164/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  35%|▎| 5164/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=0.96"
+      "Epoch 0:  35%|▎| 5167/14932 [07:17<13:47, 11.81it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  35%|▎| 5167/14932 [07:17<13:47, 11.81it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -47950,8 +47925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5165/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=0.96\r",
-      "Epoch 0:  35%|▎| 5165/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  35%|▎| 5168/14932 [07:17<13:47, 11.81it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  35%|▎| 5168/14932 [07:17<13:47, 11.81it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -47959,8 +47934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5166/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  35%|▎| 5166/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  35%|▎| 5169/14932 [07:17<13:46, 11.81it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  35%|▎| 5169/14932 [07:17<13:46, 11.81it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -47968,8 +47943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5167/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  35%|▎| 5167/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  35%|▎| 5170/14932 [07:17<13:46, 11.81it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  35%|▎| 5170/14932 [07:17<13:46, 11.81it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -47977,8 +47952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5168/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  35%|▎| 5168/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  35%|▎| 5171/14932 [07:18<13:46, 11.80it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  35%|▎| 5171/14932 [07:18<13:46, 11.80it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -47986,8 +47961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5169/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  35%|▎| 5169/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  35%|▎| 5172/14932 [07:18<13:46, 11.80it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  35%|▎| 5172/14932 [07:18<13:46, 11.80it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -47995,8 +47970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5170/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  35%|▎| 5170/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  35%|▎| 5173/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  35%|▎| 5173/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -48004,8 +47979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5171/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  35%|▎| 5171/14932 [07:21<13:54, 11.70it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  35%|▎| 5174/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  35%|▎| 5174/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -48013,8 +47988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5172/14932 [07:21<13:53, 11.70it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  35%|▎| 5172/14932 [07:21<13:53, 11.70it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  35%|▎| 5175/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  35%|▎| 5175/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -48022,8 +47997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5173/14932 [07:21<13:53, 11.70it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  35%|▎| 5173/14932 [07:21<13:53, 11.70it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  35%|▎| 5176/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  35%|▎| 5176/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -48031,8 +48006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5174/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  35%|▎| 5174/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  35%|▎| 5177/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  35%|▎| 5177/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -48040,8 +48015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5175/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  35%|▎| 5175/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  35%|▎| 5178/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  35%|▎| 5178/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -48049,8 +48024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5176/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  35%|▎| 5176/14932 [07:22<13:53, 11.70it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  35%|▎| 5179/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  35%|▎| 5179/14932 [07:18<13:46, 11.81it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -48058,8 +48033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5177/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  35%|▎| 5177/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  35%|▎| 5180/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  35%|▎| 5180/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -48067,8 +48042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5178/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  35%|▎| 5178/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  35%|▎| 5181/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  35%|▎| 5181/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -48076,8 +48051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5179/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  35%|▎| 5179/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  35%|▎| 5182/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  35%|▎| 5182/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -48085,8 +48060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5180/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  35%|▎| 5180/14932 [07:22<13:53, 11.71it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  35%|▎| 5183/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  35%|▎| 5183/14932 [07:18<13:45, 11.81it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -48094,8 +48069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5181/14932 [07:22<13:52, 11.71it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  35%|▎| 5181/14932 [07:22<13:52, 11.71it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  35%|▎| 5184/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  35%|▎| 5184/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -48103,8 +48078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5182/14932 [07:22<13:52, 11.71it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  35%|▎| 5182/14932 [07:22<13:52, 11.71it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  35%|▎| 5185/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  35%|▎| 5185/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -48112,8 +48087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5183/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  35%|▎| 5183/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  35%|▎| 5186/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  35%|▎| 5186/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -48121,8 +48096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5184/14932 [07:23<13:53, 11.69it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  35%|▎| 5184/14932 [07:23<13:53, 11.69it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  35%|▎| 5187/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  35%|▎| 5187/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -48130,8 +48105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5185/14932 [07:23<13:53, 11.69it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  35%|▎| 5185/14932 [07:23<13:53, 11.69it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  35%|▎| 5188/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  35%|▎| 5188/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -48139,8 +48114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5186/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  35%|▎| 5186/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  35%|▎| 5189/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  35%|▎| 5189/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -48148,8 +48123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5187/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  35%|▎| 5187/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  35%|▎| 5190/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  35%|▎| 5190/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -48157,8 +48132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5188/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  35%|▎| 5188/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  35%|▎| 5191/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  35%|▎| 5191/14932 [07:19<13:45, 11.81it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -48166,8 +48141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5189/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  35%|▎| 5189/14932 [07:23<13:53, 11.70it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  35%|▎| 5192/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  35%|▎| 5192/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -48175,8 +48150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5190/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  35%|▎| 5190/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  35%|▎| 5193/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  35%|▎| 5193/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -48184,8 +48159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5191/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  35%|▎| 5191/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  35%|▎| 5194/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  35%|▎| 5194/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -48193,8 +48168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5192/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  35%|▎| 5192/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  35%|▎| 5195/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  35%|▎| 5195/14932 [07:19<13:44, 11.81it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -48202,8 +48177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5193/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  35%|▎| 5193/14932 [07:23<13:52, 11.70it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  35%|▎| 5196/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  35%|▎| 5196/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -48211,8 +48186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5194/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  35%|▎| 5194/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  35%|▎| 5197/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  35%|▎| 5197/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -48220,8 +48195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5195/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  35%|▎| 5195/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  35%|▎| 5198/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  35%|▎| 5198/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -48229,8 +48204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5196/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  35%|▎| 5196/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=0.82"
+      "Epoch 0:  35%|▎| 5199/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  35%|▎| 5199/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -48238,8 +48213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5197/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=0.82\r",
-      "Epoch 0:  35%|▎| 5197/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  35%|▎| 5200/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  35%|▎| 5200/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -48247,8 +48222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5198/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  35%|▎| 5198/14932 [07:24<13:52, 11.70it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  35%|▎| 5201/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  35%|▎| 5201/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -48256,8 +48231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5199/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  35%|▎| 5199/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  35%|▎| 5202/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  35%|▎| 5202/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -48265,8 +48240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5200/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  35%|▎| 5200/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  35%|▎| 5203/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  35%|▎| 5203/14932 [07:20<13:44, 11.81it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -48274,8 +48249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5201/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  35%|▎| 5201/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  35%|▎| 5204/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  35%|▎| 5204/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -48283,8 +48258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5202/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  35%|▎| 5202/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  35%|▎| 5205/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  35%|▎| 5205/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -48292,8 +48267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5203/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  35%|▎| 5203/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  35%|▎| 5206/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  35%|▎| 5206/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -48301,8 +48276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5204/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  35%|▎| 5204/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  35%|▎| 5207/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  35%|▎| 5207/14932 [07:20<13:43, 11.81it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -48310,8 +48285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5205/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  35%|▎| 5205/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  35%|▎| 5208/14932 [07:21<13:43, 11.81it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  35%|▎| 5208/14932 [07:21<13:43, 11.81it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -48319,8 +48294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5206/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  35%|▎| 5206/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  35%|▎| 5209/14932 [07:21<13:43, 11.81it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  35%|▎| 5209/14932 [07:21<13:43, 11.81it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -48328,8 +48303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5207/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  35%|▎| 5207/14932 [07:24<13:51, 11.70it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  35%|▎| 5210/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  35%|▎| 5210/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -48337,8 +48312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5208/14932 [07:25<13:51, 11.70it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  35%|▎| 5208/14932 [07:25<13:51, 11.70it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  35%|▎| 5211/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  35%|▎| 5211/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -48346,8 +48321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5209/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  35%|▎| 5209/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  35%|▎| 5212/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  35%|▎| 5212/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -48355,8 +48330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5210/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  35%|▎| 5210/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  35%|▎| 5213/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  35%|▎| 5213/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -48364,8 +48339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5211/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  35%|▎| 5211/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  35%|▎| 5214/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  35%|▎| 5214/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -48373,8 +48348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5212/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  35%|▎| 5212/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  35%|▎| 5215/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  35%|▎| 5215/14932 [07:21<13:43, 11.80it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -48382,8 +48357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5213/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  35%|▎| 5213/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  35%|▎| 5216/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  35%|▎| 5216/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -48391,8 +48366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5214/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  35%|▎| 5214/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  35%|▎| 5217/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  35%|▎| 5217/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -48400,8 +48375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5215/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  35%|▎| 5215/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  35%|▎| 5218/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  35%|▎| 5218/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -48409,8 +48384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5216/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  35%|▎| 5216/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  35%|▎| 5219/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  35%|▎| 5219/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -48418,8 +48393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5217/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  35%|▎| 5217/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  35%|▎| 5220/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  35%|▎| 5220/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -48427,7 +48402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5218/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  35%|▎| 5221/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  35%|▎| 5221/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -48435,7 +48411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5218/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  35%|▎| 5222/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  35%|▎| 5222/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -48443,8 +48420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5219/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  35%|▎| 5219/14932 [07:25<13:50, 11.70it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  35%|▎| 5223/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  35%|▎| 5223/14932 [07:22<13:43, 11.80it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -48452,8 +48429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5220/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  35%|▎| 5220/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  35%|▎| 5224/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  35%|▎| 5224/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -48461,8 +48438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5221/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  35%|▎| 5221/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  35%|▎| 5225/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  35%|▎| 5225/14932 [07:22<13:42, 11.80it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -48470,8 +48447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5222/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  35%|▎| 5222/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  35%|▎| 5226/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  35%|▎| 5226/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -48479,8 +48456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5223/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  35%|▎| 5223/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  35%|▎| 5227/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  35%|▎| 5227/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -48488,8 +48465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5224/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  35%|▎| 5224/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  35%|▎| 5228/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  35%|▎| 5228/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -48497,8 +48474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5225/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  35%|▎| 5225/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  35%|▎| 5229/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  35%|▎| 5229/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -48506,8 +48483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5226/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  35%|▎| 5226/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  35%|▎| 5230/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  35%|▎| 5230/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -48515,8 +48492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5227/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  35%|▎| 5227/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  35%|▎| 5231/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  35%|▎| 5231/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -48524,8 +48501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5228/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  35%|▎| 5228/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  35%|▎| 5232/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  35%|▎| 5232/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -48533,8 +48510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5229/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  35%|▎| 5229/14932 [07:26<13:49, 11.70it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  35%|▎| 5233/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  35%|▎| 5233/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -48542,8 +48519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5230/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  35%|▎| 5230/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  35%|▎| 5234/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  35%|▎| 5234/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -48551,8 +48528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5231/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  35%|▎| 5231/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  35%|▎| 5235/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  35%|▎| 5235/14932 [07:23<13:42, 11.80it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -48560,8 +48537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5232/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  35%|▎| 5232/14932 [07:26<13:48, 11.70it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  35%|▎| 5236/14932 [07:23<13:41, 11.80it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  35%|▎| 5236/14932 [07:23<13:41, 11.80it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -48569,8 +48546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5233/14932 [07:27<13:48, 11.70it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  35%|▎| 5233/14932 [07:27<13:48, 11.70it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  35%|▎| 5237/14932 [07:23<13:41, 11.80it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  35%|▎| 5237/14932 [07:23<13:41, 11.80it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -48578,8 +48555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5234/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  35%|▎| 5234/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  35%|▎| 5238/14932 [07:23<13:41, 11.80it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  35%|▎| 5238/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -48587,8 +48564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5235/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  35%|▎| 5235/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  35%|▎| 5239/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:  35%|▎| 5239/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -48596,8 +48573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5236/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  35%|▎| 5236/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  35%|▎| 5240/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  35%|▎| 5240/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -48605,8 +48582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5237/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  35%|▎| 5237/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  35%|▎| 5241/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  35%|▎| 5241/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -48614,7 +48591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5238/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  35%|▎| 5242/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  35%|▎| 5242/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -48622,7 +48600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5238/14932 [07:27<13:48, 11.71it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  35%|▎| 5243/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  35%|▎| 5243/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -48630,8 +48609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5239/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  35%|▎| 5239/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  35%|▎| 5244/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  35%|▎| 5244/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -48639,8 +48618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5240/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  35%|▎| 5240/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  35%|▎| 5245/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  35%|▎| 5245/14932 [07:24<13:41, 11.80it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -48648,8 +48627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5241/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  35%|▎| 5241/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  35%|▎| 5246/14932 [07:24<13:40, 11.80it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:  35%|▎| 5246/14932 [07:24<13:40, 11.80it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -48657,8 +48636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5242/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  35%|▎| 5242/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  35%|▎| 5247/14932 [07:24<13:40, 11.80it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  35%|▎| 5247/14932 [07:24<13:40, 11.80it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -48666,8 +48645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5243/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  35%|▎| 5243/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  35%|▎| 5248/14932 [07:24<13:41, 11.79it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  35%|▎| 5248/14932 [07:24<13:41, 11.79it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -48675,8 +48654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5244/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  35%|▎| 5244/14932 [07:27<13:47, 11.71it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  35%|▎| 5249/14932 [07:25<13:41, 11.79it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  35%|▎| 5249/14932 [07:25<13:41, 11.79it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -48684,8 +48663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5245/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  35%|▎| 5245/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  35%|▎| 5250/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  35%|▎| 5250/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -48693,7 +48672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5246/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  35%|▎| 5251/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  35%|▎| 5251/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -48701,7 +48681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5246/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  35%|▎| 5252/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  35%|▎| 5252/14932 [07:25<13:40, 11.79it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -48709,8 +48690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5247/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  35%|▎| 5247/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  35%|▎| 5253/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  35%|▎| 5253/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -48718,8 +48699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5248/14932 [07:28<13:47, 11.70it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  35%|▎| 5248/14932 [07:28<13:47, 11.70it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  35%|▎| 5254/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  35%|▎| 5254/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -48727,8 +48708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5249/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  35%|▎| 5249/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  35%|▎| 5255/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  35%|▎| 5255/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -48736,8 +48717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5250/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  35%|▎| 5250/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=0.82"
+      "Epoch 0:  35%|▎| 5256/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  35%|▎| 5256/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -48745,8 +48726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5251/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=0.82\r",
-      "Epoch 0:  35%|▎| 5251/14932 [07:28<13:47, 11.71it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  35%|▎| 5257/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  35%|▎| 5257/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -48754,8 +48735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5252/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  35%|▎| 5252/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  35%|▎| 5258/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  35%|▎| 5258/14932 [07:25<13:40, 11.80it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -48763,8 +48744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5253/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  35%|▎| 5253/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  35%|▎| 5259/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  35%|▎| 5259/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -48772,8 +48753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5254/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  35%|▎| 5254/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  35%|▎| 5260/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  35%|▎| 5260/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -48781,8 +48762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5255/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  35%|▎| 5255/14932 [07:28<13:46, 11.71it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  35%|▎| 5261/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  35%|▎| 5261/14932 [07:25<13:39, 11.80it/s, v_num=ui8w, train/loss=0.83"
      ]
     },
     {
@@ -48790,8 +48771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5256/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  35%|▎| 5256/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  35%|▎| 5262/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=0.83\r",
+      "Epoch 0:  35%|▎| 5262/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -48799,8 +48780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5257/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  35%|▎| 5257/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  35%|▎| 5263/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  35%|▎| 5263/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -48808,8 +48789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5258/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  35%|▎| 5258/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  35%|▎| 5264/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  35%|▎| 5264/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -48817,8 +48798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5259/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  35%|▎| 5259/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  35%|▎| 5265/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  35%|▎| 5265/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -48826,8 +48807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5260/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  35%|▎| 5260/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  35%|▎| 5266/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  35%|▎| 5266/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -48835,8 +48816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5261/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  35%|▎| 5261/14932 [07:29<13:46, 11.71it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  35%|▎| 5267/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  35%|▎| 5267/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -48844,8 +48825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5262/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  35%|▎| 5262/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  35%|▎| 5268/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  35%|▎| 5268/14932 [07:26<13:39, 11.80it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -48853,8 +48834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5263/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  35%|▎| 5263/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  35%|▎| 5269/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  35%|▎| 5269/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -48862,8 +48843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5264/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  35%|▎| 5264/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  35%|▎| 5270/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  35%|▎| 5270/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -48871,8 +48852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5265/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  35%|▎| 5265/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  35%|▎| 5271/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  35%|▎| 5271/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -48880,8 +48861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5266/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  35%|▎| 5266/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  35%|▎| 5272/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  35%|▎| 5272/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -48889,8 +48870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5267/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  35%|▎| 5267/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  35%|▎| 5273/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  35%|▎| 5273/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -48898,8 +48879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5268/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  35%|▎| 5268/14932 [07:29<13:45, 11.71it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  35%|▎| 5274/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  35%|▎| 5274/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -48907,8 +48888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5269/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  35%|▎| 5269/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  35%|▎| 5275/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  35%|▎| 5275/14932 [07:26<13:38, 11.80it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -48916,8 +48897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5270/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  35%|▎| 5270/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  35%|▎| 5276/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  35%|▎| 5276/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -48925,8 +48906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5271/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  35%|▎| 5271/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  35%|▎| 5277/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  35%|▎| 5277/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -48934,8 +48915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5272/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  35%|▎| 5272/14932 [07:30<13:45, 11.71it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  35%|▎| 5278/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  35%|▎| 5278/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=1.15"
      ]
     },
     {
@@ -48943,8 +48924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5273/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  35%|▎| 5273/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  35%|▎| 5279/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=1.15\r",
+      "Epoch 0:  35%|▎| 5279/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -48952,8 +48933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5274/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  35%|▎| 5274/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  35%|▎| 5280/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  35%|▎| 5280/14932 [07:27<13:38, 11.80it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -48961,8 +48942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5275/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  35%|▎| 5275/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  35%|▎| 5281/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  35%|▎| 5281/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -48970,8 +48951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5276/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  35%|▎| 5276/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  35%|▎| 5282/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  35%|▎| 5282/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -48979,8 +48960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5277/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  35%|▎| 5277/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  35%|▎| 5283/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  35%|▎| 5283/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -48988,8 +48969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5278/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  35%|▎| 5278/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  35%|▎| 5284/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  35%|▎| 5284/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -48997,8 +48978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5279/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  35%|▎| 5279/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  35%|▎| 5285/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  35%|▎| 5285/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -49006,8 +48987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5280/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  35%|▎| 5280/14932 [07:30<13:44, 11.71it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  35%|▎| 5286/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  35%|▎| 5286/14932 [07:27<13:37, 11.80it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -49015,8 +48996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5281/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  35%|▎| 5281/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  35%|▎| 5287/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  35%|▎| 5287/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -49024,8 +49005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5282/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  35%|▎| 5282/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  35%|▎| 5288/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  35%|▎| 5288/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -49033,8 +49014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5283/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  35%|▎| 5283/14932 [07:31<13:44, 11.71it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  35%|▎| 5289/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  35%|▎| 5289/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -49042,8 +49023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5284/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  35%|▎| 5284/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  35%|▎| 5290/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  35%|▎| 5290/14932 [07:28<13:37, 11.80it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -49051,8 +49032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5285/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  35%|▎| 5285/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  35%|▎| 5291/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  35%|▎| 5291/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -49060,8 +49041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5286/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  35%|▎| 5286/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  35%|▎| 5292/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  35%|▎| 5292/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -49069,8 +49050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5287/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  35%|▎| 5287/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=0.92"
+      "Epoch 0:  35%|▎| 5293/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  35%|▎| 5293/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -49078,8 +49059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5288/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=0.92\r",
-      "Epoch 0:  35%|▎| 5288/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  35%|▎| 5294/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  35%|▎| 5294/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -49087,8 +49068,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5289/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  35%|▎| 5289/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  35%|▎| 5295/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -49096,8 +49076,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5290/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  35%|▎| 5290/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  35%|▎| 5295/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -49105,8 +49084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5291/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  35%|▎| 5291/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  35%|▎| 5296/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  35%|▎| 5296/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -49114,8 +49093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5292/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  35%|▎| 5292/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  35%|▎| 5297/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  35%|▎| 5297/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -49123,8 +49102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5293/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  35%|▎| 5293/14932 [07:31<13:43, 11.71it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  35%|▎| 5298/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  35%|▎| 5298/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -49132,8 +49111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5294/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  35%|▎| 5294/14932 [07:32<13:43, 11.71it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  35%|▎| 5299/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  35%|▎| 5299/14932 [07:28<13:36, 11.80it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -49141,8 +49120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5295/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  35%|▎| 5295/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  35%|▎| 5300/14932 [07:29<13:36, 11.80it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  35%|▎| 5300/14932 [07:29<13:36, 11.80it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -49150,8 +49129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5296/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  35%|▎| 5296/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  36%|▎| 5301/14932 [07:29<13:36, 11.80it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  36%|▎| 5301/14932 [07:29<13:36, 11.80it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -49159,8 +49138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5297/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  35%|▎| 5297/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  36%|▎| 5302/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  36%|▎| 5302/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -49168,8 +49147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5298/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  35%|▎| 5298/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  36%|▎| 5303/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  36%|▎| 5303/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -49177,8 +49156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5299/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  35%|▎| 5299/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  36%|▎| 5304/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  36%|▎| 5304/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -49186,8 +49165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  35%|▎| 5300/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  35%|▎| 5300/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  36%|▎| 5305/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  36%|▎| 5305/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -49195,8 +49174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5301/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  36%|▎| 5301/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  36%|▎| 5306/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  36%|▎| 5306/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -49204,8 +49183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5302/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  36%|▎| 5302/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  36%|▎| 5307/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  36%|▎| 5307/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -49213,8 +49192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5303/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  36%|▎| 5303/14932 [07:32<13:42, 11.71it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  36%|▎| 5308/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  36%|▎| 5308/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -49222,8 +49201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5304/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  36%|▎| 5304/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=1.51"
+      "Epoch 0:  36%|▎| 5309/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  36%|▎| 5309/14932 [07:29<13:35, 11.80it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -49231,8 +49210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5305/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=1.51\r",
-      "Epoch 0:  36%|▎| 5305/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  36%|▎| 5310/14932 [07:29<13:35, 11.81it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  36%|▎| 5310/14932 [07:29<13:35, 11.81it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -49240,8 +49219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5306/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  36%|▎| 5306/14932 [07:32<13:41, 11.71it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  36%|▎| 5311/14932 [07:29<13:34, 11.81it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  36%|▎| 5311/14932 [07:29<13:34, 11.81it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -49249,8 +49228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5307/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  36%|▎| 5307/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  36%|▎| 5312/14932 [07:30<13:35, 11.80it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  36%|▎| 5312/14932 [07:30<13:35, 11.80it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -49258,8 +49237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5308/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  36%|▎| 5308/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  36%|▎| 5313/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  36%|▎| 5313/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -49267,8 +49246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5309/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  36%|▎| 5309/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  36%|▎| 5314/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  36%|▎| 5314/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -49276,8 +49255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5310/14932 [07:33<13:41, 11.72it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  36%|▎| 5310/14932 [07:33<13:41, 11.72it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  36%|▎| 5315/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  36%|▎| 5315/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -49285,8 +49264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5311/14932 [07:33<13:41, 11.72it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  36%|▎| 5311/14932 [07:33<13:41, 11.72it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  36%|▎| 5316/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  36%|▎| 5316/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -49294,8 +49273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5312/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  36%|▎| 5312/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  36%|▎| 5317/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  36%|▎| 5317/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -49303,8 +49282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5313/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  36%|▎| 5313/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  36%|▎| 5318/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  36%|▎| 5318/14932 [07:30<13:34, 11.80it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -49312,8 +49291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5314/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  36%|▎| 5314/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  36%|▎| 5319/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  36%|▎| 5319/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -49321,8 +49300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5315/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  36%|▎| 5315/14932 [07:33<13:41, 11.71it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  36%|▎| 5320/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  36%|▎| 5320/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -49330,8 +49309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5316/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  36%|▎| 5316/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=1.15"
+      "Epoch 0:  36%|▎| 5321/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  36%|▎| 5321/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -49339,8 +49318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5317/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=1.15\r",
-      "Epoch 0:  36%|▎| 5317/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  36%|▎| 5322/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  36%|▎| 5322/14932 [07:30<13:34, 11.81it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -49348,8 +49327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5318/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  36%|▎| 5318/14932 [07:33<13:40, 11.71it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  36%|▎| 5323/14932 [07:30<13:33, 11.81it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  36%|▎| 5323/14932 [07:30<13:33, 11.81it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -49357,8 +49336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5319/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  36%|▎| 5319/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  36%|▎| 5324/14932 [07:30<13:33, 11.81it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  36%|▎| 5324/14932 [07:30<13:33, 11.81it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -49366,8 +49345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5320/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  36%|▎| 5320/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  36%|▎| 5325/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  36%|▎| 5325/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -49375,8 +49354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5321/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  36%|▎| 5321/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  36%|▎| 5326/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  36%|▎| 5326/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -49384,8 +49363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5322/14932 [07:34<13:40, 11.71it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  36%|▎| 5322/14932 [07:34<13:40, 11.71it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  36%|▎| 5327/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  36%|▎| 5327/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -49393,8 +49372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5323/14932 [07:34<13:40, 11.71it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  36%|▎| 5323/14932 [07:34<13:40, 11.71it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  36%|▎| 5328/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  36%|▎| 5328/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -49402,8 +49381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5324/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  36%|▎| 5324/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  36%|▎| 5329/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  36%|▎| 5329/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -49411,8 +49390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5325/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  36%|▎| 5325/14932 [07:34<13:40, 11.72it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  36%|▎| 5330/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  36%|▎| 5330/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -49420,8 +49399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5326/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  36%|▎| 5326/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  36%|▎| 5331/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  36%|▎| 5331/14932 [07:31<13:33, 11.81it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -49429,8 +49408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5327/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  36%|▎| 5327/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=1.04"
+      "Epoch 0:  36%|▎| 5332/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  36%|▎| 5332/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -49438,8 +49417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5328/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=1.04\r",
-      "Epoch 0:  36%|▎| 5328/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  36%|▎| 5333/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  36%|▎| 5333/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -49447,8 +49426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5329/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  36%|▎| 5329/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  36%|▎| 5334/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  36%|▎| 5334/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -49456,8 +49435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5330/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  36%|▎| 5330/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  36%|▎| 5335/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  36%|▎| 5335/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -49465,8 +49444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5331/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  36%|▎| 5331/14932 [07:34<13:39, 11.72it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  36%|▎| 5336/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  36%|▎| 5336/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -49474,8 +49453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5332/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  36%|▎| 5332/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  36%|▎| 5337/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  36%|▎| 5337/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -49483,8 +49462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5333/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  36%|▎| 5333/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  36%|▎| 5338/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  36%|▎| 5338/14932 [07:31<13:32, 11.81it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -49492,8 +49471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5334/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  36%|▎| 5334/14932 [07:35<13:39, 11.72it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  36%|▎| 5339/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  36%|▎| 5339/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -49501,8 +49480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5335/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  36%|▎| 5335/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  36%|▎| 5340/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  36%|▎| 5340/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -49510,8 +49489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5336/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  36%|▎| 5336/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  36%|▎| 5341/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  36%|▎| 5341/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -49519,8 +49498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5337/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  36%|▎| 5337/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  36%|▎| 5342/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  36%|▎| 5342/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -49528,8 +49507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5338/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  36%|▎| 5338/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  36%|▎| 5343/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  36%|▎| 5343/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -49537,7 +49516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5339/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  36%|▎| 5344/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  36%|▎| 5344/14932 [07:32<13:32, 11.81it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -49545,7 +49525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5339/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  36%|▎| 5345/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  36%|▎| 5345/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -49553,8 +49534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5340/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  36%|▎| 5340/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  36%|▎| 5346/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  36%|▎| 5346/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -49562,8 +49543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5341/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  36%|▎| 5341/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  36%|▎| 5347/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  36%|▎| 5347/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -49571,8 +49552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5342/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  36%|▎| 5342/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  36%|▎| 5348/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  36%|▎| 5348/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -49580,8 +49561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5343/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  36%|▎| 5343/14932 [07:35<13:38, 11.72it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  36%|▎| 5349/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  36%|▎| 5349/14932 [07:32<13:31, 11.81it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -49589,8 +49570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5344/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  36%|▎| 5344/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  36%|▎| 5350/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  36%|▎| 5350/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -49598,8 +49579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5345/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  36%|▎| 5345/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  36%|▎| 5351/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  36%|▎| 5351/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -49607,8 +49588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5346/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  36%|▎| 5346/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  36%|▎| 5352/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  36%|▎| 5352/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -49616,8 +49597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5347/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  36%|▎| 5347/14932 [07:36<13:38, 11.72it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  36%|▎| 5353/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  36%|▎| 5353/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -49625,8 +49606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5348/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  36%|▎| 5348/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  36%|▎| 5354/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  36%|▎| 5354/14932 [07:33<13:31, 11.81it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -49634,8 +49615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5349/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  36%|▎| 5349/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  36%|▎| 5355/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  36%|▎| 5355/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -49643,8 +49624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5350/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  36%|▎| 5350/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  36%|▎| 5356/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  36%|▎| 5356/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -49652,8 +49633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5351/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  36%|▎| 5351/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  36%|▎| 5357/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  36%|▎| 5357/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -49661,8 +49642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5352/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  36%|▎| 5352/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  36%|▎| 5358/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  36%|▎| 5358/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -49670,8 +49651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5353/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  36%|▎| 5353/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  36%|▎| 5359/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  36%|▎| 5359/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -49679,8 +49660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5354/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  36%|▎| 5354/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  36%|▎| 5360/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  36%|▎| 5360/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -49688,8 +49669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5355/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  36%|▎| 5355/14932 [07:36<13:37, 11.72it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  36%|▎| 5361/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  36%|▎| 5361/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -49697,8 +49678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5356/14932 [07:37<13:37, 11.72it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  36%|▎| 5356/14932 [07:37<13:37, 11.72it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  36%|▎| 5362/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  36%|▎| 5362/14932 [07:33<13:30, 11.81it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -49706,8 +49687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5357/14932 [07:37<13:37, 11.72it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  36%|▎| 5357/14932 [07:37<13:37, 11.72it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  36%|▎| 5363/14932 [07:34<13:30, 11.81it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  36%|▎| 5363/14932 [07:34<13:30, 11.81it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -49715,8 +49696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5358/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  36%|▎| 5358/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  36%|▎| 5364/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  36%|▎| 5364/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -49724,8 +49705,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5359/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  36%|▎| 5359/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  36%|▎| 5365/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -49733,8 +49713,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5360/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  36%|▎| 5360/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  36%|▎| 5365/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -49742,8 +49721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5361/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  36%|▎| 5361/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  36%|▎| 5366/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  36%|▎| 5366/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -49751,8 +49730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5362/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  36%|▎| 5362/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  36%|▎| 5367/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  36%|▎| 5367/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -49760,8 +49739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5363/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  36%|▎| 5363/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  36%|▎| 5368/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  36%|▎| 5368/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -49769,8 +49748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5364/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  36%|▎| 5364/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  36%|▎| 5369/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  36%|▎| 5369/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -49778,8 +49757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5365/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  36%|▎| 5365/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  36%|▎| 5370/14932 [07:34<13:29, 11.82it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  36%|▎| 5370/14932 [07:34<13:29, 11.82it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -49787,8 +49766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5366/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  36%|▎| 5366/14932 [07:37<13:36, 11.72it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  36%|▎| 5371/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  36%|▎| 5371/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -49796,8 +49775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5367/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  36%|▎| 5367/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  36%|▎| 5372/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  36%|▎| 5372/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -49805,8 +49784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5368/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  36%|▎| 5368/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  36%|▎| 5373/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  36%|▎| 5373/14932 [07:34<13:29, 11.81it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -49814,8 +49793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5369/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  36%|▎| 5369/14932 [07:38<13:36, 11.72it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  36%|▎| 5374/14932 [07:34<13:28, 11.82it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  36%|▎| 5374/14932 [07:34<13:28, 11.82it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -49823,8 +49802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5370/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  36%|▎| 5370/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  36%|▎| 5375/14932 [07:34<13:28, 11.82it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  36%|▎| 5375/14932 [07:34<13:28, 11.82it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -49832,8 +49811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5371/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  36%|▎| 5371/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  36%|▎| 5376/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  36%|▎| 5376/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -49841,8 +49820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5372/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  36%|▎| 5372/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  36%|▎| 5377/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  36%|▎| 5377/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -49850,8 +49829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5373/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  36%|▎| 5373/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  36%|▎| 5378/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  36%|▎| 5378/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -49859,8 +49838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5374/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  36%|▎| 5374/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  36%|▎| 5379/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  36%|▎| 5379/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -49868,8 +49847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5375/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  36%|▎| 5375/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  36%|▎| 5380/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  36%|▎| 5380/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -49877,8 +49856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5376/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  36%|▎| 5376/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  36%|▎| 5381/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  36%|▎| 5381/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -49886,8 +49865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5377/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  36%|▎| 5377/14932 [07:38<13:35, 11.72it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  36%|▎| 5382/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  36%|▎| 5382/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -49895,8 +49874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5378/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  36%|▎| 5378/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  36%|▎| 5383/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  36%|▎| 5383/14932 [07:35<13:28, 11.81it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -49904,8 +49883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5379/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  36%|▎| 5379/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  36%|▎| 5384/14932 [07:35<13:28, 11.82it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  36%|▎| 5384/14932 [07:35<13:28, 11.82it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -49913,8 +49892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5380/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  36%|▎| 5380/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  36%|▎| 5385/14932 [07:35<13:28, 11.82it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  36%|▎| 5385/14932 [07:35<13:28, 11.82it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -49922,8 +49901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5381/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  36%|▎| 5381/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  36%|▎| 5386/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  36%|▎| 5386/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -49931,8 +49910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5382/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  36%|▎| 5382/14932 [07:39<13:35, 11.72it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  36%|▎| 5387/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  36%|▎| 5387/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -49940,8 +49919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5383/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  36%|▎| 5383/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  36%|▎| 5388/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  36%|▎| 5388/14932 [07:35<13:27, 11.82it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -49949,8 +49928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5384/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  36%|▎| 5384/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  36%|▎| 5389/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  36%|▎| 5389/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -49958,8 +49937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5385/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  36%|▎| 5385/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  36%|▎| 5390/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  36%|▎| 5390/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -49967,8 +49946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5386/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  36%|▎| 5386/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  36%|▎| 5391/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  36%|▎| 5391/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -49976,8 +49955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5387/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  36%|▎| 5387/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  36%|▎| 5392/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  36%|▎| 5392/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -49985,8 +49964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5388/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  36%|▎| 5388/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  36%|▎| 5393/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  36%|▎| 5393/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -49994,8 +49973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5389/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  36%|▎| 5389/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  36%|▎| 5394/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  36%|▎| 5394/14932 [07:36<13:27, 11.81it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -50003,8 +49982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5390/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  36%|▎| 5390/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  36%|▎| 5395/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  36%|▎| 5395/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -50012,8 +49991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5391/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  36%|▎| 5391/14932 [07:39<13:34, 11.72it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  36%|▎| 5396/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  36%|▎| 5396/14932 [07:36<13:27, 11.82it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -50021,8 +50000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5392/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  36%|▎| 5392/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.91"
+      "Epoch 0:  36%|▎| 5397/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  36%|▎| 5397/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -50030,8 +50009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5393/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.91\r",
-      "Epoch 0:  36%|▎| 5393/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  36%|▎| 5398/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  36%|▎| 5398/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -50039,8 +50018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5394/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  36%|▎| 5394/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  36%|▎| 5399/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  36%|▎| 5399/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -50048,8 +50027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5395/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  36%|▎| 5395/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  36%|▎| 5400/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  36%|▎| 5400/14932 [07:36<13:26, 11.82it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -50057,8 +50036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5396/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  36%|▎| 5396/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  36%|▎| 5401/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  36%|▎| 5401/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -50066,8 +50045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5397/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  36%|▎| 5397/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  36%|▎| 5402/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  36%|▎| 5402/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -50075,8 +50054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5398/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  36%|▎| 5398/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  36%|▎| 5403/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  36%|▎| 5403/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -50084,8 +50063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5399/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  36%|▎| 5399/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  36%|▎| 5404/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  36%|▎| 5404/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -50093,8 +50072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5400/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  36%|▎| 5400/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  36%|▎| 5405/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  36%|▎| 5405/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -50102,8 +50081,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5401/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  36%|▎| 5401/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  36%|▎| 5406/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -50111,8 +50089,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5402/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  36%|▎| 5402/14932 [07:40<13:33, 11.72it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  36%|▎| 5406/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -50120,8 +50097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5403/14932 [07:40<13:32, 11.72it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  36%|▎| 5403/14932 [07:40<13:32, 11.72it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  36%|▎| 5407/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  36%|▎| 5407/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -50129,8 +50106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5404/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  36%|▎| 5404/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  36%|▎| 5408/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  36%|▎| 5408/14932 [07:37<13:26, 11.82it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -50138,8 +50115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5405/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  36%|▎| 5405/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  36%|▎| 5409/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  36%|▎| 5409/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -50147,8 +50124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5406/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  36%|▎| 5406/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=1.10"
+      "Epoch 0:  36%|▎| 5410/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  36%|▎| 5410/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -50156,8 +50133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5407/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=1.10\r",
-      "Epoch 0:  36%|▎| 5407/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  36%|▎| 5411/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  36%|▎| 5411/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -50165,8 +50142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5408/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  36%|▎| 5408/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  36%|▎| 5412/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  36%|▎| 5412/14932 [07:37<13:25, 11.82it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -50174,8 +50151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5409/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  36%|▎| 5409/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:  36%|▎| 5413/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  36%|▎| 5413/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -50183,8 +50160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5410/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:  36%|▎| 5410/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  36%|▎| 5414/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  36%|▎| 5414/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -50192,8 +50169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5411/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  36%|▎| 5411/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  36%|▎| 5415/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  36%|▎| 5415/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -50201,8 +50178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5412/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  36%|▎| 5412/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  36%|▎| 5416/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  36%|▎| 5416/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -50210,8 +50187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5413/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  36%|▎| 5413/14932 [07:41<13:32, 11.72it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  36%|▎| 5417/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  36%|▎| 5417/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -50219,8 +50196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5414/14932 [07:41<13:31, 11.72it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  36%|▎| 5414/14932 [07:41<13:31, 11.72it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  36%|▎| 5418/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  36%|▎| 5418/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -50228,8 +50205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5415/14932 [07:41<13:31, 11.72it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  36%|▎| 5415/14932 [07:41<13:31, 11.72it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  36%|▎| 5419/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  36%|▎| 5419/14932 [07:38<13:25, 11.82it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -50237,8 +50214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5416/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  36%|▎| 5416/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  36%|▎| 5420/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  36%|▎| 5420/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -50246,8 +50223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5417/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  36%|▎| 5417/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  36%|▎| 5421/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  36%|▎| 5421/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -50255,8 +50232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5418/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  36%|▎| 5418/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  36%|▎| 5422/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  36%|▎| 5422/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -50264,8 +50241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5419/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  36%|▎| 5419/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  36%|▎| 5423/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  36%|▎| 5423/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -50273,8 +50250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5420/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  36%|▎| 5420/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  36%|▎| 5424/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  36%|▎| 5424/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -50282,8 +50259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5421/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  36%|▎| 5421/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  36%|▎| 5425/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  36%|▎| 5425/14932 [07:38<13:24, 11.82it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -50291,8 +50268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5422/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  36%|▎| 5422/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  36%|▎| 5426/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  36%|▎| 5426/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -50300,8 +50277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5423/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  36%|▎| 5423/14932 [07:42<13:31, 11.72it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  36%|▎| 5427/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  36%|▎| 5427/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -50309,8 +50286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5424/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  36%|▎| 5424/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  36%|▎| 5428/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  36%|▎| 5428/14932 [07:39<13:24, 11.82it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -50318,8 +50295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5425/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  36%|▎| 5425/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  36%|▎| 5429/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  36%|▎| 5429/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -50327,8 +50304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5426/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  36%|▎| 5426/14932 [07:42<13:30, 11.72it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  36%|▎| 5430/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  36%|▎| 5430/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -50336,8 +50313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5427/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  36%|▎| 5427/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  36%|▎| 5431/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  36%|▎| 5431/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -50345,8 +50322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5428/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  36%|▎| 5428/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  36%|▎| 5432/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  36%|▎| 5432/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -50354,8 +50331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5429/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  36%|▎| 5429/14932 [07:42<13:30, 11.73it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  36%|▎| 5433/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  36%|▎| 5433/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -50363,8 +50340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5430/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  36%|▎| 5430/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  36%|▎| 5434/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  36%|▎| 5434/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -50372,8 +50349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5431/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  36%|▎| 5431/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  36%|▎| 5435/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  36%|▎| 5435/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -50381,8 +50358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5432/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  36%|▎| 5432/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  36%|▎| 5436/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  36%|▎| 5436/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -50390,8 +50367,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5433/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  36%|▎| 5433/14932 [07:43<13:30, 11.73it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  36%|▎| 5437/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -50399,8 +50375,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5434/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  36%|▎| 5434/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  36%|▎| 5437/14932 [07:39<13:23, 11.82it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -50408,8 +50383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5435/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  36%|▎| 5435/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  36%|▎| 5438/14932 [07:39<13:22, 11.82it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  36%|▎| 5438/14932 [07:39<13:22, 11.82it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -50417,8 +50392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5436/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  36%|▎| 5436/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  36%|▎| 5439/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  36%|▎| 5439/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -50426,8 +50401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5437/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  36%|▎| 5437/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  36%|▎| 5440/14932 [07:40<13:23, 11.82it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  36%|▎| 5440/14932 [07:40<13:23, 11.82it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -50435,8 +50410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5438/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  36%|▎| 5438/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  36%|▎| 5441/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  36%|▎| 5441/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -50444,8 +50419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5439/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  36%|▎| 5439/14932 [07:43<13:29, 11.73it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  36%|▎| 5442/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  36%|▎| 5442/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -50453,8 +50428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5440/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  36%|▎| 5440/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  36%|▎| 5443/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  36%|▎| 5443/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -50462,8 +50437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5441/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  36%|▎| 5441/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  36%|▎| 5444/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  36%|▎| 5444/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -50471,8 +50446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5442/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  36%|▎| 5442/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  36%|▎| 5445/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  36%|▎| 5445/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -50480,8 +50455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5443/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  36%|▎| 5443/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  36%|▎| 5446/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  36%|▎| 5446/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -50489,8 +50464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5444/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  36%|▎| 5444/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  36%|▎| 5447/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  36%|▎| 5447/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -50498,8 +50473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5445/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  36%|▎| 5445/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  36%|▎| 5448/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  36%|▎| 5448/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -50507,8 +50482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5446/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  36%|▎| 5446/14932 [07:44<13:29, 11.72it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  36%|▎| 5449/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  36%|▎| 5449/14932 [07:40<13:22, 11.82it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -50516,8 +50491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5447/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  36%|▎| 5447/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  36%|▎| 5450/14932 [07:40<13:21, 11.82it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  36%|▎| 5450/14932 [07:40<13:21, 11.82it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -50525,8 +50500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5448/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  36%|▎| 5448/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  37%|▎| 5451/14932 [07:40<13:21, 11.82it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  37%|▎| 5451/14932 [07:40<13:21, 11.82it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -50534,8 +50509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5449/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  36%|▎| 5449/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  37%|▎| 5452/14932 [07:41<13:21, 11.82it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  37%|▎| 5452/14932 [07:41<13:21, 11.82it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -50543,8 +50518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  36%|▎| 5450/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  36%|▎| 5450/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  37%|▎| 5453/14932 [07:41<13:21, 11.82it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  37%|▎| 5453/14932 [07:41<13:21, 11.82it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -50552,8 +50527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5451/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  37%|▎| 5451/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  37%|▎| 5454/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  37%|▎| 5454/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -50561,8 +50536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5452/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  37%|▎| 5452/14932 [07:44<13:28, 11.73it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  37%|▎| 5455/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  37%|▎| 5455/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -50570,8 +50545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5453/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  37%|▎| 5453/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  37%|▎| 5456/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  37%|▎| 5456/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -50579,8 +50554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5454/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  37%|▎| 5454/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  37%|▎| 5457/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  37%|▎| 5457/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -50588,8 +50563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5455/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  37%|▎| 5455/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  37%|▎| 5458/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5458/14932 [07:41<13:21, 11.83it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -50597,8 +50572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5456/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  37%|▎| 5456/14932 [07:45<13:28, 11.73it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  37%|▎| 5459/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  37%|▎| 5459/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -50606,8 +50581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5457/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  37%|▎| 5457/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  37%|▎| 5460/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  37%|▎| 5460/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -50615,8 +50590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5458/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  37%|▎| 5458/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  37%|▎| 5461/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  37%|▎| 5461/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -50624,8 +50599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5459/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  37%|▎| 5459/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  37%|▎| 5462/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  37%|▎| 5462/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -50633,8 +50608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5460/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  37%|▎| 5460/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  37%|▎| 5463/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  37%|▎| 5463/14932 [07:41<13:20, 11.83it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -50642,8 +50617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5461/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  37%|▎| 5461/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  37%|▎| 5464/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  37%|▎| 5464/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -50651,8 +50626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5462/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  37%|▎| 5462/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  37%|▎| 5465/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  37%|▎| 5465/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -50660,8 +50635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5463/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  37%|▎| 5463/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  37%|▎| 5466/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  37%|▎| 5466/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=0.91"
      ]
     },
     {
@@ -50669,8 +50644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5464/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  37%|▎| 5464/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  37%|▎| 5467/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=0.91\r",
+      "Epoch 0:  37%|▎| 5467/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -50678,8 +50653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5465/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  37%|▎| 5465/14932 [07:45<13:27, 11.73it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  37%|▎| 5468/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  37%|▎| 5468/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -50687,8 +50662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5466/14932 [07:45<13:26, 11.73it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  37%|▎| 5466/14932 [07:45<13:26, 11.73it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  37%|▎| 5469/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  37%|▎| 5469/14932 [07:42<13:20, 11.83it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -50696,8 +50671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5467/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  37%|▎| 5467/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  37%|▎| 5470/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  37%|▎| 5470/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -50705,8 +50680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5468/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  37%|▎| 5468/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  37%|▎| 5471/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  37%|▎| 5471/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -50714,8 +50689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5469/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  37%|▎| 5469/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  37%|▎| 5472/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  37%|▎| 5472/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -50723,8 +50698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5470/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  37%|▎| 5470/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  37%|▎| 5473/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  37%|▎| 5473/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -50732,8 +50707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5471/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  37%|▎| 5471/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  37%|▎| 5474/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  37%|▎| 5474/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -50741,8 +50716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5472/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  37%|▎| 5472/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  37%|▎| 5475/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  37%|▎| 5475/14932 [07:42<13:19, 11.83it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -50750,8 +50725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5473/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  37%|▎| 5473/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  37%|▎| 5476/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  37%|▎| 5476/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -50759,8 +50734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5474/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  37%|▎| 5474/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  37%|▎| 5477/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  37%|▎| 5477/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -50768,8 +50743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5475/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  37%|▎| 5475/14932 [07:46<13:26, 11.73it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  37%|▎| 5478/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  37%|▎| 5478/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -50777,8 +50752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5476/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  37%|▎| 5476/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  37%|▎| 5479/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  37%|▎| 5479/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -50786,8 +50761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5477/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  37%|▎| 5477/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  37%|▎| 5480/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  37%|▎| 5480/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -50795,8 +50770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5478/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  37%|▎| 5478/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  37%|▎| 5481/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  37%|▎| 5481/14932 [07:43<13:19, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -50804,8 +50779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5479/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  37%|▎| 5479/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  37%|▎| 5482/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5482/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -50813,8 +50788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5480/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  37%|▎| 5480/14932 [07:47<13:26, 11.73it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  37%|▎| 5483/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  37%|▎| 5483/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -50822,8 +50797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5481/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  37%|▎| 5481/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  37%|▎| 5484/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  37%|▎| 5484/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -50831,8 +50806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5482/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  37%|▎| 5482/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  37%|▎| 5485/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  37%|▎| 5485/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -50840,8 +50815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5483/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  37%|▎| 5483/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  37%|▎| 5486/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  37%|▎| 5486/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -50849,8 +50824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5484/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  37%|▎| 5484/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  37%|▎| 5487/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  37%|▎| 5487/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -50858,8 +50833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5485/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  37%|▎| 5485/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  37%|▎| 5488/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  37%|▎| 5488/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -50867,8 +50842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5486/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  37%|▎| 5486/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  37%|▎| 5489/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  37%|▎| 5489/14932 [07:43<13:18, 11.83it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -50876,8 +50851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5487/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  37%|▎| 5487/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  37%|▎| 5490/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  37%|▎| 5490/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -50885,8 +50860,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5488/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  37%|▎| 5488/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  37%|▎| 5491/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -50894,8 +50868,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5489/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  37%|▎| 5489/14932 [07:47<13:25, 11.73it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  37%|▎| 5491/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -50903,8 +50876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5490/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  37%|▎| 5490/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  37%|▎| 5492/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  37%|▎| 5492/14932 [07:44<13:18, 11.83it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -50912,8 +50885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5491/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  37%|▎| 5491/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  37%|▎| 5493/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  37%|▎| 5493/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -50921,8 +50894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5492/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  37%|▎| 5492/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  37%|▎| 5494/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  37%|▎| 5494/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -50930,8 +50903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5493/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  37%|▎| 5493/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  37%|▎| 5495/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  37%|▎| 5495/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -50939,8 +50912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5494/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  37%|▎| 5494/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  37%|▎| 5496/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  37%|▎| 5496/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -50948,8 +50921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5495/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  37%|▎| 5495/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  37%|▎| 5497/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  37%|▎| 5497/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -50957,8 +50930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5496/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  37%|▎| 5496/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  37%|▎| 5498/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  37%|▎| 5498/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=1.00"
      ]
     },
     {
@@ -50966,8 +50939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5497/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  37%|▎| 5497/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  37%|▎| 5499/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=1.00\r",
+      "Epoch 0:  37%|▎| 5499/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -50975,8 +50948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5498/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  37%|▎| 5498/14932 [07:48<13:24, 11.73it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  37%|▎| 5500/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  37%|▎| 5500/14932 [07:44<13:17, 11.83it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -50984,8 +50957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5499/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  37%|▎| 5499/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  37%|▎| 5501/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  37%|▎| 5501/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -50993,8 +50966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5500/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  37%|▎| 5500/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  37%|▎| 5502/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  37%|▎| 5502/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -51002,8 +50975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5501/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  37%|▎| 5501/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  37%|▎| 5503/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  37%|▎| 5503/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -51011,8 +50984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5502/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  37%|▎| 5502/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  37%|▎| 5504/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  37%|▎| 5504/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -51020,8 +50993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5503/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  37%|▎| 5503/14932 [07:48<13:23, 11.73it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  37%|▎| 5505/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  37%|▎| 5505/14932 [07:45<13:17, 11.83it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -51029,8 +51002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5504/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  37%|▎| 5504/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  37%|▎| 5506/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  37%|▎| 5506/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -51038,8 +51011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5505/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  37%|▎| 5505/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  37%|▎| 5507/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  37%|▎| 5507/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=0.96"
      ]
     },
     {
@@ -51047,8 +51020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5506/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  37%|▎| 5506/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  37%|▎| 5508/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=0.96\r",
+      "Epoch 0:  37%|▎| 5508/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -51056,8 +51029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5507/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  37%|▎| 5507/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  37%|▎| 5509/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  37%|▎| 5509/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -51065,8 +51038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5508/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  37%|▎| 5508/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  37%|▎| 5510/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  37%|▎| 5510/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -51074,8 +51047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5509/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  37%|▎| 5509/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  37%|▎| 5511/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  37%|▎| 5511/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -51083,8 +51056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5510/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  37%|▎| 5510/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  37%|▎| 5512/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  37%|▎| 5512/14932 [07:45<13:16, 11.83it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -51092,8 +51065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5511/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  37%|▎| 5511/14932 [07:49<13:23, 11.73it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  37%|▎| 5513/14932 [07:46<13:16, 11.83it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  37%|▎| 5513/14932 [07:46<13:16, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -51101,8 +51074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5512/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  37%|▎| 5512/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  37%|▎| 5514/14932 [07:46<13:16, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5514/14932 [07:46<13:16, 11.83it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -51110,8 +51083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5513/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  37%|▎| 5513/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  37%|▎| 5515/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  37%|▎| 5515/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -51119,8 +51092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5514/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  37%|▎| 5514/14932 [07:49<13:22, 11.73it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  37%|▎| 5516/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  37%|▎| 5516/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -51128,8 +51101,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5515/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  37%|▎| 5515/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  37%|▎| 5517/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -51137,8 +51109,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5516/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  37%|▎| 5516/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  37%|▎| 5517/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -51146,8 +51117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5517/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  37%|▎| 5517/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  37%|▎| 5518/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  37%|▎| 5518/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -51155,8 +51126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5518/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  37%|▎| 5518/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  37%|▎| 5519/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  37%|▎| 5519/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -51164,8 +51135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5519/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  37%|▎| 5519/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  37%|▎| 5520/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  37%|▎| 5520/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -51173,8 +51144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5520/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  37%|▎| 5520/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  37%|▎| 5521/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  37%|▎| 5521/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -51182,8 +51153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5521/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  37%|▎| 5521/14932 [07:50<13:22, 11.73it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  37%|▎| 5522/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  37%|▎| 5522/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -51191,8 +51162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5522/14932 [07:50<13:21, 11.73it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  37%|▎| 5522/14932 [07:50<13:21, 11.73it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  37%|▎| 5523/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  37%|▎| 5523/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -51200,8 +51171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5523/14932 [07:50<13:21, 11.73it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  37%|▎| 5523/14932 [07:50<13:21, 11.73it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  37%|▎| 5524/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  37%|▎| 5524/14932 [07:46<13:15, 11.83it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -51209,8 +51180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5524/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  37%|▎| 5524/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  37%|▎| 5525/14932 [07:46<13:14, 11.83it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  37%|▎| 5525/14932 [07:46<13:14, 11.83it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -51218,8 +51189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5525/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  37%|▎| 5525/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  37%|▎| 5526/14932 [07:46<13:14, 11.83it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  37%|▎| 5526/14932 [07:46<13:14, 11.83it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -51227,7 +51198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5526/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  37%|▎| 5527/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  37%|▎| 5527/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -51235,7 +51207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5526/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  37%|▎| 5528/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  37%|▎| 5528/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -51243,8 +51216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5527/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  37%|▎| 5527/14932 [07:50<13:21, 11.74it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  37%|▎| 5529/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  37%|▎| 5529/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -51252,8 +51225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5528/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  37%|▎| 5528/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  37%|▎| 5530/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  37%|▎| 5530/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -51261,8 +51234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5529/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  37%|▎| 5529/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  37%|▎| 5531/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  37%|▎| 5531/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -51270,8 +51243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5530/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  37%|▎| 5530/14932 [07:51<13:21, 11.74it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  37%|▎| 5532/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  37%|▎| 5532/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -51279,8 +51252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5531/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  37%|▎| 5531/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  37%|▎| 5533/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  37%|▎| 5533/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -51288,8 +51261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5532/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  37%|▎| 5532/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  37%|▎| 5534/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  37%|▎| 5534/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -51297,8 +51270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5533/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  37%|▎| 5533/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  37%|▎| 5535/14932 [07:47<13:13, 11.84it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  37%|▎| 5535/14932 [07:47<13:13, 11.84it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -51306,8 +51279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5534/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  37%|▎| 5534/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  37%|▎| 5536/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  37%|▎| 5536/14932 [07:47<13:14, 11.83it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -51315,8 +51288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5535/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  37%|▎| 5535/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  37%|▎| 5537/14932 [07:47<13:13, 11.83it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  37%|▎| 5537/14932 [07:47<13:13, 11.83it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -51324,8 +51297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5536/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  37%|▎| 5536/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  37%|▎| 5538/14932 [07:47<13:13, 11.83it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  37%|▎| 5538/14932 [07:47<13:13, 11.83it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -51333,8 +51306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5537/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  37%|▎| 5537/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  37%|▎| 5539/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  37%|▎| 5539/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -51342,8 +51315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5538/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  37%|▎| 5538/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  37%|▎| 5540/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  37%|▎| 5540/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=5.00"
      ]
     },
     {
@@ -51351,8 +51324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5539/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  37%|▎| 5539/14932 [07:51<13:20, 11.74it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  37%|▎| 5541/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=5.00\r",
+      "Epoch 0:  37%|▎| 5541/14932 [07:48<13:13, 11.83it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -51360,8 +51333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5540/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  37%|▎| 5540/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  37%|▎| 5542/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  37%|▎| 5542/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -51369,8 +51342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5541/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  37%|▎| 5541/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  37%|▎| 5543/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  37%|▎| 5543/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -51378,8 +51351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5542/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  37%|▎| 5542/14932 [07:52<13:20, 11.74it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  37%|▎| 5544/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  37%|▎| 5544/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -51387,8 +51360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5543/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  37%|▎| 5543/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  37%|▎| 5545/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  37%|▎| 5545/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -51396,8 +51369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5544/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  37%|▎| 5544/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  37%|▎| 5546/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  37%|▎| 5546/14932 [07:48<13:13, 11.84it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -51405,8 +51378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5545/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  37%|▎| 5545/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  37%|▎| 5547/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  37%|▎| 5547/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -51414,8 +51387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5546/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  37%|▎| 5546/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=1.01"
+      "Epoch 0:  37%|▎| 5548/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  37%|▎| 5548/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -51423,8 +51396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5547/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=1.01\r",
-      "Epoch 0:  37%|▎| 5547/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  37%|▎| 5549/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  37%|▎| 5549/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -51432,8 +51405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5548/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  37%|▎| 5548/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  37%|▎| 5550/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  37%|▎| 5550/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -51441,8 +51414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5549/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  37%|▎| 5549/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  37%|▎| 5551/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  37%|▎| 5551/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -51450,8 +51423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5550/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  37%|▎| 5550/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  37%|▎| 5552/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  37%|▎| 5552/14932 [07:48<13:12, 11.84it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -51459,7 +51432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5551/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  37%|▎| 5553/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  37%|▎| 5553/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -51467,7 +51441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5551/14932 [07:52<13:19, 11.74it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  37%|▎| 5554/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  37%|▎| 5554/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -51475,8 +51450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5552/14932 [07:52<13:18, 11.74it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  37%|▎| 5552/14932 [07:52<13:18, 11.74it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  37%|▎| 5555/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  37%|▎| 5555/14932 [07:49<13:12, 11.84it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -51484,8 +51459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5553/14932 [07:52<13:18, 11.74it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  37%|▎| 5553/14932 [07:52<13:18, 11.74it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  37%|▎| 5556/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  37%|▎| 5556/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -51493,8 +51468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5554/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  37%|▎| 5554/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  37%|▎| 5557/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  37%|▎| 5557/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -51502,8 +51477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5555/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  37%|▎| 5555/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  37%|▎| 5558/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  37%|▎| 5558/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -51511,8 +51486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5556/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  37%|▎| 5556/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  37%|▎| 5559/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  37%|▎| 5559/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -51520,8 +51495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5557/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  37%|▎| 5557/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  37%|▎| 5560/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  37%|▎| 5560/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -51529,8 +51504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5558/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  37%|▎| 5558/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  37%|▎| 5561/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  37%|▎| 5561/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -51538,8 +51513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5559/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  37%|▎| 5559/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  37%|▎| 5562/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  37%|▎| 5562/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -51547,8 +51522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5560/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  37%|▎| 5560/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  37%|▎| 5563/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  37%|▎| 5563/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -51556,8 +51531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5561/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  37%|▎| 5561/14932 [07:53<13:18, 11.74it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  37%|▎| 5564/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  37%|▎| 5564/14932 [07:49<13:11, 11.84it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -51565,8 +51540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5562/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  37%|▎| 5562/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  37%|▎| 5565/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  37%|▎| 5565/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -51574,8 +51549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5563/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  37%|▎| 5563/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  37%|▎| 5566/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  37%|▎| 5566/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -51583,8 +51558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5564/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  37%|▎| 5564/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  37%|▎| 5567/14932 [07:50<13:10, 11.84it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  37%|▎| 5567/14932 [07:50<13:10, 11.84it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -51592,8 +51567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5565/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  37%|▎| 5565/14932 [07:53<13:17, 11.74it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  37%|▎| 5568/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:  37%|▎| 5568/14932 [07:50<13:11, 11.84it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -51601,8 +51576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5566/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  37%|▎| 5566/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  37%|▎| 5569/14932 [07:50<13:11, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  37%|▎| 5569/14932 [07:50<13:11, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -51610,8 +51585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5567/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  37%|▎| 5567/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  37%|▎| 5570/14932 [07:50<13:11, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5570/14932 [07:50<13:11, 11.83it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -51619,8 +51594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5568/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  37%|▎| 5568/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  37%|▎| 5571/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  37%|▎| 5571/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -51628,8 +51603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5569/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  37%|▎| 5569/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  37%|▎| 5572/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  37%|▎| 5572/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -51637,8 +51612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5570/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  37%|▎| 5570/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  37%|▎| 5573/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  37%|▎| 5573/14932 [07:50<13:10, 11.83it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -51646,8 +51621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5571/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  37%|▎| 5571/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  37%|▎| 5574/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  37%|▎| 5574/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -51655,8 +51630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5572/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  37%|▎| 5572/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  37%|▎| 5575/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  37%|▎| 5575/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -51664,8 +51639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5573/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  37%|▎| 5573/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  37%|▎| 5576/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  37%|▎| 5576/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -51673,8 +51648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5574/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  37%|▎| 5574/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  37%|▎| 5577/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  37%|▎| 5577/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -51682,8 +51657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5575/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  37%|▎| 5575/14932 [07:54<13:17, 11.74it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  37%|▎| 5578/14932 [07:51<13:10, 11.84it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  37%|▎| 5578/14932 [07:51<13:10, 11.84it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -51691,8 +51666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5576/14932 [07:55<13:17, 11.74it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  37%|▎| 5576/14932 [07:55<13:17, 11.74it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  37%|▎| 5579/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  37%|▎| 5579/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -51700,8 +51675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5577/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  37%|▎| 5577/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  37%|▎| 5580/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  37%|▎| 5580/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -51709,8 +51684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5578/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  37%|▎| 5578/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  37%|▎| 5581/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  37%|▎| 5581/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -51718,8 +51693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5579/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  37%|▎| 5579/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  37%|▎| 5582/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5582/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -51727,8 +51702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5580/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  37%|▎| 5580/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  37%|▎| 5583/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  37%|▎| 5583/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -51736,8 +51711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5581/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  37%|▎| 5581/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  37%|▎| 5584/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  37%|▎| 5584/14932 [07:51<13:10, 11.83it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -51745,8 +51720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5582/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  37%|▎| 5582/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  37%|▎| 5585/14932 [07:51<13:09, 11.83it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  37%|▎| 5585/14932 [07:51<13:09, 11.83it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -51754,8 +51729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5583/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  37%|▎| 5583/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  37%|▎| 5586/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  37%|▎| 5586/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -51763,8 +51738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5584/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  37%|▎| 5584/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  37%|▎| 5587/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  37%|▎| 5587/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -51772,8 +51747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5585/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  37%|▎| 5585/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  37%|▎| 5588/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  37%|▎| 5588/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -51781,8 +51756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5586/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  37%|▎| 5586/14932 [07:55<13:16, 11.74it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  37%|▎| 5589/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  37%|▎| 5589/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -51790,8 +51765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5587/14932 [07:55<13:15, 11.74it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  37%|▎| 5587/14932 [07:55<13:15, 11.74it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  37%|▎| 5590/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  37%|▎| 5590/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -51799,8 +51774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5588/14932 [07:55<13:15, 11.74it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  37%|▎| 5588/14932 [07:55<13:15, 11.74it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  37%|▎| 5591/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  37%|▎| 5591/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -51808,8 +51783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5589/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  37%|▎| 5589/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  37%|▎| 5592/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  37%|▎| 5592/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=1.04"
      ]
     },
     {
@@ -51817,8 +51792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5590/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  37%|▎| 5590/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  37%|▎| 5593/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=1.04\r",
+      "Epoch 0:  37%|▎| 5593/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -51826,8 +51801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5591/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  37%|▎| 5591/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  37%|▎| 5594/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  37%|▎| 5594/14932 [07:52<13:09, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -51835,8 +51810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5592/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  37%|▎| 5592/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  37%|▎| 5595/14932 [07:52<13:08, 11.84it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  37%|▎| 5595/14932 [07:52<13:08, 11.84it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -51844,8 +51819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5593/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  37%|▎| 5593/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  37%|▎| 5596/14932 [07:52<13:08, 11.83it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  37%|▎| 5596/14932 [07:52<13:08, 11.83it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -51853,8 +51828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5594/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  37%|▎| 5594/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  37%|▎| 5597/14932 [07:52<13:08, 11.83it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  37%|▎| 5597/14932 [07:52<13:08, 11.83it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -51862,8 +51837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5595/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  37%|▎| 5595/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  37%|▎| 5598/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  37%|▎| 5598/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -51871,8 +51846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5596/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  37%|▎| 5596/14932 [07:56<13:15, 11.74it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  37%|▎| 5599/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  37%|▎| 5599/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -51880,8 +51855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5597/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  37%|▎| 5597/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  38%|▍| 5600/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  38%|▍| 5600/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -51889,8 +51864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5598/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  37%|▎| 5598/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  38%|▍| 5601/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  38%|▍| 5601/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -51898,8 +51873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  37%|▎| 5599/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  37%|▎| 5599/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=1.67"
+      "Epoch 0:  38%|▍| 5602/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  38%|▍| 5602/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -51907,8 +51882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5600/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=1.67\r",
-      "Epoch 0:  38%|▍| 5600/14932 [07:56<13:14, 11.74it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  38%|▍| 5603/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  38%|▍| 5603/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -51916,8 +51891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5601/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  38%|▍| 5601/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  38%|▍| 5604/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  38%|▍| 5604/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -51925,8 +51900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5602/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  38%|▍| 5602/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  38%|▍| 5605/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  38%|▍| 5605/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -51934,8 +51909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5603/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  38%|▍| 5603/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  38%|▍| 5606/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  38%|▍| 5606/14932 [07:53<13:08, 11.83it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -51943,8 +51918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5604/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  38%|▍| 5604/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  38%|▍| 5607/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  38%|▍| 5607/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -51952,8 +51927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5605/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  38%|▍| 5605/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  38%|▍| 5608/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  38%|▍| 5608/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -51961,8 +51936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5606/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  38%|▍| 5606/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  38%|▍| 5609/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  38%|▍| 5609/14932 [07:53<13:07, 11.83it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -51970,8 +51945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5607/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  38%|▍| 5607/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  38%|▍| 5610/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  38%|▍| 5610/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -51979,8 +51954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5608/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  38%|▍| 5608/14932 [07:57<13:14, 11.74it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  38%|▍| 5611/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  38%|▍| 5611/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -51988,8 +51963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5609/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  38%|▍| 5609/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  38%|▍| 5612/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  38%|▍| 5612/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -51997,8 +51972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5610/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  38%|▍| 5610/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  38%|▍| 5613/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  38%|▍| 5613/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -52006,8 +51981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5611/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  38%|▍| 5611/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  38%|▍| 5614/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  38%|▍| 5614/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -52015,8 +51990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5612/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  38%|▍| 5612/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  38%|▍| 5615/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  38%|▍| 5615/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -52024,8 +51999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5613/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  38%|▍| 5613/14932 [07:57<13:13, 11.74it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  38%|▍| 5616/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  38%|▍| 5616/14932 [07:54<13:07, 11.84it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -52033,8 +52008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5614/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  38%|▍| 5614/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  38%|▍| 5617/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  38%|▍| 5617/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -52042,8 +52017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5615/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  38%|▍| 5615/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  38%|▍| 5618/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  38%|▍| 5618/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -52051,8 +52026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5616/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  38%|▍| 5616/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  38%|▍| 5619/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  38%|▍| 5619/14932 [07:54<13:07, 11.83it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -52060,8 +52035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5617/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  38%|▍| 5617/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  38%|▍| 5620/14932 [07:54<13:06, 11.83it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  38%|▍| 5620/14932 [07:54<13:06, 11.83it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -52069,8 +52044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5618/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  38%|▍| 5618/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  38%|▍| 5621/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  38%|▍| 5621/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -52078,8 +52053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5619/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  38%|▍| 5619/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  38%|▍| 5622/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  38%|▍| 5622/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -52087,8 +52062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5620/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  38%|▍| 5620/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  38%|▍| 5623/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  38%|▍| 5623/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -52096,8 +52071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5621/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  38%|▍| 5621/14932 [07:58<13:13, 11.74it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  38%|▍| 5624/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  38%|▍| 5624/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -52105,8 +52080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5622/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  38%|▍| 5622/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  38%|▍| 5625/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  38%|▍| 5625/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -52114,8 +52089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5623/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  38%|▍| 5623/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  38%|▍| 5626/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  38%|▍| 5626/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -52123,8 +52098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5624/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  38%|▍| 5624/14932 [07:58<13:12, 11.74it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  38%|▍| 5627/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  38%|▍| 5627/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -52132,8 +52107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5625/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  38%|▍| 5625/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.09"
+      "Epoch 0:  38%|▍| 5628/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  38%|▍| 5628/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -52141,8 +52116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5626/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.09\r",
-      "Epoch 0:  38%|▍| 5626/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  38%|▍| 5629/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  38%|▍| 5629/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -52150,8 +52125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5627/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  38%|▍| 5627/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  38%|▍| 5630/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  38%|▍| 5630/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -52159,8 +52134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5628/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  38%|▍| 5628/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.21"
+      "Epoch 0:  38%|▍| 5631/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  38%|▍| 5631/14932 [07:55<13:06, 11.83it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -52168,8 +52143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5629/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.21\r",
-      "Epoch 0:  38%|▍| 5629/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  38%|▍| 5632/14932 [07:56<13:06, 11.83it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  38%|▍| 5632/14932 [07:56<13:06, 11.83it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -52177,8 +52152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5630/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  38%|▍| 5630/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  38%|▍| 5633/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  38%|▍| 5633/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -52186,8 +52161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5631/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  38%|▍| 5631/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  38%|▍| 5634/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  38%|▍| 5634/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -52195,8 +52170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5632/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  38%|▍| 5632/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  38%|▍| 5635/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  38%|▍| 5635/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -52204,8 +52179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5633/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  38%|▍| 5633/14932 [07:59<13:12, 11.74it/s, v_num=o30c, train/loss=1.57"
+      "Epoch 0:  38%|▍| 5636/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  38%|▍| 5636/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -52213,8 +52188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5634/14932 [07:59<13:11, 11.74it/s, v_num=o30c, train/loss=1.57\r",
-      "Epoch 0:  38%|▍| 5634/14932 [07:59<13:11, 11.74it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  38%|▍| 5637/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  38%|▍| 5637/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -52222,8 +52197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5635/14932 [08:00<13:12, 11.74it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  38%|▍| 5635/14932 [08:00<13:12, 11.74it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  38%|▍| 5638/14932 [07:56<13:05, 11.82it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  38%|▍| 5638/14932 [07:56<13:05, 11.82it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -52231,8 +52206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5636/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  38%|▍| 5636/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  38%|▍| 5639/14932 [07:56<13:05, 11.82it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  38%|▍| 5639/14932 [07:56<13:05, 11.82it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -52240,8 +52215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5637/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  38%|▍| 5637/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  38%|▍| 5640/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  38%|▍| 5640/14932 [07:56<13:05, 11.83it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -52249,8 +52224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5638/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  38%|▍| 5638/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  38%|▍| 5641/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  38%|▍| 5641/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -52258,8 +52233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5639/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  38%|▍| 5639/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  38%|▍| 5642/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  38%|▍| 5642/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -52267,8 +52242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5640/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  38%|▍| 5640/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  38%|▍| 5643/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  38%|▍| 5643/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -52276,8 +52251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5641/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  38%|▍| 5641/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  38%|▍| 5644/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  38%|▍| 5644/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -52285,8 +52260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5642/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  38%|▍| 5642/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=0.84"
+      "Epoch 0:  38%|▍| 5645/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  38%|▍| 5645/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -52294,8 +52269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5643/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=0.84\r",
-      "Epoch 0:  38%|▍| 5643/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  38%|▍| 5646/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  38%|▍| 5646/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -52303,8 +52278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5644/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  38%|▍| 5644/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  38%|▍| 5647/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  38%|▍| 5647/14932 [07:57<13:05, 11.83it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -52312,8 +52287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5645/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  38%|▍| 5645/14932 [08:00<13:11, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  38%|▍| 5648/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  38%|▍| 5648/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -52321,8 +52296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5646/14932 [08:00<13:10, 11.74it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  38%|▍| 5646/14932 [08:00<13:10, 11.74it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  38%|▍| 5649/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  38%|▍| 5649/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -52330,8 +52305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5647/14932 [08:00<13:10, 11.74it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  38%|▍| 5647/14932 [08:00<13:10, 11.74it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  38%|▍| 5650/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  38%|▍| 5650/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -52339,8 +52314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5648/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  38%|▍| 5648/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  38%|▍| 5651/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  38%|▍| 5651/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -52348,8 +52323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5649/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  38%|▍| 5649/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  38%|▍| 5652/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  38%|▍| 5652/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -52357,8 +52332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5650/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  38%|▍| 5650/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=1.17"
+      "Epoch 0:  38%|▍| 5653/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  38%|▍| 5653/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -52366,8 +52341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5651/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=1.17\r",
-      "Epoch 0:  38%|▍| 5651/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  38%|▍| 5654/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  38%|▍| 5654/14932 [07:57<13:04, 11.83it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -52375,8 +52350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5652/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  38%|▍| 5652/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  38%|▍| 5655/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  38%|▍| 5655/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=0.82"
      ]
     },
     {
@@ -52384,8 +52359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5653/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  38%|▍| 5653/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  38%|▍| 5656/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=0.82\r",
+      "Epoch 0:  38%|▍| 5656/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -52393,8 +52368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5654/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  38%|▍| 5654/14932 [08:01<13:10, 11.74it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  38%|▍| 5657/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  38%|▍| 5657/14932 [07:58<13:04, 11.83it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -52402,8 +52377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5655/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  38%|▍| 5655/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  38%|▍| 5658/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  38%|▍| 5658/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -52411,8 +52386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5656/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  38%|▍| 5656/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  38%|▍| 5659/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  38%|▍| 5659/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -52420,8 +52395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5657/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  38%|▍| 5657/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  38%|▍| 5660/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  38%|▍| 5660/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -52429,8 +52404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5658/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  38%|▍| 5658/14932 [08:01<13:09, 11.74it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  38%|▍| 5661/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  38%|▍| 5661/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -52438,8 +52413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5659/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  38%|▍| 5659/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  38%|▍| 5662/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  38%|▍| 5662/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -52447,8 +52422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5660/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  38%|▍| 5660/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  38%|▍| 5663/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  38%|▍| 5663/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -52456,8 +52431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5661/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  38%|▍| 5661/14932 [08:01<13:09, 11.75it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  38%|▍| 5664/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  38%|▍| 5664/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -52465,8 +52440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5662/14932 [08:02<13:09, 11.75it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  38%|▍| 5662/14932 [08:02<13:09, 11.75it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  38%|▍| 5665/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  38%|▍| 5665/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -52474,8 +52449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5663/14932 [08:02<13:09, 11.75it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  38%|▍| 5663/14932 [08:02<13:09, 11.75it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  38%|▍| 5666/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  38%|▍| 5666/14932 [07:58<13:03, 11.83it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -52483,8 +52458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5664/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  38%|▍| 5664/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  38%|▍| 5667/14932 [07:59<13:03, 11.83it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  38%|▍| 5667/14932 [07:59<13:03, 11.83it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -52492,8 +52467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5665/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  38%|▍| 5665/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  38%|▍| 5668/14932 [07:59<13:03, 11.83it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  38%|▍| 5668/14932 [07:59<13:03, 11.83it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -52501,8 +52476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5666/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  38%|▍| 5666/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  38%|▍| 5669/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  38%|▍| 5669/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -52510,8 +52485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5667/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  38%|▍| 5667/14932 [08:02<13:09, 11.74it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  38%|▍| 5670/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  38%|▍| 5670/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -52519,8 +52494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5668/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  38%|▍| 5668/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  38%|▍| 5671/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  38%|▍| 5671/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -52528,8 +52503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5669/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  38%|▍| 5669/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  38%|▍| 5672/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  38%|▍| 5672/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -52537,8 +52512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5670/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  38%|▍| 5670/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  38%|▍| 5673/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  38%|▍| 5673/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -52546,8 +52521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5671/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  38%|▍| 5671/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  38%|▍| 5674/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  38%|▍| 5674/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -52555,8 +52530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5672/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  38%|▍| 5672/14932 [08:02<13:08, 11.74it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  38%|▍| 5675/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  38%|▍| 5675/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -52564,8 +52539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5673/14932 [08:03<13:08, 11.74it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  38%|▍| 5673/14932 [08:03<13:08, 11.74it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  38%|▍| 5676/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  38%|▍| 5676/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -52573,7 +52548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5674/14932 [08:03<13:08, 11.74it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  38%|▍| 5677/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  38%|▍| 5677/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -52581,7 +52557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5674/14932 [08:03<13:08, 11.74it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  38%|▍| 5678/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  38%|▍| 5678/14932 [07:59<13:02, 11.83it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -52589,8 +52566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5675/14932 [08:03<13:08, 11.75it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  38%|▍| 5675/14932 [08:03<13:08, 11.75it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  38%|▍| 5679/14932 [07:59<13:01, 11.83it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  38%|▍| 5679/14932 [07:59<13:01, 11.83it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -52598,8 +52575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5676/14932 [08:03<13:08, 11.75it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  38%|▍| 5676/14932 [08:03<13:08, 11.75it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  38%|▍| 5680/14932 [07:59<13:01, 11.83it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  38%|▍| 5680/14932 [07:59<13:01, 11.83it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -52607,8 +52584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5677/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  38%|▍| 5677/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  38%|▍| 5681/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  38%|▍| 5681/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -52616,8 +52593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5678/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  38%|▍| 5678/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  38%|▍| 5682/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  38%|▍| 5682/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -52625,8 +52602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5679/14932 [08:03<13:07, 11.74it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  38%|▍| 5679/14932 [08:03<13:07, 11.74it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  38%|▍| 5683/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  38%|▍| 5683/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -52634,8 +52611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5680/14932 [08:03<13:07, 11.74it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  38%|▍| 5680/14932 [08:03<13:07, 11.74it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  38%|▍| 5684/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  38%|▍| 5684/14932 [08:00<13:01, 11.83it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -52643,8 +52620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5681/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  38%|▍| 5681/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  38%|▍| 5685/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  38%|▍| 5685/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -52652,8 +52629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5682/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  38%|▍| 5682/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  38%|▍| 5686/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  38%|▍| 5686/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -52661,8 +52638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5683/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  38%|▍| 5683/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  38%|▍| 5687/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  38%|▍| 5687/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=0.58"
      ]
     },
     {
@@ -52670,8 +52647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5684/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  38%|▍| 5684/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  38%|▍| 5688/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=0.58\r",
+      "Epoch 0:  38%|▍| 5688/14932 [08:00<13:01, 11.84it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -52679,8 +52656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5685/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  38%|▍| 5685/14932 [08:03<13:07, 11.75it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  38%|▍| 5689/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  38%|▍| 5689/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -52688,8 +52665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5686/14932 [08:04<13:07, 11.75it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  38%|▍| 5686/14932 [08:04<13:07, 11.75it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  38%|▍| 5690/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  38%|▍| 5690/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -52697,8 +52674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5687/14932 [08:04<13:07, 11.75it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  38%|▍| 5687/14932 [08:04<13:07, 11.75it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  38%|▍| 5691/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  38%|▍| 5691/14932 [08:00<13:00, 11.84it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -52706,8 +52683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5688/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  38%|▍| 5688/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  38%|▍| 5692/14932 [08:00<13:00, 11.83it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  38%|▍| 5692/14932 [08:00<13:00, 11.83it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -52715,8 +52692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5689/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  38%|▍| 5689/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  38%|▍| 5693/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  38%|▍| 5693/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -52724,8 +52701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5690/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  38%|▍| 5690/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  38%|▍| 5694/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  38%|▍| 5694/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -52733,8 +52710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5691/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  38%|▍| 5691/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  38%|▍| 5695/14932 [08:01<13:00, 11.84it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  38%|▍| 5695/14932 [08:01<13:00, 11.84it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -52742,8 +52719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5692/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  38%|▍| 5692/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  38%|▍| 5696/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  38%|▍| 5696/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -52751,8 +52728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5693/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  38%|▍| 5693/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  38%|▍| 5697/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  38%|▍| 5697/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -52760,8 +52737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5694/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  38%|▍| 5694/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  38%|▍| 5698/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  38%|▍| 5698/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -52769,8 +52746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5695/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  38%|▍| 5695/14932 [08:04<13:06, 11.75it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  38%|▍| 5699/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  38%|▍| 5699/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -52778,8 +52755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5696/14932 [08:04<13:06, 11.74it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  38%|▍| 5696/14932 [08:04<13:06, 11.74it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  38%|▍| 5700/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  38%|▍| 5700/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -52787,8 +52764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5697/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  38%|▍| 5697/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  38%|▍| 5701/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  38%|▍| 5701/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -52796,8 +52773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5698/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  38%|▍| 5698/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  38%|▍| 5702/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  38%|▍| 5702/14932 [08:01<13:00, 11.83it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -52805,8 +52782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5699/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  38%|▍| 5699/14932 [08:05<13:06, 11.75it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  38%|▍| 5703/14932 [08:02<13:00, 11.83it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  38%|▍| 5703/14932 [08:02<13:00, 11.83it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -52814,8 +52791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5700/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  38%|▍| 5700/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  38%|▍| 5704/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  38%|▍| 5704/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -52823,8 +52800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5701/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  38%|▍| 5701/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  38%|▍| 5705/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  38%|▍| 5705/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -52832,8 +52809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5702/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  38%|▍| 5702/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  38%|▍| 5706/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  38%|▍| 5706/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -52841,8 +52818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5703/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  38%|▍| 5703/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  38%|▍| 5707/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  38%|▍| 5707/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -52850,8 +52827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5704/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  38%|▍| 5704/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  38%|▍| 5708/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  38%|▍| 5708/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -52859,8 +52836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5705/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  38%|▍| 5705/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  38%|▍| 5709/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  38%|▍| 5709/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -52868,8 +52845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5706/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  38%|▍| 5706/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  38%|▍| 5710/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  38%|▍| 5710/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -52877,8 +52854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5707/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  38%|▍| 5707/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  38%|▍| 5711/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  38%|▍| 5711/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -52886,8 +52863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5708/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  38%|▍| 5708/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  38%|▍| 5712/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  38%|▍| 5712/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -52895,8 +52872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5709/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  38%|▍| 5709/14932 [08:05<13:05, 11.75it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  38%|▍| 5713/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  38%|▍| 5713/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=0.91"
      ]
     },
     {
@@ -52904,8 +52881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5710/14932 [08:05<13:04, 11.75it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  38%|▍| 5710/14932 [08:05<13:04, 11.75it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  38%|▍| 5714/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=0.91\r",
+      "Epoch 0:  38%|▍| 5714/14932 [08:02<12:59, 11.83it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -52913,8 +52890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5711/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  38%|▍| 5711/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  38%|▍| 5715/14932 [08:02<12:58, 11.83it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  38%|▍| 5715/14932 [08:02<12:58, 11.83it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -52922,8 +52899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5712/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  38%|▍| 5712/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  38%|▍| 5716/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  38%|▍| 5716/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -52931,8 +52908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5713/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  38%|▍| 5713/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  38%|▍| 5717/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  38%|▍| 5717/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -52940,8 +52917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5714/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  38%|▍| 5714/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  38%|▍| 5718/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  38%|▍| 5718/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -52949,8 +52926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5715/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  38%|▍| 5715/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  38%|▍| 5719/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  38%|▍| 5719/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -52958,8 +52935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5716/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  38%|▍| 5716/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  38%|▍| 5720/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  38%|▍| 5720/14932 [08:03<12:58, 11.83it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -52967,8 +52944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5717/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  38%|▍| 5717/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  38%|▍| 5721/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  38%|▍| 5721/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -52976,8 +52953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5718/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  38%|▍| 5718/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  38%|▍| 5722/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  38%|▍| 5722/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -52985,8 +52962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5719/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  38%|▍| 5719/14932 [08:06<13:04, 11.75it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  38%|▍| 5723/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  38%|▍| 5723/14932 [08:03<12:58, 11.84it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -52994,8 +52971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5720/14932 [08:06<13:03, 11.75it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  38%|▍| 5720/14932 [08:06<13:03, 11.75it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  38%|▍| 5724/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  38%|▍| 5724/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -53003,8 +52980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5721/14932 [08:06<13:03, 11.75it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  38%|▍| 5721/14932 [08:06<13:03, 11.75it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  38%|▍| 5725/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  38%|▍| 5725/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -53012,8 +52989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5722/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  38%|▍| 5722/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  38%|▍| 5726/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  38%|▍| 5726/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -53021,8 +52998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5723/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  38%|▍| 5723/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  38%|▍| 5727/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  38%|▍| 5727/14932 [08:03<12:57, 11.84it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -53030,8 +53007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5724/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  38%|▍| 5724/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  38%|▍| 5728/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  38%|▍| 5728/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -53039,8 +53016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5725/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  38%|▍| 5725/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  38%|▍| 5729/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  38%|▍| 5729/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -53048,8 +53025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5726/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  38%|▍| 5726/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  38%|▍| 5730/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  38%|▍| 5730/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -53057,8 +53034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5727/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  38%|▍| 5727/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  38%|▍| 5731/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  38%|▍| 5731/14932 [08:04<12:57, 11.83it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -53066,8 +53043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5728/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  38%|▍| 5728/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  38%|▍| 5732/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  38%|▍| 5732/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -53075,8 +53052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5729/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  38%|▍| 5729/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  38%|▍| 5733/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  38%|▍| 5733/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -53084,8 +53061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5730/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  38%|▍| 5730/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  38%|▍| 5734/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  38%|▍| 5734/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -53093,8 +53070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5731/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  38%|▍| 5731/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  38%|▍| 5735/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  38%|▍| 5735/14932 [08:04<12:57, 11.84it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -53102,8 +53079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5732/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  38%|▍| 5732/14932 [08:07<13:03, 11.75it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  38%|▍| 5736/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  38%|▍| 5736/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=0.96"
      ]
     },
     {
@@ -53111,8 +53088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5733/14932 [08:08<13:03, 11.75it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  38%|▍| 5733/14932 [08:08<13:03, 11.75it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  38%|▍| 5737/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=0.96\r",
+      "Epoch 0:  38%|▍| 5737/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -53120,8 +53097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5734/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  38%|▍| 5734/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  38%|▍| 5738/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  38%|▍| 5738/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -53129,8 +53106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5735/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  38%|▍| 5735/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  38%|▍| 5739/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  38%|▍| 5739/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -53138,8 +53115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5736/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  38%|▍| 5736/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  38%|▍| 5740/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  38%|▍| 5740/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -53147,8 +53124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5737/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  38%|▍| 5737/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  38%|▍| 5741/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  38%|▍| 5741/14932 [08:04<12:56, 11.84it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -53156,8 +53133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5738/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  38%|▍| 5738/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  38%|▍| 5742/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  38%|▍| 5742/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -53165,8 +53142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5739/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  38%|▍| 5739/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  38%|▍| 5743/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  38%|▍| 5743/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -53174,8 +53151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5740/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  38%|▍| 5740/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  38%|▍| 5744/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  38%|▍| 5744/14932 [08:05<12:56, 11.84it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -53183,8 +53160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5741/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  38%|▍| 5741/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  38%|▍| 5745/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  38%|▍| 5745/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -53192,8 +53169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5742/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  38%|▍| 5742/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  38%|▍| 5746/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  38%|▍| 5746/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -53201,8 +53178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5743/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  38%|▍| 5743/14932 [08:08<13:02, 11.75it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  38%|▍| 5747/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  38%|▍| 5747/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -53210,8 +53187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5744/14932 [08:08<13:01, 11.75it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  38%|▍| 5744/14932 [08:08<13:01, 11.75it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  38%|▍| 5748/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  38%|▍| 5748/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -53219,8 +53196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5745/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  38%|▍| 5745/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  39%|▍| 5749/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  39%|▍| 5749/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -53228,8 +53205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5746/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  38%|▍| 5746/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  39%|▍| 5750/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  39%|▍| 5750/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -53237,8 +53214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5747/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  38%|▍| 5747/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  39%|▍| 5751/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  39%|▍| 5751/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -53246,8 +53223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  38%|▍| 5748/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  38%|▍| 5748/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  39%|▍| 5752/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  39%|▍| 5752/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -53255,8 +53232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5749/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  39%|▍| 5749/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  39%|▍| 5753/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  39%|▍| 5753/14932 [08:05<12:55, 11.84it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -53264,8 +53241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5750/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  39%|▍| 5750/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  39%|▍| 5754/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  39%|▍| 5754/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -53273,8 +53250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5751/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  39%|▍| 5751/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  39%|▍| 5755/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  39%|▍| 5755/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -53282,8 +53259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5752/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  39%|▍| 5752/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  39%|▍| 5756/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  39%|▍| 5756/14932 [08:06<12:55, 11.84it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -53291,8 +53268,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5753/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  39%|▍| 5753/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  39%|▍| 5757/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -53300,8 +53276,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5754/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  39%|▍| 5754/14932 [08:09<13:01, 11.75it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  39%|▍| 5757/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -53309,8 +53284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5755/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  39%|▍| 5755/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  39%|▍| 5758/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  39%|▍| 5758/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -53318,8 +53293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5756/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  39%|▍| 5756/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  39%|▍| 5759/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  39%|▍| 5759/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -53327,8 +53302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5757/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  39%|▍| 5757/14932 [08:09<13:00, 11.75it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  39%|▍| 5760/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  39%|▍| 5760/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -53336,8 +53311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5758/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  39%|▍| 5758/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  39%|▍| 5761/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  39%|▍| 5761/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -53345,8 +53320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5759/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  39%|▍| 5759/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  39%|▍| 5762/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  39%|▍| 5762/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -53354,8 +53329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5760/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  39%|▍| 5760/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  39%|▍| 5763/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  39%|▍| 5763/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -53363,8 +53338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5761/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  39%|▍| 5761/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  39%|▍| 5764/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  39%|▍| 5764/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -53372,8 +53347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5762/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  39%|▍| 5762/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  39%|▍| 5765/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  39%|▍| 5765/14932 [08:06<12:54, 11.84it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -53381,8 +53356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5763/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  39%|▍| 5763/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  39%|▍| 5766/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  39%|▍| 5766/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -53390,8 +53365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5764/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  39%|▍| 5764/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  39%|▍| 5767/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  39%|▍| 5767/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -53399,8 +53374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5765/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  39%|▍| 5765/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  39%|▍| 5768/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  39%|▍| 5768/14932 [08:07<12:54, 11.84it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -53408,8 +53383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5766/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  39%|▍| 5766/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  39%|▍| 5769/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  39%|▍| 5769/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -53417,8 +53392,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5767/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  39%|▍| 5767/14932 [08:10<13:00, 11.75it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  39%|▍| 5770/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -53426,8 +53400,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5768/14932 [08:10<12:59, 11.75it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  39%|▍| 5768/14932 [08:10<12:59, 11.75it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  39%|▍| 5770/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -53435,8 +53408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5769/14932 [08:10<12:59, 11.75it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  39%|▍| 5769/14932 [08:10<12:59, 11.75it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  39%|▍| 5771/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  39%|▍| 5771/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -53444,8 +53417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5770/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  39%|▍| 5770/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  39%|▍| 5772/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  39%|▍| 5772/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -53453,8 +53426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5771/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  39%|▍| 5771/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  39%|▍| 5773/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  39%|▍| 5773/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -53462,8 +53435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5772/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  39%|▍| 5772/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  39%|▍| 5774/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  39%|▍| 5774/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -53471,8 +53444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5773/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  39%|▍| 5773/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  39%|▍| 5775/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  39%|▍| 5775/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -53480,8 +53453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5774/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  39%|▍| 5774/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  39%|▍| 5776/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  39%|▍| 5776/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -53489,8 +53462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5775/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  39%|▍| 5775/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  39%|▍| 5777/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  39%|▍| 5777/14932 [08:07<12:53, 11.84it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -53498,8 +53471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5776/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  39%|▍| 5776/14932 [08:11<12:59, 11.75it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  39%|▍| 5778/14932 [08:07<12:52, 11.84it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  39%|▍| 5778/14932 [08:07<12:52, 11.84it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -53507,8 +53480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5777/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  39%|▍| 5777/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  39%|▍| 5779/14932 [08:07<12:52, 11.84it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  39%|▍| 5779/14932 [08:07<12:52, 11.84it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -53516,8 +53489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5778/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  39%|▍| 5778/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  39%|▍| 5780/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  39%|▍| 5780/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -53525,8 +53498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5779/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  39%|▍| 5779/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  39%|▍| 5781/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  39%|▍| 5781/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -53534,8 +53507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5780/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  39%|▍| 5780/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  39%|▍| 5782/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  39%|▍| 5782/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -53543,8 +53516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5781/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  39%|▍| 5781/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  39%|▍| 5783/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  39%|▍| 5783/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -53552,8 +53525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5782/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  39%|▍| 5782/14932 [08:11<12:58, 11.75it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  39%|▍| 5784/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  39%|▍| 5784/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -53561,8 +53534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5783/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  39%|▍| 5783/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  39%|▍| 5785/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  39%|▍| 5785/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -53570,8 +53543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5784/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  39%|▍| 5784/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  39%|▍| 5786/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  39%|▍| 5786/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -53579,8 +53552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5785/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  39%|▍| 5785/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  39%|▍| 5787/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  39%|▍| 5787/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -53588,8 +53561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5786/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  39%|▍| 5786/14932 [08:12<12:58, 11.75it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  39%|▍| 5788/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  39%|▍| 5788/14932 [08:08<12:52, 11.84it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -53597,8 +53570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5787/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  39%|▍| 5787/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  39%|▍| 5789/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  39%|▍| 5789/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -53606,8 +53579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5788/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  39%|▍| 5788/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  39%|▍| 5790/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  39%|▍| 5790/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -53615,8 +53588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5789/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  39%|▍| 5789/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  39%|▍| 5791/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  39%|▍| 5791/14932 [08:08<12:51, 11.84it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -53624,8 +53597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5790/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  39%|▍| 5790/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  39%|▍| 5792/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  39%|▍| 5792/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -53633,8 +53606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5791/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  39%|▍| 5791/14932 [08:12<12:57, 11.76it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  39%|▍| 5793/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  39%|▍| 5793/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -53642,8 +53615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5792/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  39%|▍| 5792/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  39%|▍| 5794/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  39%|▍| 5794/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -53651,8 +53624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5793/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  39%|▍| 5793/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  39%|▍| 5795/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  39%|▍| 5795/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -53660,8 +53633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5794/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  39%|▍| 5794/14932 [08:12<12:57, 11.75it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  39%|▍| 5796/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  39%|▍| 5796/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -53669,8 +53642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5795/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  39%|▍| 5795/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  39%|▍| 5797/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  39%|▍| 5797/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -53678,7 +53651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5796/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  39%|▍| 5798/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  39%|▍| 5798/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -53686,7 +53660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5796/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  39%|▍| 5799/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  39%|▍| 5799/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -53694,8 +53669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5797/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  39%|▍| 5797/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  39%|▍| 5800/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  39%|▍| 5800/14932 [08:09<12:51, 11.84it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -53703,8 +53678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5798/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  39%|▍| 5798/14932 [08:13<12:57, 11.75it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  39%|▍| 5801/14932 [08:09<12:50, 11.84it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  39%|▍| 5801/14932 [08:09<12:50, 11.84it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -53712,8 +53687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5799/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  39%|▍| 5799/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  39%|▍| 5802/14932 [08:09<12:50, 11.84it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  39%|▍| 5802/14932 [08:09<12:50, 11.84it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -53721,8 +53696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5800/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  39%|▍| 5800/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  39%|▍| 5803/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  39%|▍| 5803/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -53730,8 +53705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5801/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  39%|▍| 5801/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  39%|▍| 5804/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  39%|▍| 5804/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -53739,8 +53714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5802/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  39%|▍| 5802/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  39%|▍| 5805/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  39%|▍| 5805/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -53748,8 +53723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5803/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  39%|▍| 5803/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  39%|▍| 5806/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  39%|▍| 5806/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -53757,8 +53732,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5804/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  39%|▍| 5804/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  39%|▍| 5807/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -53766,8 +53740,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5805/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  39%|▍| 5805/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=0.62"
+      "Epoch 0:  39%|▍| 5807/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -53775,8 +53748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5806/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=0.62\r",
-      "Epoch 0:  39%|▍| 5806/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  39%|▍| 5808/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  39%|▍| 5808/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -53784,8 +53757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5807/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  39%|▍| 5807/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  39%|▍| 5809/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  39%|▍| 5809/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -53793,8 +53766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5808/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  39%|▍| 5808/14932 [08:13<12:56, 11.76it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  39%|▍| 5810/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  39%|▍| 5810/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -53802,8 +53775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5809/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  39%|▍| 5809/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  39%|▍| 5811/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  39%|▍| 5811/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -53811,8 +53784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5810/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  39%|▍| 5810/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  39%|▍| 5812/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  39%|▍| 5812/14932 [08:10<12:50, 11.84it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -53820,8 +53793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5811/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  39%|▍| 5811/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  39%|▍| 5813/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  39%|▍| 5813/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -53829,8 +53802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5812/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  39%|▍| 5812/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  39%|▍| 5814/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  39%|▍| 5814/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -53838,8 +53811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5813/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  39%|▍| 5813/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  39%|▍| 5815/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  39%|▍| 5815/14932 [08:10<12:49, 11.84it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -53847,8 +53820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5814/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  39%|▍| 5814/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  39%|▍| 5816/14932 [08:11<12:49, 11.85it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  39%|▍| 5816/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -53856,8 +53829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5815/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  39%|▍| 5815/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  39%|▍| 5817/14932 [08:11<12:49, 11.85it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  39%|▍| 5817/14932 [08:11<12:49, 11.85it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -53865,8 +53838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5816/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  39%|▍| 5816/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  39%|▍| 5818/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  39%|▍| 5818/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -53874,8 +53847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5817/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  39%|▍| 5817/14932 [08:14<12:55, 11.76it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  39%|▍| 5819/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  39%|▍| 5819/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -53883,8 +53856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5818/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  39%|▍| 5818/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  39%|▍| 5820/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  39%|▍| 5820/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -53892,8 +53865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5819/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  39%|▍| 5819/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  39%|▍| 5821/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  39%|▍| 5821/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -53901,8 +53874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5820/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  39%|▍| 5820/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  39%|▍| 5822/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  39%|▍| 5822/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -53910,8 +53883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5821/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  39%|▍| 5821/14932 [08:14<12:54, 11.76it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  39%|▍| 5823/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  39%|▍| 5823/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -53919,8 +53892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5822/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  39%|▍| 5822/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  39%|▍| 5824/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  39%|▍| 5824/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -53928,8 +53901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5823/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  39%|▍| 5823/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  39%|▍| 5825/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  39%|▍| 5825/14932 [08:11<12:49, 11.84it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -53937,8 +53910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5824/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  39%|▍| 5824/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  39%|▍| 5826/14932 [08:11<12:48, 11.84it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  39%|▍| 5826/14932 [08:11<12:48, 11.84it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -53946,8 +53919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5825/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  39%|▍| 5825/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  39%|▍| 5827/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  39%|▍| 5827/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -53955,8 +53928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5826/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  39%|▍| 5826/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  39%|▍| 5828/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  39%|▍| 5828/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -53964,8 +53937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5827/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  39%|▍| 5827/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  39%|▍| 5829/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  39%|▍| 5829/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -53973,8 +53946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5828/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  39%|▍| 5828/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  39%|▍| 5830/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  39%|▍| 5830/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -53982,8 +53955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5829/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  39%|▍| 5829/14932 [08:15<12:54, 11.76it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  39%|▍| 5831/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  39%|▍| 5831/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -53991,8 +53964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5830/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  39%|▍| 5830/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  39%|▍| 5832/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  39%|▍| 5832/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -54000,8 +53973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5831/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  39%|▍| 5831/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  39%|▍| 5833/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  39%|▍| 5833/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -54009,8 +53982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5832/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  39%|▍| 5832/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  39%|▍| 5834/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  39%|▍| 5834/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -54018,8 +53991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5833/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  39%|▍| 5833/14932 [08:15<12:53, 11.76it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  39%|▍| 5835/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  39%|▍| 5835/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -54027,8 +54000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5834/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  39%|▍| 5834/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  39%|▍| 5836/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  39%|▍| 5836/14932 [08:12<12:48, 11.84it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -54036,8 +54009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5835/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  39%|▍| 5835/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  39%|▍| 5837/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  39%|▍| 5837/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -54045,8 +54018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5836/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  39%|▍| 5836/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  39%|▍| 5838/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  39%|▍| 5838/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -54054,8 +54027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5837/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  39%|▍| 5837/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  39%|▍| 5839/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  39%|▍| 5839/14932 [08:12<12:47, 11.84it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -54063,8 +54036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5838/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  39%|▍| 5838/14932 [08:16<12:53, 11.76it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  39%|▍| 5840/14932 [08:13<12:47, 11.84it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  39%|▍| 5840/14932 [08:13<12:47, 11.84it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -54072,8 +54045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5839/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  39%|▍| 5839/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  39%|▍| 5841/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  39%|▍| 5841/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -54081,8 +54054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5840/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  39%|▍| 5840/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  39%|▍| 5842/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  39%|▍| 5842/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -54090,8 +54063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5841/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  39%|▍| 5841/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  39%|▍| 5843/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  39%|▍| 5843/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=0.92"
      ]
     },
     {
@@ -54099,8 +54072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5842/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  39%|▍| 5842/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  39%|▍| 5844/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=0.92\r",
+      "Epoch 0:  39%|▍| 5844/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -54108,8 +54081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5843/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  39%|▍| 5843/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  39%|▍| 5845/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  39%|▍| 5845/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -54117,7 +54090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5844/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  39%|▍| 5846/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  39%|▍| 5846/14932 [08:13<12:47, 11.85it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -54125,7 +54099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5844/14932 [08:16<12:52, 11.76it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  39%|▍| 5847/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  39%|▍| 5847/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -54133,8 +54108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5845/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  39%|▍| 5845/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  39%|▍| 5848/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  39%|▍| 5848/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -54142,8 +54117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5846/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  39%|▍| 5846/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  39%|▍| 5849/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  39%|▍| 5849/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -54151,8 +54126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5847/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  39%|▍| 5847/14932 [08:16<12:52, 11.77it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  39%|▍| 5850/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  39%|▍| 5850/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -54160,8 +54135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5848/14932 [08:17<12:52, 11.77it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  39%|▍| 5848/14932 [08:17<12:52, 11.77it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  39%|▍| 5851/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  39%|▍| 5851/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -54169,8 +54144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5849/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  39%|▍| 5849/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  39%|▍| 5852/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  39%|▍| 5852/14932 [08:13<12:46, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -54178,8 +54153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5850/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  39%|▍| 5850/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  39%|▍| 5853/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  39%|▍| 5853/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -54187,8 +54162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5851/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  39%|▍| 5851/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  39%|▍| 5854/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  39%|▍| 5854/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -54196,8 +54171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5852/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  39%|▍| 5852/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  39%|▍| 5855/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  39%|▍| 5855/14932 [08:14<12:46, 11.85it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -54205,8 +54180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5853/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  39%|▍| 5853/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  39%|▍| 5856/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  39%|▍| 5856/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -54214,8 +54189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5854/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  39%|▍| 5854/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  39%|▍| 5857/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  39%|▍| 5857/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -54223,8 +54198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5855/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  39%|▍| 5855/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  39%|▍| 5858/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  39%|▍| 5858/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -54232,8 +54207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5856/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  39%|▍| 5856/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  39%|▍| 5859/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  39%|▍| 5859/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -54241,8 +54216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5857/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  39%|▍| 5857/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  39%|▍| 5860/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  39%|▍| 5860/14932 [08:14<12:46, 11.84it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -54250,8 +54225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5858/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  39%|▍| 5858/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  39%|▍| 5861/14932 [08:14<12:45, 11.84it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  39%|▍| 5861/14932 [08:14<12:45, 11.84it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -54259,8 +54234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5859/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  39%|▍| 5859/14932 [08:17<12:51, 11.77it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  39%|▍| 5862/14932 [08:14<12:45, 11.84it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  39%|▍| 5862/14932 [08:14<12:45, 11.84it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -54268,8 +54243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5860/14932 [08:18<12:51, 11.77it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  39%|▍| 5860/14932 [08:18<12:51, 11.77it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  39%|▍| 5863/14932 [08:15<12:45, 11.84it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  39%|▍| 5863/14932 [08:15<12:45, 11.84it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -54277,8 +54252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5861/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  39%|▍| 5861/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  39%|▍| 5864/14932 [08:15<12:45, 11.84it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  39%|▍| 5864/14932 [08:15<12:45, 11.84it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -54286,8 +54261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5862/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  39%|▍| 5862/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  39%|▍| 5865/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  39%|▍| 5865/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -54295,8 +54270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5863/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  39%|▍| 5863/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  39%|▍| 5866/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  39%|▍| 5866/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -54304,8 +54279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5864/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  39%|▍| 5864/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  39%|▍| 5867/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  39%|▍| 5867/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -54313,8 +54288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5865/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  39%|▍| 5865/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  39%|▍| 5868/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  39%|▍| 5868/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -54322,8 +54297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5866/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  39%|▍| 5866/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  39%|▍| 5869/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  39%|▍| 5869/14932 [08:15<12:45, 11.85it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -54331,8 +54306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5867/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  39%|▍| 5867/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  39%|▍| 5870/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  39%|▍| 5870/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -54340,8 +54315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5868/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  39%|▍| 5868/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  39%|▍| 5871/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  39%|▍| 5871/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -54349,8 +54324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5869/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  39%|▍| 5869/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  39%|▍| 5872/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  39%|▍| 5872/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -54358,8 +54333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5870/14932 [08:18<12:49, 11.77it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  39%|▍| 5870/14932 [08:18<12:50, 11.77it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  39%|▍| 5873/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  39%|▍| 5873/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -54367,8 +54342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5871/14932 [08:18<12:49, 11.77it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  39%|▍| 5871/14932 [08:18<12:49, 11.77it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  39%|▍| 5874/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  39%|▍| 5874/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -54376,8 +54351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5872/14932 [08:18<12:49, 11.77it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  39%|▍| 5872/14932 [08:18<12:49, 11.77it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  39%|▍| 5875/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  39%|▍| 5875/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -54385,8 +54360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5873/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  39%|▍| 5873/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  39%|▍| 5876/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  39%|▍| 5876/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -54394,8 +54369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5874/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  39%|▍| 5874/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  39%|▍| 5877/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  39%|▍| 5877/14932 [08:15<12:44, 11.85it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -54403,8 +54378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5875/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  39%|▍| 5875/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  39%|▍| 5878/14932 [08:16<12:44, 11.85it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  39%|▍| 5878/14932 [08:16<12:44, 11.85it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -54412,8 +54387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5876/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  39%|▍| 5876/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  39%|▍| 5879/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  39%|▍| 5879/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -54421,8 +54396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5877/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  39%|▍| 5877/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  39%|▍| 5880/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  39%|▍| 5880/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -54430,8 +54405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5878/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  39%|▍| 5878/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  39%|▍| 5881/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  39%|▍| 5881/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -54439,8 +54414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5879/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  39%|▍| 5879/14932 [08:19<12:49, 11.77it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  39%|▍| 5882/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  39%|▍| 5882/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -54448,8 +54423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5880/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  39%|▍| 5880/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  39%|▍| 5883/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  39%|▍| 5883/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -54457,8 +54432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5881/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  39%|▍| 5881/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  39%|▍| 5884/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  39%|▍| 5884/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -54466,8 +54441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5882/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  39%|▍| 5882/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  39%|▍| 5885/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  39%|▍| 5885/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -54475,8 +54450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5883/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  39%|▍| 5883/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  39%|▍| 5886/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  39%|▍| 5886/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -54484,8 +54459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5884/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  39%|▍| 5884/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  39%|▍| 5887/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  39%|▍| 5887/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -54493,8 +54468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5885/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  39%|▍| 5885/14932 [08:19<12:48, 11.77it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  39%|▍| 5888/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  39%|▍| 5888/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -54502,8 +54477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5886/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  39%|▍| 5886/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  39%|▍| 5889/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  39%|▍| 5889/14932 [08:16<12:43, 11.85it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -54511,8 +54486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5887/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  39%|▍| 5887/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  39%|▍| 5890/14932 [08:17<12:43, 11.85it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  39%|▍| 5890/14932 [08:17<12:43, 11.85it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -54520,8 +54495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5888/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  39%|▍| 5888/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  39%|▍| 5891/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  39%|▍| 5891/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -54529,8 +54504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5889/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  39%|▍| 5889/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  39%|▍| 5892/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  39%|▍| 5892/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -54538,8 +54513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5890/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  39%|▍| 5890/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  39%|▍| 5893/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  39%|▍| 5893/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -54547,8 +54522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5891/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  39%|▍| 5891/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  39%|▍| 5894/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  39%|▍| 5894/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=0.83"
      ]
     },
     {
@@ -54556,8 +54531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5892/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  39%|▍| 5892/14932 [08:20<12:48, 11.77it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  39%|▍| 5895/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=0.83\r",
+      "Epoch 0:  39%|▍| 5895/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -54565,8 +54540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5893/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  39%|▍| 5893/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=6.41"
+      "Epoch 0:  39%|▍| 5896/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  39%|▍| 5896/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -54574,8 +54549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5894/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=6.41\r",
-      "Epoch 0:  39%|▍| 5894/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=1.56"
+      "Epoch 0:  39%|▍| 5897/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  39%|▍| 5897/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -54583,8 +54558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5895/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=1.56\r",
-      "Epoch 0:  39%|▍| 5895/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  39%|▍| 5898/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  39%|▍| 5898/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -54592,8 +54567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5896/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  39%|▍| 5896/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  40%|▍| 5899/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  40%|▍| 5899/14932 [08:17<12:42, 11.85it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -54601,8 +54576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5897/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  39%|▍| 5897/14932 [08:20<12:47, 11.77it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  40%|▍| 5900/14932 [08:17<12:41, 11.85it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  40%|▍| 5900/14932 [08:17<12:41, 11.85it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -54610,8 +54585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  39%|▍| 5898/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  39%|▍| 5898/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  40%|▍| 5901/14932 [08:17<12:41, 11.85it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  40%|▍| 5901/14932 [08:17<12:41, 11.85it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -54619,8 +54594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5899/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  40%|▍| 5899/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  40%|▍| 5902/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  40%|▍| 5902/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -54628,8 +54603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5900/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  40%|▍| 5900/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  40%|▍| 5903/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  40%|▍| 5903/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -54637,8 +54612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5901/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  40%|▍| 5901/14932 [08:21<12:47, 11.77it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  40%|▍| 5904/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  40%|▍| 5904/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -54646,8 +54621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5902/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  40%|▍| 5902/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  40%|▍| 5905/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  40%|▍| 5905/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -54655,8 +54630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5903/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  40%|▍| 5903/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  40%|▍| 5906/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  40%|▍| 5906/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -54664,8 +54639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5904/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  40%|▍| 5904/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  40%|▍| 5907/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  40%|▍| 5907/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -54673,8 +54648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5905/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  40%|▍| 5905/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  40%|▍| 5908/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  40%|▍| 5908/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -54682,8 +54657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5906/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  40%|▍| 5906/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  40%|▍| 5909/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  40%|▍| 5909/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -54691,8 +54666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5907/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  40%|▍| 5907/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  40%|▍| 5910/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  40%|▍| 5910/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -54700,8 +54675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5908/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  40%|▍| 5908/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  40%|▍| 5911/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  40%|▍| 5911/14932 [08:18<12:41, 11.85it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -54709,8 +54684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5909/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  40%|▍| 5909/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  40%|▍| 5912/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  40%|▍| 5912/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -54718,8 +54693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5910/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  40%|▍| 5910/14932 [08:21<12:46, 11.77it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  40%|▍| 5913/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  40%|▍| 5913/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -54727,8 +54702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5911/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  40%|▍| 5911/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  40%|▍| 5914/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  40%|▍| 5914/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -54736,8 +54711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5912/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  40%|▍| 5912/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  40%|▍| 5915/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  40%|▍| 5915/14932 [08:18<12:40, 11.85it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -54745,8 +54720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5913/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  40%|▍| 5913/14932 [08:22<12:46, 11.77it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  40%|▍| 5916/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  40%|▍| 5916/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -54754,8 +54729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5914/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  40%|▍| 5914/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  40%|▍| 5917/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  40%|▍| 5917/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -54763,8 +54738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5915/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  40%|▍| 5915/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  40%|▍| 5918/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  40%|▍| 5918/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -54772,8 +54747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5916/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  40%|▍| 5916/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  40%|▍| 5919/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  40%|▍| 5919/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -54781,8 +54756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5917/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  40%|▍| 5917/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  40%|▍| 5920/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  40%|▍| 5920/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -54790,8 +54765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5918/14932 [08:22<12:45, 11.78it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  40%|▍| 5918/14932 [08:22<12:45, 11.78it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  40%|▍| 5921/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  40%|▍| 5921/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -54799,8 +54774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5919/14932 [08:22<12:45, 11.78it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  40%|▍| 5919/14932 [08:22<12:45, 11.78it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  40%|▍| 5922/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  40%|▍| 5922/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -54808,8 +54783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5920/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  40%|▍| 5920/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  40%|▍| 5923/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  40%|▍| 5923/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -54817,8 +54792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5921/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  40%|▍| 5921/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  40%|▍| 5924/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  40%|▍| 5924/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -54826,8 +54801,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5922/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  40%|▍| 5922/14932 [08:22<12:45, 11.77it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  40%|▍| 5925/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -54835,8 +54809,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5923/14932 [08:23<12:45, 11.77it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  40%|▍| 5923/14932 [08:23<12:45, 11.77it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  40%|▍| 5925/14932 [08:19<12:40, 11.85it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -54844,8 +54817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5924/14932 [08:23<12:45, 11.77it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  40%|▍| 5924/14932 [08:23<12:45, 11.77it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  40%|▍| 5926/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  40%|▍| 5926/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -54853,8 +54826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5925/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  40%|▍| 5925/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  40%|▍| 5927/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  40%|▍| 5927/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -54862,7 +54835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5926/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  40%|▍| 5928/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  40%|▍| 5928/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -54870,7 +54844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5926/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  40%|▍| 5929/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  40%|▍| 5929/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -54878,8 +54853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5927/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  40%|▍| 5927/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  40%|▍| 5930/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  40%|▍| 5930/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -54887,8 +54862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5928/14932 [08:23<12:44, 11.78it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  40%|▍| 5928/14932 [08:23<12:44, 11.78it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  40%|▍| 5931/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  40%|▍| 5931/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -54896,8 +54871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5929/14932 [08:23<12:44, 11.78it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  40%|▍| 5929/14932 [08:23<12:44, 11.78it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  40%|▍| 5932/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  40%|▍| 5932/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -54905,7 +54880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5930/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  40%|▍| 5933/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  40%|▍| 5933/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -54913,7 +54889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5930/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  40%|▍| 5934/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  40%|▍| 5934/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -54921,8 +54898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5931/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  40%|▍| 5931/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  40%|▍| 5935/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  40%|▍| 5935/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -54930,8 +54907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5932/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  40%|▍| 5932/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  40%|▍| 5936/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  40%|▍| 5936/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -54939,8 +54916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5933/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  40%|▍| 5933/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  40%|▍| 5937/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  40%|▍| 5937/14932 [08:20<12:39, 11.85it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -54948,8 +54925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5934/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  40%|▍| 5934/14932 [08:23<12:44, 11.77it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  40%|▍| 5938/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  40%|▍| 5938/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -54957,8 +54934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5935/14932 [08:24<12:44, 11.77it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  40%|▍| 5935/14932 [08:24<12:44, 11.77it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  40%|▍| 5939/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  40%|▍| 5939/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -54966,8 +54943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5936/14932 [08:24<12:44, 11.77it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  40%|▍| 5936/14932 [08:24<12:44, 11.77it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  40%|▍| 5940/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  40%|▍| 5940/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -54975,8 +54952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5937/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  40%|▍| 5937/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  40%|▍| 5941/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  40%|▍| 5941/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -54984,8 +54961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5938/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  40%|▍| 5938/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  40%|▍| 5942/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  40%|▍| 5942/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -54993,8 +54970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5939/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  40%|▍| 5939/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  40%|▍| 5943/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  40%|▍| 5943/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -55002,8 +54979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5940/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  40%|▍| 5940/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  40%|▍| 5944/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  40%|▍| 5944/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -55011,8 +54988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5941/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  40%|▍| 5941/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  40%|▍| 5945/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  40%|▍| 5945/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -55020,8 +54997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5942/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  40%|▍| 5942/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  40%|▍| 5946/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  40%|▍| 5946/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -55029,8 +55006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5943/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  40%|▍| 5943/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  40%|▍| 5947/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  40%|▍| 5947/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -55038,8 +55015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5944/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  40%|▍| 5944/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  40%|▍| 5948/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  40%|▍| 5948/14932 [08:21<12:38, 11.85it/s, v_num=ui8w, train/loss=0.88"
      ]
     },
     {
@@ -55047,8 +55024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5945/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  40%|▍| 5945/14932 [08:24<12:43, 11.78it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  40%|▍| 5949/14932 [08:21<12:37, 11.85it/s, v_num=ui8w, train/loss=0.88\r",
+      "Epoch 0:  40%|▍| 5949/14932 [08:21<12:37, 11.85it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -55056,8 +55033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5946/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  40%|▍| 5946/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  40%|▍| 5950/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  40%|▍| 5950/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -55065,8 +55042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5947/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  40%|▍| 5947/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  40%|▍| 5951/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  40%|▍| 5951/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -55074,8 +55051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5948/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  40%|▍| 5948/14932 [08:24<12:42, 11.78it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  40%|▍| 5952/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  40%|▍| 5952/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -55083,8 +55060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5949/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  40%|▍| 5949/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  40%|▍| 5953/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  40%|▍| 5953/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -55092,8 +55069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5950/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  40%|▍| 5950/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  40%|▍| 5954/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  40%|▍| 5954/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -55101,8 +55078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5951/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  40%|▍| 5951/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  40%|▍| 5955/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  40%|▍| 5955/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -55110,8 +55087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5952/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  40%|▍| 5952/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  40%|▍| 5956/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  40%|▍| 5956/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -55119,8 +55096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5953/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  40%|▍| 5953/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  40%|▍| 5957/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  40%|▍| 5957/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -55128,8 +55105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5954/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  40%|▍| 5954/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  40%|▍| 5958/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  40%|▍| 5958/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -55137,8 +55114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5955/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  40%|▍| 5955/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  40%|▍| 5959/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  40%|▍| 5959/14932 [08:22<12:37, 11.85it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -55146,8 +55123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5956/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  40%|▍| 5956/14932 [08:25<12:42, 11.78it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  40%|▍| 5960/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  40%|▍| 5960/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -55155,8 +55132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5957/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  40%|▍| 5957/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  40%|▍| 5961/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  40%|▍| 5961/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -55164,8 +55141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5958/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  40%|▍| 5958/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  40%|▍| 5962/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  40%|▍| 5962/14932 [08:23<12:37, 11.85it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -55173,8 +55150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5959/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  40%|▍| 5959/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  40%|▍| 5963/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  40%|▍| 5963/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -55182,8 +55159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5960/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  40%|▍| 5960/14932 [08:25<12:41, 11.78it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  40%|▍| 5964/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  40%|▍| 5964/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -55191,8 +55168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5961/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  40%|▍| 5961/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  40%|▍| 5965/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  40%|▍| 5965/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -55200,8 +55177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5962/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  40%|▍| 5962/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  40%|▍| 5966/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  40%|▍| 5966/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -55209,8 +55186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5963/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  40%|▍| 5963/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  40%|▍| 5967/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  40%|▍| 5967/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -55218,8 +55195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5964/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  40%|▍| 5964/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  40%|▍| 5968/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  40%|▍| 5968/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -55227,8 +55204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5965/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  40%|▍| 5965/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  40%|▍| 5969/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  40%|▍| 5969/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -55236,8 +55213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5966/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  40%|▍| 5966/14932 [08:26<12:41, 11.78it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  40%|▍| 5970/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  40%|▍| 5970/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -55245,8 +55222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5967/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  40%|▍| 5967/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  40%|▍| 5971/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  40%|▍| 5971/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -55254,8 +55231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5968/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  40%|▍| 5968/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  40%|▍| 5972/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  40%|▍| 5972/14932 [08:23<12:36, 11.85it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -55263,8 +55240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5969/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  40%|▍| 5969/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  40%|▍| 5973/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  40%|▍| 5973/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -55272,8 +55249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5970/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  40%|▍| 5970/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  40%|▍| 5974/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  40%|▍| 5974/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -55281,8 +55258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5971/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  40%|▍| 5971/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  40%|▍| 5975/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  40%|▍| 5975/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -55290,8 +55267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5972/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  40%|▍| 5972/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  40%|▍| 5976/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  40%|▍| 5976/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -55299,8 +55276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5973/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  40%|▍| 5973/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  40%|▍| 5977/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  40%|▍| 5977/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -55308,8 +55285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5974/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  40%|▍| 5974/14932 [08:26<12:40, 11.78it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  40%|▍| 5978/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  40%|▍| 5978/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -55317,8 +55294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5975/14932 [08:27<12:40, 11.78it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  40%|▍| 5975/14932 [08:27<12:40, 11.78it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  40%|▍| 5979/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  40%|▍| 5979/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -55326,8 +55303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5976/14932 [08:27<12:40, 11.78it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  40%|▍| 5976/14932 [08:27<12:40, 11.78it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  40%|▍| 5980/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  40%|▍| 5980/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -55335,8 +55312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5977/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  40%|▍| 5977/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  40%|▍| 5981/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  40%|▍| 5981/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -55344,8 +55321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5978/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  40%|▍| 5978/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  40%|▍| 5982/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  40%|▍| 5982/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -55353,8 +55330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5979/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  40%|▍| 5979/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  40%|▍| 5983/14932 [08:24<12:34, 11.85it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  40%|▍| 5983/14932 [08:24<12:34, 11.85it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -55362,8 +55339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5980/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  40%|▍| 5980/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  40%|▍| 5984/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  40%|▍| 5984/14932 [08:24<12:35, 11.85it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -55371,8 +55348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5981/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  40%|▍| 5981/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  40%|▍| 5985/14932 [08:25<12:35, 11.85it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  40%|▍| 5985/14932 [08:25<12:35, 11.85it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -55380,8 +55357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5982/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  40%|▍| 5982/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  40%|▍| 5986/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  40%|▍| 5986/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -55389,8 +55366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5983/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  40%|▍| 5983/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  40%|▍| 5987/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  40%|▍| 5987/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=1.60"
      ]
     },
     {
@@ -55398,8 +55375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5984/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  40%|▍| 5984/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  40%|▍| 5988/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=1.60\r",
+      "Epoch 0:  40%|▍| 5988/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -55407,8 +55384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5985/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  40%|▍| 5985/14932 [08:27<12:39, 11.78it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  40%|▍| 5989/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  40%|▍| 5989/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -55416,8 +55393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5986/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  40%|▍| 5986/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  40%|▍| 5990/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  40%|▍| 5990/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -55425,8 +55402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5987/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  40%|▍| 5987/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  40%|▍| 5991/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  40%|▍| 5991/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -55434,8 +55411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5988/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  40%|▍| 5988/14932 [08:28<12:39, 11.78it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  40%|▍| 5992/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  40%|▍| 5992/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -55443,8 +55420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5989/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  40%|▍| 5989/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  40%|▍| 5993/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  40%|▍| 5993/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -55452,8 +55429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5990/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  40%|▍| 5990/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  40%|▍| 5994/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  40%|▍| 5994/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -55461,8 +55438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5991/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  40%|▍| 5991/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  40%|▍| 5995/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  40%|▍| 5995/14932 [08:25<12:34, 11.85it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -55470,8 +55447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5992/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  40%|▍| 5992/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  40%|▍| 5996/14932 [08:25<12:33, 11.85it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  40%|▍| 5996/14932 [08:25<12:33, 11.85it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -55479,8 +55456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5993/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  40%|▍| 5993/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  40%|▍| 5997/14932 [08:25<12:33, 11.85it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  40%|▍| 5997/14932 [08:25<12:33, 11.85it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -55488,8 +55465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5994/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  40%|▍| 5994/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  40%|▍| 5998/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  40%|▍| 5998/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -55497,8 +55474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5995/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  40%|▍| 5995/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  40%|▍| 5999/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  40%|▍| 5999/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -55506,8 +55483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5996/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  40%|▍| 5996/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  40%|▍| 6000/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  40%|▍| 6000/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -55515,8 +55492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5997/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  40%|▍| 5997/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  40%|▍| 6001/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  40%|▍| 6001/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -55524,8 +55501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5998/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  40%|▍| 5998/14932 [08:28<12:38, 11.78it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  40%|▍| 6002/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  40%|▍| 6002/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -55533,8 +55510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 5999/14932 [08:29<12:38, 11.78it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  40%|▍| 5999/14932 [08:29<12:38, 11.78it/s, v_num=o30c, train/loss=1.69"
+      "Epoch 0:  40%|▍| 6003/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  40%|▍| 6003/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -55542,8 +55519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6000/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.69\r",
-      "Epoch 0:  40%|▍| 6000/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  40%|▍| 6004/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  40%|▍| 6004/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -55551,8 +55528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6001/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  40%|▍| 6001/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  40%|▍| 6005/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  40%|▍| 6005/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -55560,8 +55537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6002/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  40%|▍| 6002/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  40%|▍| 6006/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  40%|▍| 6006/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -55569,8 +55546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6003/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  40%|▍| 6003/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  40%|▍| 6007/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  40%|▍| 6007/14932 [08:26<12:33, 11.85it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -55578,8 +55555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6004/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  40%|▍| 6004/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  40%|▍| 6008/14932 [08:26<12:32, 11.85it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  40%|▍| 6008/14932 [08:26<12:32, 11.85it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -55587,8 +55564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6005/14932 [08:29<12:37, 11.78it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  40%|▍| 6005/14932 [08:29<12:37, 11.78it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  40%|▍| 6009/14932 [08:26<12:32, 11.85it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  40%|▍| 6009/14932 [08:26<12:32, 11.85it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -55596,8 +55573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6006/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  40%|▍| 6006/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=0.88"
+      "Epoch 0:  40%|▍| 6010/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  40%|▍| 6010/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -55605,8 +55582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6007/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=0.88\r",
-      "Epoch 0:  40%|▍| 6007/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  40%|▍| 6011/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  40%|▍| 6011/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -55614,8 +55591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6008/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  40%|▍| 6008/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  40%|▍| 6012/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  40%|▍| 6012/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -55623,8 +55600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6009/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  40%|▍| 6009/14932 [08:29<12:37, 11.79it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  40%|▍| 6013/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  40%|▍| 6013/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -55632,8 +55609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6010/14932 [08:29<12:36, 11.79it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  40%|▍| 6010/14932 [08:29<12:36, 11.79it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  40%|▍| 6014/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  40%|▍| 6014/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -55641,8 +55618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6011/14932 [08:29<12:36, 11.79it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  40%|▍| 6011/14932 [08:29<12:36, 11.79it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  40%|▍| 6015/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  40%|▍| 6015/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -55650,8 +55627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6012/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  40%|▍| 6012/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  40%|▍| 6016/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  40%|▍| 6016/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -55659,8 +55636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6013/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  40%|▍| 6013/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  40%|▍| 6017/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  40%|▍| 6017/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -55668,8 +55645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6014/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  40%|▍| 6014/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  40%|▍| 6018/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  40%|▍| 6018/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -55677,8 +55654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6015/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  40%|▍| 6015/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  40%|▍| 6019/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  40%|▍| 6019/14932 [08:27<12:32, 11.85it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -55686,8 +55663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6016/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=0.89\r",
-      "Epoch 0:  40%|▍| 6016/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  40%|▍| 6020/14932 [08:27<12:31, 11.85it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  40%|▍| 6020/14932 [08:27<12:31, 11.85it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -55695,8 +55672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6017/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  40%|▍| 6017/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  40%|▍| 6021/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  40%|▍| 6021/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -55704,8 +55681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6018/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  40%|▍| 6018/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  40%|▍| 6022/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  40%|▍| 6022/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -55713,7 +55690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6019/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  40%|▍| 6023/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  40%|▍| 6023/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -55721,7 +55699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6019/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  40%|▍| 6024/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  40%|▍| 6024/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -55729,8 +55708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6020/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  40%|▍| 6020/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  40%|▍| 6025/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  40%|▍| 6025/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -55738,8 +55717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6021/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  40%|▍| 6021/14932 [08:30<12:36, 11.79it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  40%|▍| 6026/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  40%|▍| 6026/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -55747,8 +55726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6022/14932 [08:30<12:35, 11.79it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  40%|▍| 6022/14932 [08:30<12:35, 11.79it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  40%|▍| 6027/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  40%|▍| 6027/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -55756,8 +55735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6023/14932 [08:30<12:35, 11.79it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  40%|▍| 6023/14932 [08:30<12:35, 11.79it/s, v_num=o30c, train/loss=0.87"
+      "Epoch 0:  40%|▍| 6028/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  40%|▍| 6028/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -55765,8 +55744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6024/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=0.87\r",
-      "Epoch 0:  40%|▍| 6024/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  40%|▍| 6029/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  40%|▍| 6029/14932 [08:28<12:31, 11.85it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -55774,8 +55753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6025/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  40%|▍| 6025/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  40%|▍| 6030/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  40%|▍| 6030/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -55783,8 +55762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6026/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  40%|▍| 6026/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  40%|▍| 6031/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  40%|▍| 6031/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -55792,8 +55771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6027/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  40%|▍| 6027/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  40%|▍| 6032/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  40%|▍| 6032/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -55801,8 +55780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6028/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  40%|▍| 6028/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  40%|▍| 6033/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  40%|▍| 6033/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -55810,8 +55789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6029/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  40%|▍| 6029/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  40%|▍| 6034/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  40%|▍| 6034/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -55819,8 +55798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6030/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  40%|▍| 6030/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  40%|▍| 6035/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  40%|▍| 6035/14932 [08:28<12:30, 11.86it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -55828,8 +55807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6031/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  40%|▍| 6031/14932 [08:31<12:35, 11.79it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  40%|▍| 6036/14932 [08:29<12:30, 11.86it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  40%|▍| 6036/14932 [08:29<12:30, 11.86it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -55837,8 +55816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6032/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  40%|▍| 6032/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  40%|▍| 6037/14932 [08:29<12:30, 11.86it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  40%|▍| 6037/14932 [08:29<12:30, 11.86it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -55846,8 +55825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6033/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  40%|▍| 6033/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  40%|▍| 6038/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  40%|▍| 6038/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -55855,8 +55834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6034/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  40%|▍| 6034/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  40%|▍| 6039/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  40%|▍| 6039/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -55864,8 +55843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6035/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  40%|▍| 6035/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  40%|▍| 6040/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  40%|▍| 6040/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -55873,8 +55852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6036/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  40%|▍| 6036/14932 [08:31<12:34, 11.79it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  40%|▍| 6041/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  40%|▍| 6041/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -55882,8 +55861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6037/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  40%|▍| 6037/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  40%|▍| 6042/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  40%|▍| 6042/14932 [08:29<12:30, 11.85it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -55891,8 +55870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6038/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  40%|▍| 6038/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  40%|▍| 6043/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  40%|▍| 6043/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -55900,8 +55879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6039/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  40%|▍| 6039/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  40%|▍| 6044/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  40%|▍| 6044/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -55909,8 +55888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6040/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  40%|▍| 6040/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  40%|▍| 6045/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  40%|▍| 6045/14932 [08:29<12:29, 11.85it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -55918,8 +55897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6041/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  40%|▍| 6041/14932 [08:32<12:34, 11.79it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  40%|▍| 6046/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  40%|▍| 6046/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -55927,8 +55906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6042/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  40%|▍| 6042/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  40%|▍| 6047/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  40%|▍| 6047/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -55936,8 +55915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6043/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  40%|▍| 6043/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  41%|▍| 6048/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  41%|▍| 6048/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -55945,8 +55924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6044/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  40%|▍| 6044/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  41%|▍| 6049/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  41%|▍| 6049/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -55954,8 +55933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6045/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  40%|▍| 6045/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  41%|▍| 6050/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  41%|▍| 6050/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -55963,8 +55942,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6046/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  40%|▍| 6046/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  41%|▍| 6051/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -55972,8 +55950,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  40%|▍| 6047/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  40%|▍| 6047/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  41%|▍| 6051/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -55981,8 +55958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6048/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  41%|▍| 6048/14932 [08:32<12:33, 11.79it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  41%|▍| 6052/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  41%|▍| 6052/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -55990,8 +55967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6049/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  41%|▍| 6049/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  41%|▍| 6053/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  41%|▍| 6053/14932 [08:30<12:29, 11.85it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -55999,8 +55976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6050/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  41%|▍| 6050/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  41%|▍| 6054/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  41%|▍| 6054/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -56008,8 +55985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6051/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  41%|▍| 6051/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  41%|▍| 6055/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  41%|▍| 6055/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -56017,8 +55994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6052/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  41%|▍| 6052/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  41%|▍| 6056/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  41%|▍| 6056/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -56026,8 +56003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6053/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  41%|▍| 6053/14932 [08:33<12:33, 11.79it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  41%|▍| 6057/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  41%|▍| 6057/14932 [08:30<12:28, 11.85it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -56035,8 +56012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6054/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  41%|▍| 6054/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  41%|▍| 6058/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  41%|▍| 6058/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -56044,8 +56021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6055/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  41%|▍| 6055/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  41%|▍| 6059/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  41%|▍| 6059/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -56053,8 +56030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6056/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  41%|▍| 6056/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  41%|▍| 6060/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  41%|▍| 6060/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -56062,8 +56039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6057/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  41%|▍| 6057/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  41%|▍| 6061/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  41%|▍| 6061/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -56071,7 +56048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6058/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  41%|▍| 6062/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  41%|▍| 6062/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -56079,7 +56057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6058/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  41%|▍| 6063/14932 [08:31<12:28, 11.86it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  41%|▍| 6063/14932 [08:31<12:28, 11.86it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -56087,8 +56066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6059/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  41%|▍| 6059/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  41%|▍| 6064/14932 [08:31<12:28, 11.86it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  41%|▍| 6064/14932 [08:31<12:28, 11.86it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -56096,8 +56075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6060/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  41%|▍| 6060/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  41%|▍| 6065/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  41%|▍| 6065/14932 [08:31<12:28, 11.85it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -56105,8 +56084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6061/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  41%|▍| 6061/14932 [08:33<12:32, 11.79it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  41%|▍| 6066/14932 [08:31<12:27, 11.85it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  41%|▍| 6066/14932 [08:31<12:27, 11.85it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -56114,8 +56093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6062/14932 [08:34<12:32, 11.79it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  41%|▍| 6062/14932 [08:34<12:32, 11.79it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  41%|▍| 6067/14932 [08:31<12:27, 11.85it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  41%|▍| 6067/14932 [08:31<12:27, 11.85it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -56123,8 +56102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6063/14932 [08:34<12:32, 11.79it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  41%|▍| 6063/14932 [08:34<12:32, 11.79it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  41%|▍| 6068/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  41%|▍| 6068/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -56132,8 +56111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6064/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  41%|▍| 6064/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  41%|▍| 6069/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  41%|▍| 6069/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -56141,8 +56120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6065/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  41%|▍| 6065/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  41%|▍| 6070/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  41%|▍| 6070/14932 [08:31<12:27, 11.86it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -56150,8 +56129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6066/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  41%|▍| 6066/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  41%|▍| 6071/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  41%|▍| 6071/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -56159,8 +56138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6067/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  41%|▍| 6067/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  41%|▍| 6072/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  41%|▍| 6072/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -56168,7 +56147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6068/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  41%|▍| 6073/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  41%|▍| 6073/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -56176,7 +56156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6068/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  41%|▍| 6074/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  41%|▍| 6074/14932 [08:32<12:27, 11.86it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -56184,8 +56165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6069/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  41%|▍| 6069/14932 [08:34<12:31, 11.79it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  41%|▍| 6075/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  41%|▍| 6075/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -56193,8 +56174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6070/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  41%|▍| 6070/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  41%|▍| 6076/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  41%|▍| 6076/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -56202,8 +56183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6071/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  41%|▍| 6071/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  41%|▍| 6077/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  41%|▍| 6077/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -56211,8 +56192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6072/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  41%|▍| 6072/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  41%|▍| 6078/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  41%|▍| 6078/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -56220,8 +56201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6073/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  41%|▍| 6073/14932 [08:34<12:31, 11.80it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  41%|▍| 6079/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  41%|▍| 6079/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -56229,8 +56210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6074/14932 [08:34<12:30, 11.80it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  41%|▍| 6074/14932 [08:34<12:30, 11.80it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  41%|▍| 6080/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  41%|▍| 6080/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -56238,8 +56219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6075/14932 [08:34<12:30, 11.80it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  41%|▍| 6075/14932 [08:34<12:30, 11.80it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  41%|▍| 6081/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  41%|▍| 6081/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -56247,8 +56228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6076/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  41%|▍| 6076/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  41%|▍| 6082/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  41%|▍| 6082/14932 [08:32<12:26, 11.86it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -56256,8 +56237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6077/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  41%|▍| 6077/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  41%|▍| 6083/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  41%|▍| 6083/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -56265,8 +56246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6078/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  41%|▍| 6078/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=0.96"
+      "Epoch 0:  41%|▍| 6084/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  41%|▍| 6084/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -56274,8 +56255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6079/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=0.96\r",
-      "Epoch 0:  41%|▍| 6079/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  41%|▍| 6085/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  41%|▍| 6085/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -56283,8 +56264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6080/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  41%|▍| 6080/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  41%|▍| 6086/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  41%|▍| 6086/14932 [08:33<12:26, 11.86it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -56292,8 +56273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6081/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  41%|▍| 6081/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  41%|▍| 6087/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  41%|▍| 6087/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -56301,8 +56282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6082/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  41%|▍| 6082/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  41%|▍| 6088/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  41%|▍| 6088/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=5.03"
      ]
     },
     {
@@ -56310,8 +56291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6083/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  41%|▍| 6083/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  41%|▍| 6089/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=5.03\r",
+      "Epoch 0:  41%|▍| 6089/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -56319,8 +56300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6084/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  41%|▍| 6084/14932 [08:35<12:30, 11.80it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  41%|▍| 6090/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  41%|▍| 6090/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -56328,8 +56309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6085/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  41%|▍| 6085/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  41%|▍| 6091/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  41%|▍| 6091/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -56337,8 +56318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6086/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  41%|▍| 6086/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  41%|▍| 6092/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  41%|▍| 6092/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -56346,8 +56327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6087/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  41%|▍| 6087/14932 [08:35<12:29, 11.80it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  41%|▍| 6093/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  41%|▍| 6093/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -56355,8 +56336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6088/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  41%|▍| 6088/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  41%|▍| 6094/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  41%|▍| 6094/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -56364,8 +56345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6089/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  41%|▍| 6089/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  41%|▍| 6095/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  41%|▍| 6095/14932 [08:33<12:25, 11.86it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -56373,8 +56354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6090/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  41%|▍| 6090/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  41%|▍| 6096/14932 [08:34<12:25, 11.86it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  41%|▍| 6096/14932 [08:34<12:25, 11.86it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -56382,8 +56363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6091/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  41%|▍| 6091/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  41%|▍| 6097/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  41%|▍| 6097/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -56391,8 +56372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6092/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  41%|▍| 6092/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  41%|▍| 6098/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  41%|▍| 6098/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -56400,8 +56381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6093/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  41%|▍| 6093/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  41%|▍| 6099/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  41%|▍| 6099/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -56409,8 +56390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6094/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  41%|▍| 6094/14932 [08:36<12:29, 11.80it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  41%|▍| 6100/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  41%|▍| 6100/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=0.94"
      ]
     },
     {
@@ -56418,8 +56399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6095/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  41%|▍| 6095/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  41%|▍| 6101/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=0.94\r",
+      "Epoch 0:  41%|▍| 6101/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -56427,8 +56408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6096/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  41%|▍| 6096/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  41%|▍| 6102/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  41%|▍| 6102/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -56436,8 +56417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6097/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  41%|▍| 6097/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  41%|▍| 6103/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  41%|▍| 6103/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -56445,8 +56426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6098/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  41%|▍| 6098/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  41%|▍| 6104/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  41%|▍| 6104/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -56454,8 +56435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6099/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  41%|▍| 6099/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  41%|▍| 6105/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  41%|▍| 6105/14932 [08:34<12:24, 11.86it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -56463,8 +56444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6100/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  41%|▍| 6100/14932 [08:36<12:28, 11.80it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  41%|▍| 6106/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  41%|▍| 6106/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -56472,8 +56453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6101/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  41%|▍| 6101/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  41%|▍| 6107/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  41%|▍| 6107/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -56481,8 +56462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6102/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  41%|▍| 6102/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  41%|▍| 6108/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  41%|▍| 6108/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -56490,8 +56471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6103/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  41%|▍| 6103/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  41%|▍| 6109/14932 [08:34<12:23, 11.87it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  41%|▍| 6109/14932 [08:34<12:23, 11.86it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -56499,8 +56480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6104/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  41%|▍| 6104/14932 [08:37<12:28, 11.80it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  41%|▍| 6110/14932 [08:34<12:23, 11.87it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  41%|▍| 6110/14932 [08:34<12:23, 11.87it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -56508,8 +56489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6105/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  41%|▍| 6105/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  41%|▍| 6111/14932 [08:35<12:23, 11.87it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  41%|▍| 6111/14932 [08:35<12:23, 11.87it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -56517,8 +56498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6106/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  41%|▍| 6106/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  41%|▍| 6112/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  41%|▍| 6112/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -56526,8 +56507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6107/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  41%|▍| 6107/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  41%|▍| 6113/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  41%|▍| 6113/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -56535,8 +56516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6108/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  41%|▍| 6108/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  41%|▍| 6114/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  41%|▍| 6114/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -56544,8 +56525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6109/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  41%|▍| 6109/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  41%|▍| 6115/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  41%|▍| 6115/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -56553,8 +56534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6110/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  41%|▍| 6110/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  41%|▍| 6116/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  41%|▍| 6116/14932 [08:35<12:23, 11.86it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -56562,8 +56543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6111/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  41%|▍| 6111/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  41%|▍| 6117/14932 [08:35<12:22, 11.86it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  41%|▍| 6117/14932 [08:35<12:22, 11.86it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -56571,8 +56552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6112/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  41%|▍| 6112/14932 [08:37<12:27, 11.80it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  41%|▍| 6118/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  41%|▍| 6118/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -56580,8 +56561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6113/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  41%|▍| 6113/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  41%|▍| 6119/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  41%|▍| 6119/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -56589,8 +56570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6114/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  41%|▍| 6114/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  41%|▍| 6120/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  41%|▍| 6120/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -56598,8 +56579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6115/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  41%|▍| 6115/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  41%|▍| 6121/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  41%|▍| 6121/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -56607,8 +56588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6116/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  41%|▍| 6116/14932 [08:38<12:27, 11.80it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  41%|▍| 6122/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  41%|▍| 6122/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -56616,8 +56597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6117/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  41%|▍| 6117/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  41%|▍| 6123/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  41%|▍| 6123/14932 [08:35<12:22, 11.87it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -56625,8 +56606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6118/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  41%|▍| 6118/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  41%|▍| 6124/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  41%|▍| 6124/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -56634,8 +56615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6119/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  41%|▍| 6119/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  41%|▍| 6125/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  41%|▍| 6125/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -56643,8 +56624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6120/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  41%|▍| 6120/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  41%|▍| 6126/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  41%|▍| 6126/14932 [08:36<12:22, 11.87it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -56652,8 +56633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6121/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  41%|▍| 6121/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  41%|▍| 6127/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  41%|▍| 6127/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -56661,8 +56642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6122/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  41%|▍| 6122/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  41%|▍| 6128/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  41%|▍| 6128/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -56670,8 +56651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6123/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  41%|▍| 6123/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=0.55"
+      "Epoch 0:  41%|▍| 6129/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  41%|▍| 6129/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -56679,8 +56660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6124/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=0.55\r",
-      "Epoch 0:  41%|▍| 6124/14932 [08:38<12:26, 11.80it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  41%|▍| 6130/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  41%|▍| 6130/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -56688,8 +56669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6125/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  41%|▍| 6125/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  41%|▍| 6131/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  41%|▍| 6131/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -56697,8 +56678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6126/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  41%|▍| 6126/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  41%|▍| 6132/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  41%|▍| 6132/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -56706,8 +56687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6127/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  41%|▍| 6127/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  41%|▍| 6133/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  41%|▍| 6133/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -56715,8 +56696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6128/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  41%|▍| 6128/14932 [08:39<12:26, 11.80it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  41%|▍| 6134/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  41%|▍| 6134/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -56724,8 +56705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6129/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  41%|▍| 6129/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  41%|▍| 6135/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  41%|▍| 6135/14932 [08:36<12:21, 11.87it/s, v_num=ui8w, train/loss=1.05"
      ]
     },
     {
@@ -56733,8 +56714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6130/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  41%|▍| 6130/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  41%|▍| 6136/14932 [08:37<12:21, 11.87it/s, v_num=ui8w, train/loss=1.05\r",
+      "Epoch 0:  41%|▍| 6136/14932 [08:37<12:21, 11.87it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -56742,8 +56723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6131/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  41%|▍| 6131/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  41%|▍| 6137/14932 [08:37<12:21, 11.87it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  41%|▍| 6137/14932 [08:37<12:21, 11.87it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -56751,8 +56732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6132/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  41%|▍| 6132/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  41%|▍| 6138/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  41%|▍| 6138/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -56760,8 +56741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6133/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  41%|▍| 6133/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  41%|▍| 6139/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  41%|▍| 6139/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -56769,8 +56750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6134/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  41%|▍| 6134/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=1.67"
+      "Epoch 0:  41%|▍| 6140/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  41%|▍| 6140/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -56778,8 +56759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6135/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=1.67\r",
-      "Epoch 0:  41%|▍| 6135/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  41%|▍| 6141/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  41%|▍| 6141/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -56787,8 +56768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6136/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  41%|▍| 6136/14932 [08:39<12:25, 11.80it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  41%|▍| 6142/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  41%|▍| 6142/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=1.10"
      ]
     },
     {
@@ -56796,8 +56777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6137/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  41%|▍| 6137/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  41%|▍| 6143/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=1.10\r",
+      "Epoch 0:  41%|▍| 6143/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -56805,8 +56786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6138/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  41%|▍| 6138/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  41%|▍| 6144/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  41%|▍| 6144/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -56814,8 +56795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6139/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  41%|▍| 6139/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  41%|▍| 6145/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  41%|▍| 6145/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -56823,8 +56804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6140/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  41%|▍| 6140/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  41%|▍| 6146/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  41%|▍| 6146/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -56832,8 +56813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6141/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  41%|▍| 6141/14932 [08:40<12:25, 11.80it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  41%|▍| 6147/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  41%|▍| 6147/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -56841,8 +56822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6142/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  41%|▍| 6142/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  41%|▍| 6148/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  41%|▍| 6148/14932 [08:37<12:20, 11.87it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -56850,8 +56831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6143/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  41%|▍| 6143/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  41%|▍| 6149/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  41%|▍| 6149/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -56859,7 +56840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6144/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  41%|▍| 6150/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  41%|▍| 6150/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -56867,7 +56849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6144/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  41%|▍| 6151/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  41%|▍| 6151/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -56875,8 +56858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6145/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  41%|▍| 6145/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  41%|▍| 6152/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  41%|▍| 6152/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -56884,8 +56867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6146/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  41%|▍| 6146/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  41%|▍| 6153/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  41%|▍| 6153/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -56893,8 +56876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6147/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  41%|▍| 6147/14932 [08:40<12:24, 11.80it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  41%|▍| 6154/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  41%|▍| 6154/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -56902,8 +56885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6148/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  41%|▍| 6148/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  41%|▍| 6155/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  41%|▍| 6155/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -56911,8 +56894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6149/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  41%|▍| 6149/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  41%|▍| 6156/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  41%|▍| 6156/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -56920,8 +56903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6150/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  41%|▍| 6150/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  41%|▍| 6157/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  41%|▍| 6157/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -56929,8 +56912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6151/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  41%|▍| 6151/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  41%|▍| 6158/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  41%|▍| 6158/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -56938,8 +56921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6152/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  41%|▍| 6152/14932 [08:41<12:24, 11.80it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  41%|▍| 6159/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  41%|▍| 6159/14932 [08:38<12:19, 11.87it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -56947,8 +56930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6153/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  41%|▍| 6153/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  41%|▍| 6160/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  41%|▍| 6160/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -56956,8 +56939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6154/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  41%|▍| 6154/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  41%|▍| 6161/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  41%|▍| 6161/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -56965,8 +56948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6155/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  41%|▍| 6155/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=1.06"
+      "Epoch 0:  41%|▍| 6162/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  41%|▍| 6162/14932 [08:39<12:19, 11.87it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -56974,8 +56957,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6156/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=1.06\r",
-      "Epoch 0:  41%|▍| 6156/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  41%|▍| 6163/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -56983,8 +56965,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6157/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  41%|▍| 6157/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  41%|▍| 6163/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -56992,8 +56973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6158/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  41%|▍| 6158/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  41%|▍| 6164/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  41%|▍| 6164/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -57001,8 +56982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6159/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  41%|▍| 6159/14932 [08:41<12:23, 11.80it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  41%|▍| 6165/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  41%|▍| 6165/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -57010,8 +56991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6160/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  41%|▍| 6160/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  41%|▍| 6166/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  41%|▍| 6166/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.04"
      ]
     },
     {
@@ -57019,8 +57000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6161/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  41%|▍| 6161/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  41%|▍| 6167/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.04\r",
+      "Epoch 0:  41%|▍| 6167/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -57028,8 +57009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6162/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  41%|▍| 6162/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  41%|▍| 6168/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  41%|▍| 6168/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -57037,8 +57018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6163/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  41%|▍| 6163/14932 [08:42<12:23, 11.80it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  41%|▍| 6169/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  41%|▍| 6169/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -57046,8 +57027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6164/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  41%|▍| 6164/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  41%|▍| 6170/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  41%|▍| 6170/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -57055,8 +57036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6165/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  41%|▍| 6165/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  41%|▍| 6171/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  41%|▍| 6171/14932 [08:39<12:18, 11.87it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -57064,8 +57045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6166/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  41%|▍| 6166/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  41%|▍| 6172/14932 [08:40<12:18, 11.87it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  41%|▍| 6172/14932 [08:40<12:18, 11.87it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -57073,8 +57054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6167/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  41%|▍| 6167/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  41%|▍| 6173/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  41%|▍| 6173/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -57082,8 +57063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6168/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  41%|▍| 6168/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=0.93"
+      "Epoch 0:  41%|▍| 6174/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  41%|▍| 6174/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -57091,8 +57072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6169/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=0.93\r",
-      "Epoch 0:  41%|▍| 6169/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  41%|▍| 6175/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  41%|▍| 6175/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -57100,8 +57081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6170/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  41%|▍| 6170/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  41%|▍| 6176/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  41%|▍| 6176/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -57109,8 +57090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6171/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  41%|▍| 6171/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  41%|▍| 6177/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  41%|▍| 6177/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -57118,8 +57099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6172/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  41%|▍| 6172/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  41%|▍| 6178/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  41%|▍| 6178/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -57127,8 +57108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6173/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  41%|▍| 6173/14932 [08:42<12:22, 11.80it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  41%|▍| 6179/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  41%|▍| 6179/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -57136,8 +57117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6174/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  41%|▍| 6174/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  41%|▍| 6180/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  41%|▍| 6180/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -57145,8 +57126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6175/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  41%|▍| 6175/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  41%|▍| 6181/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  41%|▍| 6181/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -57154,8 +57135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6176/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  41%|▍| 6176/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  41%|▍| 6182/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  41%|▍| 6182/14932 [08:40<12:17, 11.87it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -57163,8 +57144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6177/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  41%|▍| 6177/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  41%|▍| 6183/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:  41%|▍| 6183/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -57172,8 +57153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6178/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  41%|▍| 6178/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  41%|▍| 6184/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  41%|▍| 6184/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -57181,8 +57162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6179/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  41%|▍| 6179/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  41%|▍| 6185/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  41%|▍| 6185/14932 [08:41<12:17, 11.87it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -57190,8 +57171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6180/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  41%|▍| 6180/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  41%|▍| 6186/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  41%|▍| 6186/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -57199,8 +57180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6181/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  41%|▍| 6181/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  41%|▍| 6187/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  41%|▍| 6187/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -57208,8 +57189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6182/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  41%|▍| 6182/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  41%|▍| 6188/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  41%|▍| 6188/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -57217,8 +57198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6183/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  41%|▍| 6183/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  41%|▍| 6189/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  41%|▍| 6189/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -57226,8 +57207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6184/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  41%|▍| 6184/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  41%|▍| 6190/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  41%|▍| 6190/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -57235,8 +57216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6185/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  41%|▍| 6185/14932 [08:43<12:21, 11.80it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  41%|▍| 6191/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  41%|▍| 6191/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -57244,8 +57225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6186/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  41%|▍| 6186/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  41%|▍| 6192/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  41%|▍| 6192/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -57253,8 +57234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6187/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  41%|▍| 6187/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  41%|▍| 6193/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  41%|▍| 6193/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -57262,8 +57243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6188/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  41%|▍| 6188/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  41%|▍| 6194/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  41%|▍| 6194/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -57271,8 +57252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6189/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  41%|▍| 6189/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  41%|▍| 6195/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  41%|▍| 6195/14932 [08:41<12:16, 11.87it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -57280,8 +57261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6190/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  41%|▍| 6190/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  41%|▍| 6196/14932 [08:42<12:16, 11.87it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  41%|▍| 6196/14932 [08:42<12:16, 11.87it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -57289,8 +57270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6191/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  41%|▍| 6191/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  42%|▍| 6197/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  42%|▍| 6197/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -57298,8 +57279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6192/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  41%|▍| 6192/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  42%|▍| 6198/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  42%|▍| 6198/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -57307,8 +57288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6193/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  41%|▍| 6193/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  42%|▍| 6199/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  42%|▍| 6199/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -57316,8 +57297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6194/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  41%|▍| 6194/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  42%|▍| 6200/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  42%|▍| 6200/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -57325,8 +57306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6195/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  41%|▍| 6195/14932 [08:44<12:20, 11.80it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  42%|▍| 6201/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  42%|▍| 6201/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -57334,8 +57315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  41%|▍| 6196/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  41%|▍| 6196/14932 [08:44<12:20, 11.81it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  42%|▍| 6202/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  42%|▍| 6202/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -57343,8 +57324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6197/14932 [08:44<12:19, 11.81it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  42%|▍| 6197/14932 [08:44<12:19, 11.81it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  42%|▍| 6203/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  42%|▍| 6203/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -57352,8 +57333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6198/14932 [08:44<12:19, 11.81it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  42%|▍| 6198/14932 [08:44<12:19, 11.81it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  42%|▍| 6204/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  42%|▍| 6204/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -57361,8 +57342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6199/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  42%|▍| 6199/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  42%|▍| 6205/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  42%|▍| 6205/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -57370,8 +57351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6200/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  42%|▍| 6200/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  42%|▍| 6206/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  42%|▍| 6206/14932 [08:42<12:15, 11.87it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -57379,8 +57360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6201/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  42%|▍| 6201/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  42%|▍| 6207/14932 [08:42<12:14, 11.87it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  42%|▍| 6207/14932 [08:42<12:14, 11.87it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -57388,8 +57369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6202/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  42%|▍| 6202/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  42%|▍| 6208/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  42%|▍| 6208/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -57397,8 +57378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6203/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  42%|▍| 6203/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  42%|▍| 6209/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  42%|▍| 6209/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -57406,8 +57387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6204/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  42%|▍| 6204/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  42%|▍| 6210/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  42%|▍| 6210/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -57415,8 +57396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6205/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  42%|▍| 6205/14932 [08:45<12:19, 11.81it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  42%|▍| 6211/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  42%|▍| 6211/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -57424,8 +57405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6206/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  42%|▍| 6206/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  42%|▍| 6212/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  42%|▍| 6212/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -57433,8 +57414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6207/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  42%|▍| 6207/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  42%|▍| 6213/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  42%|▍| 6213/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -57442,8 +57423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6208/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  42%|▍| 6208/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  42%|▍| 6214/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  42%|▍| 6214/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -57451,8 +57432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6209/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  42%|▍| 6209/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  42%|▍| 6215/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  42%|▍| 6215/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -57460,8 +57441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6210/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  42%|▍| 6210/14932 [08:45<12:18, 11.81it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  42%|▍| 6216/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  42%|▍| 6216/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -57469,8 +57450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6211/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  42%|▍| 6211/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  42%|▍| 6217/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  42%|▍| 6217/14932 [08:43<12:14, 11.87it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -57478,8 +57459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6212/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  42%|▍| 6212/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  42%|▍| 6218/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  42%|▍| 6218/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -57487,8 +57468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6213/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  42%|▍| 6213/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  42%|▍| 6219/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  42%|▍| 6219/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -57496,8 +57477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6214/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  42%|▍| 6214/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  42%|▍| 6220/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  42%|▍| 6220/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -57505,8 +57486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6215/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  42%|▍| 6215/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  42%|▍| 6221/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  42%|▍| 6221/14932 [08:43<12:13, 11.87it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -57514,8 +57495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6216/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  42%|▍| 6216/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  42%|▍| 6222/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  42%|▍| 6222/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -57523,8 +57504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6217/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  42%|▍| 6217/14932 [08:46<12:18, 11.81it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  42%|▍| 6223/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  42%|▍| 6223/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -57532,8 +57513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6218/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  42%|▍| 6218/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  42%|▍| 6224/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  42%|▍| 6224/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -57541,8 +57522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6219/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  42%|▍| 6219/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  42%|▍| 6225/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  42%|▍| 6225/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -57550,8 +57531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6220/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=0.89\r",
-      "Epoch 0:  42%|▍| 6220/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  42%|▍| 6226/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  42%|▍| 6226/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -57559,8 +57540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6221/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  42%|▍| 6221/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  42%|▍| 6227/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  42%|▍| 6227/14932 [08:44<12:13, 11.87it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -57568,8 +57549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6222/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  42%|▍| 6222/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  42%|▍| 6228/14932 [08:44<12:12, 11.87it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  42%|▍| 6228/14932 [08:44<12:12, 11.87it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -57577,8 +57558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6223/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  42%|▍| 6223/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  42%|▍| 6229/14932 [08:44<12:12, 11.87it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  42%|▍| 6229/14932 [08:44<12:12, 11.87it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -57586,8 +57567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6224/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  42%|▍| 6224/14932 [08:46<12:17, 11.81it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  42%|▍| 6230/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  42%|▍| 6230/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -57595,8 +57576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6225/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  42%|▍| 6225/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  42%|▍| 6231/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  42%|▍| 6231/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -57604,8 +57585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6226/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  42%|▍| 6226/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  42%|▍| 6232/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  42%|▍| 6232/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -57613,8 +57594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6227/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  42%|▍| 6227/14932 [08:47<12:17, 11.81it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  42%|▍| 6233/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  42%|▍| 6233/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -57622,8 +57603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6228/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  42%|▍| 6228/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  42%|▍| 6234/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  42%|▍| 6234/14932 [08:44<12:12, 11.88it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -57631,8 +57612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6229/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  42%|▍| 6229/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  42%|▍| 6235/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  42%|▍| 6235/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -57640,7 +57621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6230/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  42%|▍| 6236/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  42%|▍| 6236/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -57648,7 +57630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6230/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  42%|▍| 6237/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  42%|▍| 6237/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -57656,8 +57639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6231/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  42%|▍| 6231/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  42%|▍| 6238/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  42%|▍| 6238/14932 [08:45<12:12, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -57665,8 +57648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6232/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  42%|▍| 6232/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  42%|▍| 6239/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  42%|▍| 6239/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -57674,8 +57657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6233/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  42%|▍| 6233/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  42%|▍| 6240/14932 [08:45<12:11, 11.87it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  42%|▍| 6240/14932 [08:45<12:11, 11.87it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -57683,8 +57666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6234/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  42%|▍| 6234/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  42%|▍| 6241/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  42%|▍| 6241/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -57692,8 +57675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6235/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  42%|▍| 6235/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  42%|▍| 6242/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  42%|▍| 6242/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -57701,8 +57684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6236/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  42%|▍| 6236/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  42%|▍| 6243/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  42%|▍| 6243/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -57710,8 +57693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6237/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  42%|▍| 6237/14932 [08:47<12:16, 11.81it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  42%|▍| 6244/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  42%|▍| 6244/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -57719,8 +57702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6238/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  42%|▍| 6238/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  42%|▍| 6245/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  42%|▍| 6245/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -57728,8 +57711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6239/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  42%|▍| 6239/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  42%|▍| 6246/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  42%|▍| 6246/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -57737,8 +57720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6240/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  42%|▍| 6240/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  42%|▍| 6247/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  42%|▍| 6247/14932 [08:45<12:11, 11.88it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -57746,8 +57729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6241/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  42%|▍| 6241/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  42%|▍| 6248/14932 [08:46<12:11, 11.88it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  42%|▍| 6248/14932 [08:46<12:11, 11.88it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -57755,8 +57738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6242/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  42%|▍| 6242/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  42%|▍| 6249/14932 [08:46<12:11, 11.88it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  42%|▍| 6249/14932 [08:46<12:11, 11.88it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -57764,8 +57747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6243/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  42%|▍| 6243/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  42%|▍| 6250/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  42%|▍| 6250/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -57773,8 +57756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6244/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  42%|▍| 6244/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  42%|▍| 6251/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  42%|▍| 6251/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -57782,8 +57765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6245/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  42%|▍| 6245/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  42%|▍| 6252/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  42%|▍| 6252/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -57791,8 +57774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6246/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  42%|▍| 6246/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  42%|▍| 6253/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  42%|▍| 6253/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -57800,8 +57783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6247/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  42%|▍| 6247/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  42%|▍| 6254/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  42%|▍| 6254/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -57809,8 +57792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6248/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  42%|▍| 6248/14932 [08:48<12:15, 11.81it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  42%|▍| 6255/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  42%|▍| 6255/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -57818,8 +57801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6249/14932 [08:49<12:15, 11.81it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  42%|▍| 6249/14932 [08:49<12:15, 11.81it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  42%|▍| 6256/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  42%|▍| 6256/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -57827,8 +57810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6250/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  42%|▍| 6250/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  42%|▍| 6257/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  42%|▍| 6257/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -57836,8 +57819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6251/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  42%|▍| 6251/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  42%|▍| 6258/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  42%|▍| 6258/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -57845,8 +57828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6252/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  42%|▍| 6252/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  42%|▍| 6259/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  42%|▍| 6259/14932 [08:46<12:10, 11.88it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -57854,8 +57837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6253/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  42%|▍| 6253/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  42%|▍| 6260/14932 [08:47<12:10, 11.88it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  42%|▍| 6260/14932 [08:47<12:10, 11.88it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -57863,8 +57846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6254/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  42%|▍| 6254/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  42%|▍| 6261/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  42%|▍| 6261/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -57872,8 +57855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6255/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  42%|▍| 6255/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  42%|▍| 6262/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  42%|▍| 6262/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -57881,7 +57864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6256/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  42%|▍| 6263/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  42%|▍| 6263/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -57889,7 +57873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6256/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  42%|▍| 6264/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  42%|▍| 6264/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -57897,8 +57882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6257/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  42%|▍| 6257/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  42%|▍| 6265/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  42%|▍| 6265/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -57906,8 +57891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6258/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  42%|▍| 6258/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=0.93"
+      "Epoch 0:  42%|▍| 6266/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  42%|▍| 6266/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -57915,8 +57900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6259/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=0.93\r",
-      "Epoch 0:  42%|▍| 6259/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  42%|▍| 6267/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  42%|▍| 6267/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -57924,8 +57909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6260/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  42%|▍| 6260/14932 [08:49<12:14, 11.81it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  42%|▍| 6268/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  42%|▍| 6268/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -57933,8 +57918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6261/14932 [08:50<12:14, 11.81it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  42%|▍| 6261/14932 [08:50<12:14, 11.81it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  42%|▍| 6269/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  42%|▍| 6269/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -57942,8 +57927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6262/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  42%|▍| 6262/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  42%|▍| 6270/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:  42%|▍| 6270/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -57951,8 +57936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6263/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  42%|▍| 6263/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  42%|▍| 6271/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  42%|▍| 6271/14932 [08:47<12:09, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -57960,8 +57945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6264/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  42%|▍| 6264/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  42%|▍| 6272/14932 [08:48<12:09, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  42%|▍| 6272/14932 [08:48<12:09, 11.88it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -57969,8 +57954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6265/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  42%|▍| 6265/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  42%|▍| 6273/14932 [08:48<12:09, 11.88it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  42%|▍| 6273/14932 [08:48<12:09, 11.88it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -57978,8 +57963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6266/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  42%|▍| 6266/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  42%|▍| 6274/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  42%|▍| 6274/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -57987,8 +57972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6267/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  42%|▍| 6267/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  42%|▍| 6275/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  42%|▍| 6275/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -57996,8 +57981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6268/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  42%|▍| 6268/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  42%|▍| 6276/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  42%|▍| 6276/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -58005,8 +57990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6269/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  42%|▍| 6269/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  42%|▍| 6277/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  42%|▍| 6277/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -58014,8 +57999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6270/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  42%|▍| 6270/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  42%|▍| 6278/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  42%|▍| 6278/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -58023,8 +58008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6271/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  42%|▍| 6271/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  42%|▍| 6279/14932 [08:48<12:08, 11.87it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  42%|▍| 6279/14932 [08:48<12:08, 11.87it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -58032,8 +58017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6272/14932 [08:50<12:13, 11.81it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  42%|▍| 6272/14932 [08:51<12:13, 11.81it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  42%|▍| 6280/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  42%|▍| 6280/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -58041,8 +58026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6273/14932 [08:51<12:13, 11.81it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  42%|▍| 6273/14932 [08:51<12:13, 11.81it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  42%|▍| 6281/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  42%|▍| 6281/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -58050,8 +58035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6274/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  42%|▍| 6274/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  42%|▍| 6282/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  42%|▍| 6282/14932 [08:48<12:08, 11.88it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -58059,8 +58044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6275/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  42%|▍| 6275/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  42%|▍| 6283/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  42%|▍| 6283/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -58068,8 +58053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6276/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  42%|▍| 6276/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  42%|▍| 6284/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  42%|▍| 6284/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -58077,8 +58062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6277/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  42%|▍| 6277/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  42%|▍| 6285/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  42%|▍| 6285/14932 [08:49<12:08, 11.88it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -58086,8 +58071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6278/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  42%|▍| 6278/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  42%|▍| 6286/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  42%|▍| 6286/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -58095,8 +58080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6279/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  42%|▍| 6279/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  42%|▍| 6287/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  42%|▍| 6287/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -58104,8 +58089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6280/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  42%|▍| 6280/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  42%|▍| 6288/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  42%|▍| 6288/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -58113,7 +58098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6281/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  42%|▍| 6289/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  42%|▍| 6289/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -58121,7 +58107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6281/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  42%|▍| 6290/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  42%|▍| 6290/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -58129,8 +58116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6282/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  42%|▍| 6282/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  42%|▍| 6291/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  42%|▍| 6291/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -58138,8 +58125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6283/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  42%|▍| 6283/14932 [08:51<12:12, 11.81it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  42%|▍| 6292/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  42%|▍| 6292/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -58147,8 +58134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6284/14932 [08:51<12:11, 11.81it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  42%|▍| 6284/14932 [08:51<12:11, 11.81it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  42%|▍| 6293/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  42%|▍| 6293/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -58156,8 +58143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6285/14932 [08:51<12:11, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  42%|▍| 6285/14932 [08:51<12:11, 11.82it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  42%|▍| 6294/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  42%|▍| 6294/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -58165,8 +58152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6286/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  42%|▍| 6286/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  42%|▍| 6295/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  42%|▍| 6295/14932 [08:49<12:07, 11.88it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -58174,8 +58161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6287/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  42%|▍| 6287/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  42%|▍| 6296/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  42%|▍| 6296/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -58183,8 +58170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6288/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  42%|▍| 6288/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  42%|▍| 6297/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  42%|▍| 6297/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -58192,8 +58179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6289/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  42%|▍| 6289/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  42%|▍| 6298/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  42%|▍| 6298/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -58201,8 +58188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6290/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  42%|▍| 6290/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  42%|▍| 6299/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  42%|▍| 6299/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -58210,8 +58197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6291/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  42%|▍| 6291/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  42%|▍| 6300/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  42%|▍| 6300/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -58219,8 +58206,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6292/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  42%|▍| 6292/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  42%|▍| 6301/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -58228,8 +58214,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6293/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  42%|▍| 6293/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  42%|▍| 6301/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -58237,8 +58222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6294/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  42%|▍| 6294/14932 [08:52<12:11, 11.82it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  42%|▍| 6302/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  42%|▍| 6302/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -58246,8 +58231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6295/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  42%|▍| 6295/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  42%|▍| 6303/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  42%|▍| 6303/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -58255,8 +58240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6296/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  42%|▍| 6296/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  42%|▍| 6304/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  42%|▍| 6304/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -58264,8 +58249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6297/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  42%|▍| 6297/14932 [08:52<12:10, 11.82it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  42%|▍| 6305/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  42%|▍| 6305/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -58273,8 +58258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6298/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  42%|▍| 6298/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  42%|▍| 6306/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  42%|▍| 6306/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -58282,8 +58267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6299/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  42%|▍| 6299/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  42%|▍| 6307/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  42%|▍| 6307/14932 [08:50<12:06, 11.88it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -58291,8 +58276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6300/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  42%|▍| 6300/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  42%|▍| 6308/14932 [08:50<12:05, 11.88it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  42%|▍| 6308/14932 [08:50<12:05, 11.88it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -58300,8 +58285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6301/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  42%|▍| 6301/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  42%|▍| 6309/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  42%|▍| 6309/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -58309,8 +58294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6302/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  42%|▍| 6302/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  42%|▍| 6310/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  42%|▍| 6310/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -58318,8 +58303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6303/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  42%|▍| 6303/14932 [08:53<12:10, 11.82it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  42%|▍| 6311/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  42%|▍| 6311/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -58327,8 +58312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6304/14932 [08:53<12:10, 11.81it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  42%|▍| 6304/14932 [08:53<12:10, 11.81it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  42%|▍| 6312/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  42%|▍| 6312/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -58336,8 +58321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6305/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  42%|▍| 6305/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  42%|▍| 6313/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  42%|▍| 6313/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -58345,8 +58330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6306/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  42%|▍| 6306/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  42%|▍| 6314/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  42%|▍| 6314/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -58354,8 +58339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6307/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  42%|▍| 6307/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  42%|▍| 6315/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  42%|▍| 6315/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -58363,8 +58348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6308/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  42%|▍| 6308/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  42%|▍| 6316/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  42%|▍| 6316/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -58372,8 +58357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6309/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  42%|▍| 6309/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  42%|▍| 6317/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  42%|▍| 6317/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -58381,8 +58366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6310/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  42%|▍| 6310/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  42%|▍| 6318/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  42%|▍| 6318/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -58390,8 +58375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6311/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  42%|▍| 6311/14932 [08:54<12:10, 11.81it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  42%|▍| 6319/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  42%|▍| 6319/14932 [08:51<12:05, 11.88it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -58399,8 +58384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6312/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  42%|▍| 6312/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  42%|▍| 6320/14932 [08:52<12:05, 11.88it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  42%|▍| 6320/14932 [08:52<12:05, 11.88it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -58408,8 +58393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6313/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  42%|▍| 6313/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  42%|▍| 6321/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  42%|▍| 6321/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -58417,8 +58402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6314/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  42%|▍| 6314/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  42%|▍| 6322/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  42%|▍| 6322/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -58426,8 +58411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6315/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  42%|▍| 6315/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  42%|▍| 6323/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  42%|▍| 6323/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -58435,8 +58420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6316/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  42%|▍| 6316/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  42%|▍| 6324/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  42%|▍| 6324/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -58444,8 +58429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6317/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  42%|▍| 6317/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  42%|▍| 6325/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  42%|▍| 6325/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -58453,8 +58438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6318/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  42%|▍| 6318/14932 [08:54<12:09, 11.81it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  42%|▍| 6326/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  42%|▍| 6326/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -58462,8 +58447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6319/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  42%|▍| 6319/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  42%|▍| 6327/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  42%|▍| 6327/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -58471,8 +58456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6320/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  42%|▍| 6320/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  42%|▍| 6328/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  42%|▍| 6328/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -58480,8 +58465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6321/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  42%|▍| 6321/14932 [08:55<12:09, 11.81it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  42%|▍| 6329/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  42%|▍| 6329/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -58489,8 +58474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6322/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  42%|▍| 6322/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  42%|▍| 6330/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  42%|▍| 6330/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -58498,8 +58483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6323/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  42%|▍| 6323/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  42%|▍| 6331/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  42%|▍| 6331/14932 [08:52<12:04, 11.88it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -58507,8 +58492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6324/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  42%|▍| 6324/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  42%|▍| 6332/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  42%|▍| 6332/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -58516,8 +58501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6325/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  42%|▍| 6325/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  42%|▍| 6333/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  42%|▍| 6333/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -58525,8 +58510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6326/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  42%|▍| 6326/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  42%|▍| 6334/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  42%|▍| 6334/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -58534,8 +58519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6327/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  42%|▍| 6327/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  42%|▍| 6335/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  42%|▍| 6335/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -58543,8 +58528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6328/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  42%|▍| 6328/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  42%|▍| 6336/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  42%|▍| 6336/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -58552,8 +58537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6329/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  42%|▍| 6329/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  42%|▍| 6337/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  42%|▍| 6337/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -58561,8 +58546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6330/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  42%|▍| 6330/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  42%|▍| 6338/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  42%|▍| 6338/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -58570,8 +58555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6331/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  42%|▍| 6331/14932 [08:55<12:08, 11.81it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  42%|▍| 6339/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  42%|▍| 6339/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -58579,8 +58564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6332/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  42%|▍| 6332/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  42%|▍| 6340/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  42%|▍| 6340/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -58588,8 +58573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6333/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  42%|▍| 6333/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  42%|▍| 6341/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  42%|▍| 6341/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -58597,8 +58582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6334/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  42%|▍| 6334/14932 [08:56<12:08, 11.81it/s, v_num=o30c, train/loss=1.09"
+      "Epoch 0:  42%|▍| 6342/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  42%|▍| 6342/14932 [08:53<12:03, 11.88it/s, v_num=ui8w, train/loss=5.12"
      ]
     },
     {
@@ -58606,8 +58591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6335/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=1.09\r",
-      "Epoch 0:  42%|▍| 6335/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  42%|▍| 6343/14932 [08:53<12:02, 11.88it/s, v_num=ui8w, train/loss=5.12\r",
+      "Epoch 0:  42%|▍| 6343/14932 [08:53<12:02, 11.88it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -58615,8 +58600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6336/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  42%|▍| 6336/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  42%|▍| 6344/14932 [08:53<12:02, 11.88it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  42%|▍| 6344/14932 [08:53<12:02, 11.88it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -58624,8 +58609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6337/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  42%|▍| 6337/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  42%|▍| 6345/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  42%|▍| 6345/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -58633,8 +58618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6338/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  42%|▍| 6338/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  42%|▍| 6346/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  42%|▍| 6346/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -58642,8 +58627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6339/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  42%|▍| 6339/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  43%|▍| 6347/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  43%|▍| 6347/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -58651,8 +58636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6340/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  42%|▍| 6340/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  43%|▍| 6348/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  43%|▍| 6348/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=0.77"
      ]
     },
     {
@@ -58660,8 +58645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6341/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  42%|▍| 6341/14932 [08:56<12:07, 11.81it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  43%|▍| 6349/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=0.77\r",
+      "Epoch 0:  43%|▍| 6349/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -58669,8 +58654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6342/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  42%|▍| 6342/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  43%|▍| 6350/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  43%|▍| 6350/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -58678,8 +58663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6343/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  42%|▍| 6343/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  43%|▍| 6351/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  43%|▍| 6351/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -58687,8 +58672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6344/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  42%|▍| 6344/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  43%|▍| 6352/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  43%|▍| 6352/14932 [08:54<12:02, 11.88it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -58696,8 +58681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6345/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  42%|▍| 6345/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  43%|▍| 6353/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  43%|▍| 6353/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -58705,8 +58690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  42%|▍| 6346/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  42%|▍| 6346/14932 [08:57<12:07, 11.81it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  43%|▍| 6354/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  43%|▍| 6354/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -58714,8 +58699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6347/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  43%|▍| 6347/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  43%|▍| 6355/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  43%|▍| 6355/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -58723,8 +58708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6348/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  43%|▍| 6348/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  43%|▍| 6356/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  43%|▍| 6356/14932 [08:54<12:01, 11.88it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -58732,8 +58717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6349/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  43%|▍| 6349/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  43%|▍| 6357/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  43%|▍| 6357/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=1.02"
      ]
     },
     {
@@ -58741,8 +58726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6350/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  43%|▍| 6350/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  43%|▍| 6358/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=1.02\r",
+      "Epoch 0:  43%|▍| 6358/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -58750,8 +58735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6351/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  43%|▍| 6351/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  43%|▍| 6359/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  43%|▍| 6359/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -58759,8 +58744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6352/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  43%|▍| 6352/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  43%|▍| 6360/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  43%|▍| 6360/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -58768,8 +58753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6353/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  43%|▍| 6353/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  43%|���| 6361/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  43%|▍| 6361/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -58777,8 +58762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6354/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  43%|▍| 6354/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  43%|▍| 6362/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  43%|▍| 6362/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -58786,7 +58771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6355/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  43%|▍| 6363/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  43%|▍| 6363/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -58794,7 +58780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6355/14932 [08:57<12:06, 11.81it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  43%|▍| 6364/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  43%|▍| 6364/14932 [08:55<12:01, 11.88it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -58802,8 +58789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6356/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  43%|▍| 6356/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  43%|▍| 6365/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  43%|▍| 6365/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -58811,8 +58798,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6357/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  43%|▍| 6357/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  43%|▍| 6366/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -58820,8 +58806,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6358/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  43%|▍| 6358/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  43%|▍| 6366/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -58829,8 +58814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6359/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  43%|▍| 6359/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  43%|▍| 6367/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  43%|▍| 6367/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -58838,8 +58823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6360/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  43%|▍| 6360/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  43%|▍| 6368/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  43%|▍| 6368/14932 [08:55<12:00, 11.88it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -58847,8 +58832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6361/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  43%|▍| 6361/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  43%|▍| 6369/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  43%|▍| 6369/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -58856,8 +58841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6362/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  43%|▍| 6362/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  43%|▍| 6370/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  43%|▍| 6370/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -58865,8 +58850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6363/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  43%|▍| 6363/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  43%|▍| 6371/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  43%|▍| 6371/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -58874,8 +58859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6364/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  43%|▍| 6364/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  43%|▍| 6372/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  43%|▍| 6372/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -58883,8 +58868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6365/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  43%|▍| 6365/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  43%|▍| 6373/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  43%|▍| 6373/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -58892,8 +58877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6366/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  43%|▍| 6366/14932 [08:58<12:05, 11.81it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  43%|▍| 6374/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  43%|▍| 6374/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -58901,8 +58886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6367/14932 [08:58<12:04, 11.81it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  43%|▍| 6367/14932 [08:58<12:04, 11.81it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  43%|▍| 6375/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  43%|▍| 6375/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -58910,8 +58895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6368/14932 [08:59<12:05, 11.81it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  43%|▍| 6368/14932 [08:59<12:05, 11.81it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  43%|▍| 6376/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  43%|▍| 6376/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -58919,8 +58904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6369/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  43%|▍| 6369/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  43%|▍| 6377/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  43%|▍| 6377/14932 [08:56<12:00, 11.88it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -58928,8 +58913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6370/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  43%|▍| 6370/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  43%|▍| 6378/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  43%|▍| 6378/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -58937,8 +58922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6371/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  43%|▍| 6371/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  43%|▍| 6379/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  43%|▍| 6379/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -58946,8 +58931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6372/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  43%|▍| 6372/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  43%|▍| 6380/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  43%|▍| 6380/14932 [08:56<11:59, 11.88it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -58955,8 +58940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6373/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  43%|▍| 6373/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  43%|▍| 6381/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  43%|▍| 6381/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -58964,8 +58949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6374/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  43%|▍| 6374/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  43%|▍| 6382/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  43%|▍| 6382/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -58973,8 +58958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6375/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  43%|▍| 6375/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  43%|▍| 6383/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  43%|▍| 6383/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -58982,8 +58967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6376/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  43%|▍| 6376/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  43%|▍| 6384/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  43%|▍| 6384/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -58991,8 +58976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6377/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  43%|▍| 6377/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  43%|▍| 6385/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  43%|▍| 6385/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -59000,8 +58985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6378/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  43%|▍| 6378/14932 [08:59<12:04, 11.81it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  43%|▍| 6386/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  43%|▍| 6386/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -59009,7 +58994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6379/14932 [08:59<12:03, 11.81it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  43%|▍| 6387/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  43%|▍| 6387/14932 [08:57<11:59, 11.88it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -59017,7 +59003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6379/14932 [08:59<12:03, 11.81it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  43%|▍| 6388/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  43%|▍| 6388/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -59025,8 +59012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6380/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  43%|▍| 6380/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  43%|▍| 6389/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  43%|▍| 6389/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -59034,8 +59021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6381/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  43%|▍| 6381/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  43%|▍| 6390/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  43%|▍| 6390/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -59043,8 +59030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6382/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  43%|▍| 6382/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  43%|▍| 6391/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  43%|▍| 6391/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -59052,8 +59039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6383/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  43%|▍| 6383/14932 [09:00<12:03, 11.81it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  43%|▍| 6392/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  43%|▍| 6392/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -59061,8 +59048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6384/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  43%|▍| 6384/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  43%|▍| 6393/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  43%|▍| 6393/14932 [08:57<11:58, 11.88it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -59070,8 +59057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6385/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  43%|▍| 6385/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  43%|▍| 6394/14932 [08:57<11:58, 11.89it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  43%|▍| 6394/14932 [08:57<11:58, 11.89it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -59079,8 +59066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6386/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  43%|▍| 6386/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  43%|▍| 6395/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  43%|▍| 6395/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -59088,8 +59075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6387/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  43%|▍| 6387/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  43%|▍| 6396/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  43%|▍| 6396/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -59097,8 +59084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6388/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  43%|▍| 6388/14932 [09:00<12:03, 11.82it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  43%|▍| 6397/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  43%|▍| 6397/14932 [08:58<11:58, 11.89it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -59106,8 +59093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6389/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  43%|▍| 6389/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  43%|▍| 6398/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  43%|▍| 6398/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -59115,8 +59102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6390/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  43%|▍| 6390/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  43%|▍| 6399/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  43%|▍| 6399/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -59124,8 +59111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6391/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  43%|▍| 6391/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  43%|▍| 6400/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  43%|▍| 6400/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -59133,8 +59120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6392/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  43%|▍| 6392/14932 [09:00<12:02, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  43%|▍| 6401/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  43%|▍| 6401/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -59142,8 +59129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6393/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  43%|▍| 6393/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  43%|▍| 6402/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  43%|▍| 6402/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -59151,8 +59138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6394/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  43%|▍| 6394/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  43%|▍| 6403/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  43%|▍| 6403/14932 [08:58<11:57, 11.88it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -59160,8 +59147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6395/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  43%|▍| 6395/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  43%|▍| 6404/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  43%|▍| 6404/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -59169,8 +59156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6396/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  43%|▍| 6396/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  43%|▍| 6405/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  43%|▍| 6405/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -59178,8 +59165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6397/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  43%|▍| 6397/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  43%|▍| 6406/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  43%|▍| 6406/14932 [08:58<11:57, 11.89it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -59187,8 +59174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6398/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  43%|▍| 6398/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  43%|▍| 6407/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  43%|▍| 6407/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -59196,8 +59183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6399/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  43%|▍| 6399/14932 [09:01<12:02, 11.82it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  43%|▍| 6408/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  43%|▍| 6408/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -59205,8 +59192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6400/14932 [09:01<12:02, 11.81it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  43%|▍| 6400/14932 [09:01<12:02, 11.81it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  43%|▍| 6409/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  43%|▍| 6409/14932 [08:59<11:57, 11.89it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -59214,8 +59201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6401/14932 [09:01<12:02, 11.81it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  43%|▍| 6401/14932 [09:01<12:02, 11.81it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  43%|▍| 6410/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  43%|▍| 6410/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -59223,8 +59210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6402/14932 [09:01<12:01, 11.81it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  43%|▍| 6402/14932 [09:01<12:01, 11.81it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  43%|▍| 6411/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  43%|▍| 6411/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -59232,8 +59219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6403/14932 [09:01<12:01, 11.82it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  43%|▍| 6403/14932 [09:01<12:01, 11.82it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  43%|▍| 6412/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  43%|▍| 6412/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -59241,8 +59228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6404/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  43%|▍| 6404/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  43%|▍| 6413/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  43%|▍| 6413/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -59250,8 +59237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6405/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  43%|▍| 6405/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  43%|▍| 6414/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  43%|▍| 6414/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -59259,8 +59246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6406/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  43%|▍| 6406/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  43%|▍| 6415/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  43%|▍| 6415/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -59268,8 +59255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6407/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  43%|▍| 6407/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  43%|▍| 6416/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  43%|▍| 6416/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -59277,8 +59264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6408/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  43%|▍| 6408/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  43%|▍| 6417/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  43%|▍| 6417/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -59286,8 +59273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6409/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  43%|▍| 6409/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  43%|▍| 6418/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  43%|▍| 6418/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -59295,8 +59282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6410/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  43%|▍| 6410/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  43%|▍| 6419/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  43%|▍| 6419/14932 [08:59<11:56, 11.89it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -59304,8 +59291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6411/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  43%|▍| 6411/14932 [09:02<12:01, 11.82it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  43%|▍| 6420/14932 [09:00<11:56, 11.89it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  43%|▍| 6420/14932 [09:00<11:56, 11.89it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -59313,8 +59300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6412/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  43%|▍| 6412/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  43%|▍| 6421/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  43%|▍| 6421/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -59322,8 +59309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6413/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  43%|▍| 6413/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  43%|▍| 6422/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  43%|▍| 6422/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=0.89"
      ]
     },
     {
@@ -59331,8 +59318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6414/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  43%|▍| 6414/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  43%|▍| 6423/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=0.89\r",
+      "Epoch 0:  43%|▍| 6423/14932 [09:00<11:56, 11.88it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -59340,8 +59327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6415/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  43%|▍| 6415/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  43%|▍| 6424/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  43%|▍| 6424/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -59349,8 +59336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6416/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  43%|▍| 6416/14932 [09:02<12:00, 11.82it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  43%|▍| 6425/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  43%|▍| 6425/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -59358,8 +59345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6417/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  43%|▍| 6417/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  43%|▍| 6426/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  43%|▍| 6426/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -59367,8 +59354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6418/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  43%|▍| 6418/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  43%|▍| 6427/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  43%|▍| 6427/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -59376,8 +59363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6419/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  43%|▍| 6419/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  43%|▍| 6428/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  43%|▍| 6428/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -59385,8 +59372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6420/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  43%|▍| 6420/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  43%|▍| 6429/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  43%|▍| 6429/14932 [09:00<11:55, 11.88it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -59394,8 +59381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6421/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  43%|▍| 6421/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  43%|▍| 6430/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  43%|▍| 6430/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -59403,8 +59390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6422/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  43%|▍| 6422/14932 [09:03<12:00, 11.82it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  43%|▍| 6431/14932 [09:01<11:55, 11.89it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  43%|▍| 6431/14932 [09:01<11:55, 11.89it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -59412,8 +59399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6423/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  43%|▍| 6423/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  43%|▍| 6432/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  43%|▍| 6432/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -59421,8 +59408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6424/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  43%|▍| 6424/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  43%|▍| 6433/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  43%|▍| 6433/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -59430,8 +59417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6425/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  43%|▍| 6425/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  43%|▍| 6434/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  43%|▍| 6434/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -59439,8 +59426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6426/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  43%|▍| 6426/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  43%|▍| 6435/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  43%|▍| 6435/14932 [09:01<11:55, 11.88it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -59448,8 +59435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6427/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  43%|▍| 6427/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  43%|▍| 6436/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  43%|▍| 6436/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -59457,8 +59444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6428/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  43%|▍| 6428/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  43%|▍| 6437/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  43%|▍| 6437/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -59466,8 +59453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6429/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  43%|▍| 6429/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  43%|▍| 6438/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  43%|▍| 6438/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -59475,8 +59462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6430/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  43%|▍| 6430/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  43%|▍| 6439/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  43%|▍| 6439/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -59484,8 +59471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6431/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  43%|▍| 6431/14932 [09:03<11:59, 11.82it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  43%|▍| 6440/14932 [09:01<11:54, 11.89it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  43%|▍| 6440/14932 [09:01<11:54, 11.88it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -59493,8 +59480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6432/14932 [09:04<11:59, 11.82it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  43%|▍| 6432/14932 [09:04<11:59, 11.82it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  43%|▍| 6441/14932 [09:01<11:54, 11.89it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  43%|▍| 6441/14932 [09:01<11:54, 11.89it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -59502,8 +59489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6433/14932 [09:04<11:59, 11.82it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  43%|▍| 6433/14932 [09:04<11:59, 11.82it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  43%|▍| 6442/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  43%|▍| 6442/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -59511,8 +59498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6434/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  43%|▍| 6434/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  43%|▍| 6443/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  43%|▍| 6443/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -59520,8 +59507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6435/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  43%|▍| 6435/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  43%|▍| 6444/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  43%|▍| 6444/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -59529,8 +59516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6436/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  43%|▍| 6436/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  43%|▍| 6445/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  43%|▍| 6445/14932 [09:02<11:54, 11.89it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -59538,8 +59525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6437/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  43%|▍| 6437/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  43%|▍| 6446/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  43%|▍| 6446/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -59547,8 +59534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6438/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  43%|▍| 6438/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  43%|▍| 6447/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  43%|▍| 6447/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -59556,8 +59543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6439/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  43%|▍| 6439/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  43%|▍| 6448/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  43%|▍| 6448/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -59565,8 +59552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6440/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  43%|▍| 6440/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  43%|▍| 6449/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  43%|▍| 6449/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -59574,8 +59561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6441/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  43%|▍| 6441/14932 [09:04<11:58, 11.82it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  43%|▍| 6450/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  43%|▍| 6450/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -59583,8 +59570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6442/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  43%|▍| 6442/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  43%|▍| 6451/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  43%|▍| 6451/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -59592,8 +59579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6443/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  43%|▍| 6443/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  43%|▍| 6452/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  43%|▍| 6452/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -59601,8 +59588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6444/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  43%|▍| 6444/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  43%|▍| 6453/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  43%|▍| 6453/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -59610,8 +59597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6445/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  43%|▍| 6445/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  43%|▍| 6454/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  43%|▍| 6454/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -59619,8 +59606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6446/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  43%|▍| 6446/14932 [09:05<11:58, 11.82it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  43%|▍| 6455/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  43%|▍| 6455/14932 [09:02<11:53, 11.89it/s, v_num=ui8w, train/loss=0.91"
      ]
     },
     {
@@ -59628,8 +59615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6447/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  43%|▍| 6447/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  43%|▍| 6456/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=0.91\r",
+      "Epoch 0:  43%|▍| 6456/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -59637,8 +59624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6448/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  43%|▍| 6448/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  43%|▍| 6457/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  43%|▍| 6457/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -59646,8 +59633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6449/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  43%|▍| 6449/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  43%|▍| 6458/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  43%|▍| 6458/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -59655,8 +59642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6450/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  43%|▍| 6450/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  43%|▍| 6459/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  43%|▍| 6459/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -59664,8 +59651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6451/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  43%|▍| 6451/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  43%|▍| 6460/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  43%|▍| 6460/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -59673,8 +59660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6452/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  43%|▍| 6452/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  43%|▍| 6461/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  43%|▍| 6461/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.97"
      ]
     },
     {
@@ -59682,8 +59669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6453/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  43%|▍| 6453/14932 [09:05<11:57, 11.82it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  43%|▍| 6462/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.97\r",
+      "Epoch 0:  43%|▍| 6462/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -59691,8 +59678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6454/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  43%|▍| 6454/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  43%|▍| 6463/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  43%|▍| 6463/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -59700,8 +59687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6455/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  43%|▍| 6455/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  43%|▍| 6464/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  43%|▍| 6464/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -59709,8 +59696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6456/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  43%|▍| 6456/14932 [09:06<11:57, 11.82it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  43%|▍| 6465/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  43%|▍| 6465/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -59718,8 +59705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6457/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  43%|▍| 6457/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  43%|▍| 6466/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  43%|▍| 6466/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -59727,8 +59714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6458/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  43%|▍| 6458/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  43%|▍| 6467/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  43%|▍| 6467/14932 [09:03<11:52, 11.89it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -59736,8 +59723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6459/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  43%|▍| 6459/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  43%|▍| 6468/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  43%|▍| 6468/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -59745,7 +59732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6460/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  43%|▍| 6469/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  43%|▍| 6469/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -59753,7 +59741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6460/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  43%|▍| 6470/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  43%|▍| 6470/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -59761,8 +59750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6461/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  43%|▍| 6461/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  43%|▍| 6471/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  43%|▍| 6471/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -59770,8 +59759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6462/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  43%|▍| 6462/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  43%|▍| 6472/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  43%|▍| 6472/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -59779,8 +59768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6463/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  43%|▍| 6463/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  43%|▍| 6473/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  43%|▍| 6473/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -59788,8 +59777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6464/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  43%|▍| 6464/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  43%|▍| 6474/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  43%|▍| 6474/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.72"
      ]
     },
     {
@@ -59797,8 +59786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6465/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  43%|▍| 6465/14932 [09:06<11:56, 11.82it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  43%|▍| 6475/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=1.72\r",
+      "Epoch 0:  43%|▍| 6475/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -59806,8 +59795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6466/14932 [09:07<11:56, 11.82it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  43%|▍| 6466/14932 [09:07<11:56, 11.82it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  43%|▍| 6476/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  43%|▍| 6476/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -59815,8 +59804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6467/14932 [09:07<11:56, 11.82it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  43%|▍| 6467/14932 [09:07<11:56, 11.82it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  43%|▍| 6477/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  43%|▍| 6477/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -59824,8 +59813,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6468/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  43%|▍| 6468/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  43%|▍| 6478/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -59833,8 +59821,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6469/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  43%|▍| 6469/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  43%|▍| 6478/14932 [09:04<11:51, 11.89it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -59842,8 +59829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6470/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  43%|▍| 6470/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  43%|▍| 6479/14932 [09:04<11:50, 11.89it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  43%|▍| 6479/14932 [09:04<11:50, 11.89it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -59851,8 +59838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6471/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  43%|▍| 6471/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  43%|▍| 6480/14932 [09:04<11:50, 11.89it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  43%|▍| 6480/14932 [09:04<11:50, 11.89it/s, v_num=ui8w, train/loss=1.22"
      ]
     },
     {
@@ -59860,8 +59847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6472/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  43%|▍| 6472/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  43%|▍| 6481/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=1.22\r",
+      "Epoch 0:  43%|▍| 6481/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -59869,8 +59856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6473/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  43%|▍| 6473/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  43%|▍| 6482/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  43%|▍| 6482/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -59878,8 +59865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6474/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  43%|▍| 6474/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  43%|▍| 6483/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  43%|▍| 6483/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=5.28"
      ]
     },
     {
@@ -59887,8 +59874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6475/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  43%|▍| 6475/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  43%|▍| 6484/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=5.28\r",
+      "Epoch 0:  43%|▍| 6484/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -59896,8 +59883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6476/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  43%|▍| 6476/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  43%|▍| 6485/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  43%|▍| 6485/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -59905,8 +59892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6477/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  43%|▍| 6477/14932 [09:07<11:55, 11.82it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  43%|▍| 6486/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  43%|▍| 6486/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -59914,8 +59901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6478/14932 [09:08<11:55, 11.82it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  43%|▍| 6478/14932 [09:08<11:55, 11.82it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  43%|▍| 6487/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  43%|▍| 6487/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -59923,8 +59910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6479/14932 [09:08<11:55, 11.82it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  43%|▍| 6479/14932 [09:08<11:55, 11.82it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  43%|▍| 6488/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  43%|▍| 6488/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -59932,8 +59919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6480/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  43%|▍| 6480/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  43%|▍| 6489/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  43%|▍| 6489/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -59941,8 +59928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6481/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  43%|▍| 6481/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  43%|▍| 6490/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  43%|▍| 6490/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -59950,8 +59937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6482/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=0.89\r",
-      "Epoch 0:  43%|▍| 6482/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  43%|▍| 6491/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  43%|▍| 6491/14932 [09:05<11:50, 11.89it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -59959,8 +59946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6483/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  43%|▍| 6483/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  43%|▍| 6492/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  43%|▍| 6492/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -59968,8 +59955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6484/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  43%|▍| 6484/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  43%|▍| 6493/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  43%|▍| 6493/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -59977,8 +59964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6485/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  43%|▍| 6485/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  43%|▍| 6494/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  43%|▍| 6494/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=4.72"
      ]
     },
     {
@@ -59986,8 +59973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6486/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  43%|▍| 6486/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  43%|▍| 6495/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=4.72\r",
+      "Epoch 0:  43%|▍| 6495/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -59995,8 +59982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6487/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  43%|▍| 6487/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  44%|▍| 6496/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  44%|▍| 6496/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -60004,8 +59991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6488/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  43%|▍| 6488/14932 [09:08<11:54, 11.82it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  44%|▍| 6497/14932 [09:06<11:49, 11.88it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  44%|▍| 6497/14932 [09:06<11:49, 11.88it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -60013,8 +60000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6489/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  43%|▍| 6489/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  44%|▍| 6498/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  44%|▍| 6498/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -60022,8 +60009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6490/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  43%|▍| 6490/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  44%|▍| 6499/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  44%|▍| 6499/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -60031,8 +60018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6491/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  43%|▍| 6491/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  44%|▍| 6500/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  44%|▍| 6500/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -60040,8 +60027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6492/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  43%|▍| 6492/14932 [09:09<11:54, 11.82it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  44%|▍| 6501/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  44%|▍| 6501/14932 [09:06<11:49, 11.89it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -60049,8 +60036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6493/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  43%|▍| 6493/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  44%|▍| 6502/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  44%|▍| 6502/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -60058,8 +60045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6494/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  43%|▍| 6494/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  44%|▍| 6503/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  44%|▍| 6503/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=0.94"
      ]
     },
     {
@@ -60067,8 +60054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  43%|▍| 6495/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  43%|▍| 6495/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  44%|▍| 6504/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=0.94\r",
+      "Epoch 0:  44%|▍| 6504/14932 [09:07<11:49, 11.89it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -60076,8 +60063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6496/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  44%|▍| 6496/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  44%|▍| 6505/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  44%|▍| 6505/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -60085,8 +60072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6497/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  44%|▍| 6497/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  44%|▍| 6506/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  44%|▍| 6506/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -60094,8 +60081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6498/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  44%|▍| 6498/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  44%|▍| 6507/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  44%|▍| 6507/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -60103,8 +60090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6499/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  44%|▍| 6499/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  44%|▍| 6508/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  44%|▍| 6508/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -60112,8 +60099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6500/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  44%|▍| 6500/14932 [09:09<11:53, 11.82it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  44%|▍| 6509/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  44%|▍| 6509/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -60121,8 +60108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6501/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  44%|▍| 6501/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  44%|▍| 6510/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  44%|▍| 6510/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -60130,7 +60117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6502/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  44%|▍| 6511/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  44%|▍| 6511/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -60138,7 +60126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6502/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  44%|▍| 6512/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  44%|▍| 6512/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -60146,8 +60135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6503/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  44%|▍| 6503/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  44%|▍| 6513/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  44%|▍| 6513/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -60155,8 +60144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6504/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  44%|▍| 6504/14932 [09:10<11:53, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  44%|▍| 6514/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  44%|▍| 6514/14932 [09:07<11:48, 11.89it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -60164,8 +60153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6505/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  44%|▍| 6505/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  44%|▍| 6515/14932 [09:07<11:47, 11.89it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  44%|▍| 6515/14932 [09:07<11:47, 11.89it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -60173,8 +60162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6506/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  44%|▍| 6506/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=1.04"
+      "Epoch 0:  44%|▍| 6516/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  44%|▍| 6516/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -60182,8 +60171,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6507/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=1.04\r",
-      "Epoch 0:  44%|▍| 6507/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  44%|▍| 6517/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -60191,8 +60179,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6508/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  44%|▍| 6508/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  44%|▍| 6517/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -60200,7 +60187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6509/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  44%|▍| 6518/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  44%|▍| 6518/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -60208,7 +60196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6509/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  44%|▍| 6519/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  44%|▍| 6519/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -60216,8 +60205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6510/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  44%|▍| 6510/14932 [09:10<11:52, 11.82it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  44%|▍| 6520/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  44%|▍| 6520/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -60225,8 +60214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6511/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  44%|▍| 6511/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  44%|▍| 6521/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  44%|▍| 6521/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -60234,8 +60223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6512/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  44%|▍| 6512/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  44%|▍| 6522/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  44%|▍| 6522/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -60243,8 +60232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6513/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  44%|▍| 6513/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  44%|▍| 6523/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  44%|▍| 6523/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -60252,8 +60241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6514/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  44%|▍| 6514/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  44%|▍| 6524/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  44%|▍| 6524/14932 [09:08<11:47, 11.89it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -60261,8 +60250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6515/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  44%|▍| 6515/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  44%|▍| 6525/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  44%|▍| 6525/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -60270,8 +60259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6516/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  44%|▍| 6516/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  44%|▍| 6526/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  44%|▍| 6526/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -60279,8 +60268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6517/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  44%|▍| 6517/14932 [09:11<11:52, 11.82it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  44%|▍| 6527/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  44%|▍| 6527/14932 [09:08<11:46, 11.89it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -60288,8 +60277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6518/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  44%|▍| 6518/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  44%|▍| 6528/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  44%|▍| 6528/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -60297,8 +60286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6519/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  44%|▍| 6519/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  44%|▍| 6529/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  44%|▍| 6529/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -60306,8 +60295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6520/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  44%|▍| 6520/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  44%|▍| 6530/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  44%|▍| 6530/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -60315,8 +60304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6521/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  44%|▍| 6521/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  44%|▍| 6531/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  44%|▍| 6531/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -60324,8 +60313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6522/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  44%|▍| 6522/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  44%|▍| 6532/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  44%|▍| 6532/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -60333,8 +60322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6523/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  44%|▍| 6523/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  44%|▍| 6533/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  44%|▍| 6533/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -60342,8 +60331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6524/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  44%|▍| 6524/14932 [09:11<11:51, 11.82it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  44%|▍| 6534/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  44%|▍| 6534/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -60351,8 +60340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6525/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  44%|▍| 6525/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  44%|▍| 6535/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  44%|▍| 6535/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -60360,8 +60349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6526/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  44%|▍| 6526/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  44%|▍| 6536/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  44%|▍| 6536/14932 [09:09<11:46, 11.89it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -60369,8 +60358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6527/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  44%|▍| 6527/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  44%|▍| 6537/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  44%|▍| 6537/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -60378,8 +60367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6528/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  44%|▍| 6528/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  44%|▍| 6538/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  44%|▍| 6538/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -60387,8 +60376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6529/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  44%|▍| 6529/14932 [09:12<11:51, 11.82it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  44%|▍| 6539/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  44%|▍| 6539/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -60396,8 +60385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6530/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  44%|▍| 6530/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  44%|▍| 6540/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  44%|▍| 6540/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -60405,8 +60394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6531/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  44%|▍| 6531/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  44%|▍| 6541/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  44%|▍| 6541/14932 [09:09<11:45, 11.89it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -60414,8 +60403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6532/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  44%|▍| 6532/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  44%|▍| 6542/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  44%|▍| 6542/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -60423,8 +60412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6533/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  44%|▍| 6533/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=1.10"
+      "Epoch 0:  44%|▍| 6543/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  44%|▍| 6543/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -60432,8 +60421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6534/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=1.10\r",
-      "Epoch 0:  44%|▍| 6534/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  44%|▍| 6544/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  44%|▍| 6544/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -60441,8 +60430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6535/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  44%|▍| 6535/14932 [09:12<11:50, 11.82it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  44%|▍| 6545/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  44%|▍| 6545/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=1.17"
      ]
     },
     {
@@ -60450,8 +60439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6536/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  44%|▍| 6536/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  44%|▍| 6546/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=1.17\r",
+      "Epoch 0:  44%|▍| 6546/14932 [09:10<11:45, 11.89it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -60459,8 +60448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6537/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  44%|▍| 6537/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  44%|▍| 6547/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  44%|▍| 6547/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -60468,7 +60457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6538/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  44%|▍| 6548/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  44%|▍| 6548/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -60476,7 +60466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6538/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  44%|▍| 6549/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  44%|▍| 6549/14932 [09:10<11:44, 11.89it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -60484,8 +60475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6539/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  44%|▍| 6539/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  44%|▍| 6550/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  44%|▍| 6550/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -60493,8 +60484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6540/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  44%|▍| 6540/14932 [09:13<11:50, 11.82it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  44%|▍| 6551/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  44%|▍| 6551/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -60502,8 +60493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6541/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  44%|▍| 6541/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  44%|▍| 6552/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  44%|▍| 6552/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -60511,8 +60502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6542/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  44%|▍| 6542/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  44%|▍| 6553/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  44%|▍| 6553/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -60520,8 +60511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6543/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  44%|▍| 6543/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  44%|▍| 6554/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  44%|▍| 6554/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -60529,8 +60520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6544/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  44%|▍| 6544/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  44%|▍| 6555/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  44%|▍| 6555/14932 [09:10<11:44, 11.90it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -60538,8 +60529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6545/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  44%|▍| 6545/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  44%|▍| 6556/14932 [09:11<11:44, 11.90it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  44%|▍| 6556/14932 [09:11<11:44, 11.90it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -60547,8 +60538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6546/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  44%|▍| 6546/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  44%|▍| 6557/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  44%|▍| 6557/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -60556,8 +60547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6547/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  44%|▍| 6547/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=1.15"
+      "Epoch 0:  44%|▍| 6558/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  44%|▍| 6558/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -60565,8 +60556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6548/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=1.15\r",
-      "Epoch 0:  44%|▍| 6548/14932 [09:13<11:49, 11.82it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  44%|▍| 6559/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  44%|▍| 6559/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -60574,8 +60565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6549/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  44%|▍| 6549/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  44%|▍| 6560/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  44%|▍| 6560/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -60583,8 +60574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6550/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  44%|▍| 6550/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  44%|▍| 6561/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  44%|▍| 6561/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -60592,8 +60583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6551/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  44%|▍| 6551/14932 [09:14<11:49, 11.82it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  44%|▍| 6562/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  44%|▍| 6562/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -60601,8 +60592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6552/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  44%|▍| 6552/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  44%|▍| 6563/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  44%|▍| 6563/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -60610,8 +60601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6553/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  44%|▍| 6553/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  44%|▍| 6564/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  44%|▍| 6564/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -60619,8 +60610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6554/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  44%|▍| 6554/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  44%|▍| 6565/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  44%|▍| 6565/14932 [09:11<11:43, 11.89it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -60628,8 +60619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6555/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  44%|▍| 6555/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  44%|▍| 6566/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  44%|▍| 6566/14932 [09:11<11:43, 11.90it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -60637,8 +60628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6556/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  44%|▍| 6556/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  44%|▍| 6567/14932 [09:12<11:43, 11.90it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  44%|▍| 6567/14932 [09:12<11:43, 11.90it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -60646,8 +60637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6557/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  44%|▍| 6557/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  44%|▍| 6568/14932 [09:12<11:43, 11.90it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  44%|▍| 6568/14932 [09:12<11:43, 11.90it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -60655,8 +60646,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6558/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  44%|▍| 6558/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  44%|▍| 6569/14932 [09:12<11:43, 11.89it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -60664,8 +60654,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6559/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  44%|▍| 6559/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  44%|▍| 6569/14932 [09:12<11:43, 11.89it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -60673,8 +60662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6560/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  44%|▍| 6560/14932 [09:14<11:48, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  44%|▍| 6570/14932 [09:12<11:43, 11.89it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  44%|▍| 6570/14932 [09:12<11:43, 11.89it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -60682,8 +60671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6561/14932 [09:15<11:48, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  44%|▍| 6561/14932 [09:15<11:48, 11.82it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  44%|▍| 6571/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  44%|▍| 6571/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -60691,8 +60680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6562/14932 [09:15<11:48, 11.82it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  44%|▍| 6562/14932 [09:15<11:48, 11.82it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  44%|▍| 6572/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  44%|▍| 6572/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -60700,8 +60689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6563/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  44%|▍| 6563/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  44%|▍| 6573/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  44%|▍| 6573/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -60709,8 +60698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6564/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  44%|▍| 6564/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  44%|▍| 6574/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  44%|▍| 6574/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=1.33"
      ]
     },
     {
@@ -60718,8 +60707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6565/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  44%|▍| 6565/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  44%|▍| 6575/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=1.33\r",
+      "Epoch 0:  44%|▍| 6575/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -60727,8 +60716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6566/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  44%|▍| 6566/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  44%|▍| 6576/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  44%|▍| 6576/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -60736,8 +60725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6567/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  44%|▍| 6567/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  44%|▍| 6577/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  44%|▍| 6577/14932 [09:12<11:42, 11.89it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -60745,8 +60734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6568/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  44%|▍| 6568/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  44%|▍| 6578/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  44%|▍| 6578/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -60754,8 +60743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6569/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  44%|▍| 6569/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  44%|▍| 6579/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  44%|▍| 6579/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -60763,8 +60752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6570/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  44%|▍| 6570/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  44%|▍| 6580/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  44%|▍| 6580/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -60772,8 +60761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6571/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  44%|▍| 6571/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  44%|▍| 6581/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  44%|▍| 6581/14932 [09:13<11:42, 11.89it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -60781,8 +60770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6572/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  44%|▍| 6572/14932 [09:15<11:47, 11.82it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  44%|▍| 6582/14932 [09:13<11:41, 11.89it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  44%|▍| 6582/14932 [09:13<11:41, 11.89it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -60790,8 +60779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6573/14932 [09:15<11:46, 11.82it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  44%|▍| 6573/14932 [09:15<11:46, 11.82it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  44%|▍| 6583/14932 [09:13<11:41, 11.89it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  44%|▍| 6583/14932 [09:13<11:41, 11.89it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -60799,8 +60788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6574/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  44%|▍| 6574/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  44%|▍| 6584/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  44%|▍| 6584/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -60808,8 +60797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6575/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  44%|▍| 6575/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  44%|▍| 6585/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  44%|▍| 6585/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -60817,8 +60806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6576/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  44%|▍| 6576/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=1.67"
+      "Epoch 0:  44%|▍| 6586/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  44%|▍| 6586/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -60826,8 +60815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6577/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=1.67\r",
-      "Epoch 0:  44%|▍| 6577/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  44%|▍| 6587/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  44%|▍| 6587/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -60835,8 +60824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6578/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  44%|▍| 6578/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  44%|▍| 6588/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  44%|▍| 6588/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -60844,8 +60833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6579/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  44%|▍| 6579/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  44%|▍| 6589/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  44%|▍| 6589/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -60853,8 +60842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6580/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  44%|▍| 6580/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  44%|▍| 6590/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  44%|▍| 6590/14932 [09:13<11:41, 11.90it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -60862,8 +60851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6581/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  44%|▍| 6581/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  44%|▍| 6591/14932 [09:14<11:41, 11.90it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  44%|▍| 6591/14932 [09:14<11:41, 11.90it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -60871,8 +60860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6582/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  44%|▍| 6582/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  44%|▍| 6592/14932 [09:14<11:41, 11.89it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  44%|▍| 6592/14932 [09:14<11:41, 11.89it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -60880,8 +60869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6583/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  44%|▍| 6583/14932 [09:16<11:46, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  44%|▍| 6593/14932 [09:14<11:41, 11.89it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  44%|▍| 6593/14932 [09:14<11:41, 11.89it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -60889,8 +60878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6584/14932 [09:16<11:45, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  44%|▍| 6584/14932 [09:16<11:45, 11.82it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  44%|▍| 6594/14932 [09:14<11:40, 11.89it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  44%|▍| 6594/14932 [09:14<11:40, 11.89it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -60898,8 +60887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6585/14932 [09:16<11:45, 11.82it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  44%|▍| 6585/14932 [09:16<11:45, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  44%|▍| 6595/14932 [09:14<11:40, 11.89it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  44%|▍| 6595/14932 [09:14<11:40, 11.89it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -60907,8 +60896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6586/14932 [09:16<11:45, 11.83it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  44%|▍| 6586/14932 [09:16<11:45, 11.83it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  44%|▍| 6596/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  44%|▍| 6596/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -60916,8 +60905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6587/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  44%|▍| 6587/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  44%|▍| 6597/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  44%|▍| 6597/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -60925,8 +60914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6588/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  44%|▍| 6588/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  44%|▍| 6598/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  44%|▍| 6598/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -60934,8 +60923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6589/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  44%|▍| 6589/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  44%|▍| 6599/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  44%|▍| 6599/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -60943,8 +60932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6590/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  44%|▍| 6590/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  44%|▍| 6600/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  44%|▍| 6600/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -60952,8 +60941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6591/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  44%|▍| 6591/14932 [09:17<11:45, 11.83it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  44%|▍| 6601/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  44%|▍| 6601/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -60961,8 +60950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6592/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  44%|▍| 6592/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  44%|▍| 6602/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  44%|▍| 6602/14932 [09:14<11:40, 11.90it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -60970,8 +60959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6593/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  44%|▍| 6593/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  44%|▍| 6603/14932 [09:15<11:40, 11.90it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  44%|▍| 6603/14932 [09:15<11:40, 11.90it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -60979,8 +60968,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6594/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  44%|▍| 6594/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  44%|▍| 6604/14932 [09:15<11:40, 11.90it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -60988,8 +60976,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6595/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  44%|▍| 6595/14932 [09:17<11:45, 11.82it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:  44%|▍| 6604/14932 [09:15<11:40, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -60997,8 +60984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6596/14932 [09:17<11:44, 11.83it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:  44%|▍| 6596/14932 [09:17<11:44, 11.83it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  44%|▍| 6605/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  44%|▍| 6605/14932 [09:15<11:40, 11.90it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -61006,7 +60993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6597/14932 [09:18<11:45, 11.82it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  44%|▍| 6606/14932 [09:15<11:39, 11.89it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  44%|▍| 6606/14932 [09:15<11:39, 11.89it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -61014,7 +61002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6597/14932 [09:18<11:45, 11.82it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  44%|▍| 6607/14932 [09:15<11:39, 11.89it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  44%|▍| 6607/14932 [09:15<11:39, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -61022,8 +61011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6598/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  44%|▍| 6598/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  44%|▍| 6608/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  44%|▍| 6608/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -61031,8 +61020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6599/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  44%|▍| 6599/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  44%|▍| 6609/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  44%|▍| 6609/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -61040,8 +61029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6600/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  44%|▍| 6600/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  44%|▍| 6610/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  44%|▍| 6610/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -61049,8 +61038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6601/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  44%|▍| 6601/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  44%|▍| 6611/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  44%|▍| 6611/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -61058,8 +61047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6602/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  44%|▍| 6602/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  44%|▍| 6612/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  44%|▍| 6612/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -61067,8 +61056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6603/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  44%|▍| 6603/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  44%|▍| 6613/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  44%|▍| 6613/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -61076,8 +61065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6604/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  44%|▍| 6604/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  44%|▍| 6614/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  44%|▍| 6614/14932 [09:15<11:39, 11.90it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -61085,8 +61074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6605/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  44%|▍| 6605/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  44%|▍| 6615/14932 [09:16<11:39, 11.90it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  44%|▍| 6615/14932 [09:16<11:39, 11.90it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -61094,8 +61083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6606/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  44%|▍| 6606/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  44%|▍| 6616/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  44%|▍| 6616/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -61103,8 +61092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6607/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  44%|▍| 6607/14932 [09:18<11:44, 11.82it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  44%|▍| 6617/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  44%|▍| 6617/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -61112,8 +61101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6608/14932 [09:19<11:44, 11.82it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  44%|▍| 6608/14932 [09:19<11:44, 11.82it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  44%|▍| 6618/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  44%|▍| 6618/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -61121,8 +61110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6609/14932 [09:19<11:44, 11.82it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  44%|▍| 6609/14932 [09:19<11:44, 11.82it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  44%|▍| 6619/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  44%|▍| 6619/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -61130,8 +61119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6610/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  44%|▍| 6610/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  44%|▍| 6620/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  44%|▍| 6620/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -61139,8 +61128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6611/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  44%|▍| 6611/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  44%|▍| 6621/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  44%|▍| 6621/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -61148,8 +61137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6612/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  44%|▍| 6612/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  44%|▍| 6622/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  44%|▍| 6622/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -61157,8 +61146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6613/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  44%|▍| 6613/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  44%|▍| 6623/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  44%|▍| 6623/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -61166,8 +61155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6614/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  44%|▍| 6614/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  44%|▍| 6624/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  44%|▍| 6624/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -61175,8 +61164,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6615/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  44%|▍| 6615/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  44%|▍| 6625/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -61184,8 +61172,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6616/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  44%|▍| 6616/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  44%|▍| 6625/14932 [09:16<11:38, 11.90it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -61193,8 +61180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6617/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  44%|▍| 6617/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  44%|▍| 6626/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  44%|▍| 6626/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=0.70"
      ]
     },
     {
@@ -61202,8 +61189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6618/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  44%|▍| 6618/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  44%|▍| 6627/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=0.70\r",
+      "Epoch 0:  44%|▍| 6627/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -61211,8 +61198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6619/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  44%|▍| 6619/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  44%|▍| 6628/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  44%|▍| 6628/14932 [09:17<11:38, 11.90it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -61220,8 +61207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6620/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  44%|▍| 6620/14932 [09:19<11:43, 11.82it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  44%|▍| 6629/14932 [09:17<11:37, 11.90it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  44%|▍| 6629/14932 [09:17<11:37, 11.90it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -61229,8 +61216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6621/14932 [09:19<11:42, 11.82it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  44%|▍| 6621/14932 [09:19<11:42, 11.82it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  44%|▍| 6630/14932 [09:17<11:38, 11.89it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  44%|▍| 6630/14932 [09:17<11:38, 11.89it/s, v_num=ui8w, train/loss=5.09"
      ]
     },
     {
@@ -61238,8 +61225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6622/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  44%|▍| 6622/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  44%|▍| 6631/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=5.09\r",
+      "Epoch 0:  44%|▍| 6631/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -61247,8 +61234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6623/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  44%|▍| 6623/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  44%|▍| 6632/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  44%|▍| 6632/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -61256,8 +61243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6624/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  44%|▍| 6624/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  44%|▍| 6633/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  44%|▍| 6633/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -61265,8 +61252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6625/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  44%|▍| 6625/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  44%|▍| 6634/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  44%|▍| 6634/14932 [09:17<11:37, 11.89it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -61274,8 +61261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6626/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  44%|▍| 6626/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  44%|▍| 6635/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  44%|▍| 6635/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -61283,8 +61270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6627/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  44%|▍| 6627/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  44%|▍| 6636/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  44%|▍| 6636/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -61292,8 +61279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6628/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  44%|▍| 6628/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  44%|▍| 6637/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  44%|▍| 6637/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -61301,8 +61288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6629/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  44%|▍| 6629/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  44%|▍| 6638/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  44%|▍| 6638/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -61310,8 +61297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6630/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  44%|▍| 6630/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  44%|▍| 6639/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  44%|▍| 6639/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -61319,8 +61306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6631/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  44%|▍| 6631/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  44%|▍| 6640/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  44%|▍| 6640/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -61328,8 +61315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6632/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  44%|▍| 6632/14932 [09:20<11:42, 11.82it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  44%|▍| 6641/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  44%|▍| 6641/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -61337,8 +61324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6633/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  44%|▍| 6633/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  44%|▍| 6642/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  44%|▍| 6642/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -61346,8 +61333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6634/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  44%|▍| 6634/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  44%|▍| 6643/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  44%|▍| 6643/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -61355,8 +61342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6635/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  44%|▍| 6635/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=5.25"
+      "Epoch 0:  44%|▍| 6644/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  44%|▍| 6644/14932 [09:18<11:37, 11.89it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -61364,8 +61351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6636/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=5.25\r",
-      "Epoch 0:  44%|▍| 6636/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  45%|▍| 6645/14932 [09:18<11:36, 11.89it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  45%|▍| 6645/14932 [09:18<11:36, 11.89it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -61373,8 +61360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6637/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  44%|▍| 6637/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  45%|▍| 6646/14932 [09:18<11:36, 11.89it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  45%|▍| 6646/14932 [09:18<11:36, 11.89it/s, v_num=ui8w, train/loss=1.39"
      ]
     },
     {
@@ -61382,8 +61369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6638/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  44%|▍| 6638/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  45%|▍| 6647/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=1.39\r",
+      "Epoch 0:  45%|▍| 6647/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -61391,8 +61378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6639/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  44%|▍| 6639/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  45%|▍| 6648/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  45%|▍| 6648/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -61400,8 +61387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6640/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  44%|▍| 6640/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  45%|▍| 6649/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  45%|▍| 6649/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -61409,8 +61396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6641/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  44%|▍| 6641/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  45%|▍| 6650/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  45%|▍| 6650/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -61418,8 +61405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6642/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  44%|▍| 6642/14932 [09:21<11:41, 11.82it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  45%|▍| 6651/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  45%|▍| 6651/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -61427,8 +61414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6643/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  44%|▍| 6643/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  45%|▍| 6652/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  45%|▍| 6652/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -61436,8 +61423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  44%|▍| 6644/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  44%|▍| 6644/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  45%|▍| 6653/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  45%|▍| 6653/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=1.22"
      ]
     },
     {
@@ -61445,8 +61432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6645/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  45%|▍| 6645/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  45%|▍| 6654/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=1.22\r",
+      "Epoch 0:  45%|▍| 6654/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -61454,8 +61441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6646/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  45%|▍| 6646/14932 [09:21<11:40, 11.83it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  45%|▍| 6655/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  45%|▍| 6655/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -61463,8 +61450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6647/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  45%|▍| 6647/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  45%|▍| 6656/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  45%|▍| 6656/14932 [09:19<11:36, 11.89it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -61472,8 +61459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6648/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  45%|▍| 6648/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  45%|▍| 6657/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  45%|▍| 6657/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -61481,8 +61468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6649/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  45%|▍| 6649/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  45%|▍| 6658/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  45%|▍| 6658/14932 [09:19<11:35, 11.89it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -61490,8 +61477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6650/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  45%|▍| 6650/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  45%|▍| 6659/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  45%|▍| 6659/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -61499,8 +61486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6651/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  45%|▍| 6651/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  45%|▍| 6660/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  45%|▍| 6660/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -61508,8 +61495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6652/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  45%|▍| 6652/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  45%|▍| 6661/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  45%|▍| 6661/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -61517,8 +61504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6653/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  45%|▍| 6653/14932 [09:22<11:40, 11.83it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  45%|▍| 6662/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  45%|▍| 6662/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -61526,8 +61513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6654/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  45%|▍| 6654/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  45%|▍| 6663/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  45%|▍| 6663/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -61535,8 +61522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6655/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  45%|▍| 6655/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  45%|▍| 6664/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  45%|▍| 6664/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -61544,8 +61531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6656/14932 [09:22<11:39, 11.82it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  45%|▍| 6656/14932 [09:22<11:39, 11.82it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  45%|▍| 6665/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  45%|▍| 6665/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=0.87"
      ]
     },
     {
@@ -61553,8 +61540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6657/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  45%|▍| 6657/14932 [09:22<11:39, 11.83it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  45%|▍| 6666/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=0.87\r",
+      "Epoch 0:  45%|▍| 6666/14932 [09:20<11:35, 11.89it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -61562,8 +61549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6658/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  45%|▍| 6658/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  45%|▍| 6667/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  45%|▍| 6667/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -61571,8 +61558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6659/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  45%|▍| 6659/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  45%|▍| 6668/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  45%|▍| 6668/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -61580,8 +61567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6660/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  45%|▍| 6660/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  45%|▍| 6669/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  45%|▍| 6669/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -61589,8 +61576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6661/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  45%|▍| 6661/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  45%|▍| 6670/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  45%|▍| 6670/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -61598,8 +61585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6662/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  45%|▍| 6662/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  45%|▍| 6671/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  45%|▍| 6671/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -61607,8 +61594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6663/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  45%|▍| 6663/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  45%|▍| 6672/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  45%|▍| 6672/14932 [09:20<11:34, 11.89it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -61616,8 +61603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6664/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  45%|▍| 6664/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  45%|▍| 6673/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  45%|▍| 6673/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -61625,8 +61612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6665/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  45%|▍| 6665/14932 [09:23<11:39, 11.83it/s, v_num=o30c, train/loss=1.19"
+      "Epoch 0:  45%|▍| 6674/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  45%|▍| 6674/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -61634,8 +61621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6666/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=1.19\r",
-      "Epoch 0:  45%|▍| 6666/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  45%|▍| 6675/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  45%|▍| 6675/14932 [09:21<11:34, 11.89it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -61643,8 +61630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6667/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  45%|▍| 6667/14932 [09:23<11:39, 11.82it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  45%|▍| 6676/14932 [09:21<11:34, 11.90it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  45%|▍| 6676/14932 [09:21<11:34, 11.90it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -61652,8 +61639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6668/14932 [09:23<11:38, 11.82it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  45%|▍| 6668/14932 [09:23<11:38, 11.82it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  45%|▍| 6677/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  45%|▍| 6677/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -61661,8 +61648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6669/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  45%|▍| 6669/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  45%|▍| 6678/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  45%|▍| 6678/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -61670,8 +61657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6670/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  45%|▍| 6670/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  45%|▍| 6679/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  45%|▍| 6679/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -61679,8 +61666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6671/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  45%|▍| 6671/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  45%|▍| 6680/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  45%|▍| 6680/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -61688,8 +61675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6672/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  45%|▍| 6672/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  45%|▍| 6681/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  45%|▍| 6681/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -61697,8 +61684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6673/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  45%|▍| 6673/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  45%|▍| 6682/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  45%|▍| 6682/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -61706,8 +61693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6674/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  45%|▍| 6674/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  45%|▍| 6683/14932 [09:21<11:33, 11.89it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  45%|▍| 6683/14932 [09:21<11:33, 11.89it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -61715,8 +61702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6675/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  45%|▍| 6675/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  45%|▍| 6684/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  45%|▍| 6684/14932 [09:21<11:33, 11.90it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -61724,8 +61711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6676/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  45%|▍| 6676/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  45%|▍| 6685/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  45%|▍| 6685/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -61733,8 +61720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6677/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  45%|▍| 6677/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  45%|▍| 6686/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  45%|▍| 6686/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -61742,8 +61729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6678/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  45%|▍| 6678/14932 [09:24<11:38, 11.82it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  45%|▍| 6687/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  45%|▍| 6687/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -61751,8 +61738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6679/14932 [09:24<11:37, 11.82it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  45%|▍| 6679/14932 [09:24<11:37, 11.82it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  45%|▍| 6688/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  45%|▍| 6688/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -61760,8 +61747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6680/14932 [09:24<11:37, 11.82it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  45%|▍| 6680/14932 [09:24<11:37, 11.82it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  45%|▍| 6689/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  45%|▍| 6689/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -61769,8 +61756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6681/14932 [09:24<11:37, 11.83it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  45%|▍| 6681/14932 [09:24<11:37, 11.83it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  45%|▍| 6690/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  45%|▍| 6690/14932 [09:22<11:33, 11.89it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -61778,8 +61765,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6682/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  45%|▍| 6682/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  45%|▍| 6691/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -61787,8 +61773,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6683/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  45%|▍| 6683/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  45%|▍| 6691/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -61796,8 +61781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6684/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  45%|▍| 6684/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  45%|▍| 6692/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  45%|▍| 6692/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -61805,8 +61790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6685/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  45%|▍| 6685/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  45%|▍| 6693/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:  45%|▍| 6693/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -61814,8 +61799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6686/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  45%|▍| 6686/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  45%|▍| 6694/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  45%|▍| 6694/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -61823,8 +61808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6687/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  45%|▍| 6687/14932 [09:25<11:37, 11.83it/s, v_num=o30c, train/loss=1.50"
+      "Epoch 0:  45%|▍| 6695/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  45%|▍| 6695/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -61832,8 +61817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6688/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=1.50\r",
-      "Epoch 0:  45%|▍| 6688/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  45%|▍| 6696/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  45%|▍| 6696/14932 [09:22<11:32, 11.89it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -61841,8 +61826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6689/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  45%|▍| 6689/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  45%|▍| 6697/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  45%|▍| 6697/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -61850,8 +61835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6690/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  45%|▍| 6690/14932 [09:25<11:37, 11.82it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  45%|▍| 6698/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  45%|▍| 6698/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -61859,8 +61844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6691/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  45%|▍| 6691/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  45%|▍| 6699/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  45%|▍| 6699/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=0.84"
      ]
     },
     {
@@ -61868,8 +61853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6692/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  45%|▍| 6692/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  45%|▍| 6700/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=0.84\r",
+      "Epoch 0:  45%|▍| 6700/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -61877,8 +61862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6693/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  45%|▍| 6693/14932 [09:25<11:36, 11.83it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  45%|▍| 6701/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  45%|▍| 6701/14932 [09:23<11:32, 11.89it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -61886,8 +61871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6694/14932 [09:26<11:36, 11.82it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  45%|▍| 6694/14932 [09:26<11:36, 11.82it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  45%|▍| 6702/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  45%|▍| 6702/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -61895,8 +61880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6695/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  45%|▍| 6695/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  45%|▍| 6703/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  45%|▍| 6703/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -61904,8 +61889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6696/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  45%|▍| 6696/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  45%|▍| 6704/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  45%|▍| 6704/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -61913,8 +61898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6697/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  45%|▍| 6697/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  45%|▍| 6705/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  45%|▍| 6705/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -61922,8 +61907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6698/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  45%|▍| 6698/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  45%|▍| 6706/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  45%|▍| 6706/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -61931,8 +61916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6699/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  45%|▍| 6699/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  45%|▍| 6707/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  45%|▍| 6707/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -61940,8 +61925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6700/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  45%|▍| 6700/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  45%|▍| 6708/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  45%|▍| 6708/14932 [09:23<11:31, 11.89it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -61949,8 +61934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6701/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  45%|▍| 6701/14932 [09:26<11:36, 11.83it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  45%|▍| 6709/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  45%|▍| 6709/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -61958,7 +61943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6702/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  45%|▍| 6710/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  45%|▍| 6710/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -61966,7 +61952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6702/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  45%|▍| 6711/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  45%|▍| 6711/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -61974,8 +61961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6703/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  45%|▍| 6703/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  45%|▍| 6712/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  45%|▍| 6712/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -61983,8 +61970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6704/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  45%|▍| 6704/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  45%|▍| 6713/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  45%|▍| 6713/14932 [09:24<11:31, 11.89it/s, v_num=ui8w, train/loss=1.13"
      ]
     },
     {
@@ -61992,8 +61979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6705/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  45%|▍| 6705/14932 [09:26<11:35, 11.83it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  45%|▍| 6714/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=1.13\r",
+      "Epoch 0:  45%|▍| 6714/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -62001,8 +61988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6706/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  45%|▍| 6706/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  45%|▍| 6715/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  45%|▍| 6715/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -62010,8 +61997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6707/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  45%|▍| 6707/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  45%|▍| 6716/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  45%|▍| 6716/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -62019,8 +62006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6708/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  45%|▍| 6708/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  45%|▍| 6717/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  45%|▍| 6717/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -62028,8 +62015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6709/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  45%|▍| 6709/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  45%|▍| 6718/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  45%|▍| 6718/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -62037,8 +62024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6710/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  45%|▍| 6710/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  45%|▍| 6719/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  45%|▍| 6719/14932 [09:24<11:30, 11.89it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -62046,8 +62033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6711/14932 [09:27<11:35, 11.82it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  45%|▍| 6711/14932 [09:27<11:35, 11.82it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  45%|▍| 6720/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  45%|▍| 6720/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -62055,8 +62042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6712/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  45%|▍| 6712/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  45%|▍| 6721/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  45%|▍| 6721/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -62064,8 +62051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6713/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  45%|▍| 6713/14932 [09:27<11:35, 11.83it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  45%|▍| 6722/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  45%|▍| 6722/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -62073,8 +62060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6714/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  45%|▍| 6714/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  45%|▍| 6723/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  45%|▍| 6723/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -62082,8 +62069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6715/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  45%|▍| 6715/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  45%|▍| 6724/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  45%|▍| 6724/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -62091,8 +62078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6716/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  45%|▍| 6716/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  45%|▍| 6725/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  45%|▍| 6725/14932 [09:25<11:30, 11.89it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -62100,8 +62087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6717/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  45%|▍| 6717/14932 [09:27<11:34, 11.83it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  45%|▍| 6726/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  45%|▍| 6726/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -62109,8 +62096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6718/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  45%|▍| 6718/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  45%|▍| 6727/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  45%|▍| 6727/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -62118,8 +62105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6719/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  45%|▍| 6719/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  45%|▍| 6728/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  45%|▍| 6728/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -62127,8 +62114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6720/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  45%|▍| 6720/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  45%|▍| 6729/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  45%|▍| 6729/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -62136,8 +62123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6721/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  45%|▍| 6721/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  45%|▍| 6730/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  45%|▍| 6730/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -62145,8 +62132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6722/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  45%|▍| 6722/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:  45%|▍| 6731/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  45%|▍| 6731/14932 [09:25<11:29, 11.89it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -62154,8 +62141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6723/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:  45%|▍| 6723/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  45%|▍| 6732/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  45%|▍| 6732/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -62163,8 +62150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6724/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  45%|▍| 6724/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  45%|▍| 6733/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  45%|▍| 6733/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -62172,8 +62159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6725/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  45%|▍| 6725/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  45%|▍| 6734/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  45%|▍| 6734/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -62181,8 +62168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6726/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  45%|▍| 6726/14932 [09:28<11:34, 11.82it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  45%|▍| 6735/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  45%|▍| 6735/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -62190,8 +62177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6727/14932 [09:29<11:34, 11.82it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  45%|▍| 6727/14932 [09:29<11:34, 11.82it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  45%|▍| 6736/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  45%|▍| 6736/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -62199,8 +62186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6728/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  45%|▍| 6728/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  45%|▍| 6737/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  45%|▍| 6737/14932 [09:26<11:29, 11.89it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -62208,8 +62195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6729/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  45%|▍| 6729/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  45%|▍| 6738/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  45%|▍| 6738/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -62217,8 +62204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6730/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  45%|▍| 6730/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  45%|▍| 6739/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  45%|▍| 6739/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -62226,8 +62213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6731/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  45%|▍| 6731/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  45%|▍| 6740/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  45%|▍| 6740/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -62235,8 +62222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6732/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  45%|▍| 6732/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  45%|▍| 6741/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  45%|▍| 6741/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -62244,8 +62231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6733/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  45%|▍| 6733/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  45%|▍| 6742/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  45%|▍| 6742/14932 [09:26<11:28, 11.89it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -62253,7 +62240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6734/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  45%|▍| 6743/14932 [09:26<11:28, 11.90it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  45%|▍| 6743/14932 [09:26<11:28, 11.90it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -62261,7 +62249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6734/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  45%|▍| 6744/14932 [09:26<11:28, 11.90it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  45%|▍| 6744/14932 [09:26<11:28, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -62269,8 +62258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6735/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  45%|▍| 6735/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  45%|▍| 6745/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  45%|▍| 6745/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -62278,8 +62267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6736/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  45%|▍| 6736/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  45%|▍| 6746/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  45%|▍| 6746/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -62287,8 +62276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6737/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  45%|▍| 6737/14932 [09:29<11:33, 11.82it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  45%|▍| 6747/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  45%|▍| 6747/14932 [09:27<11:28, 11.90it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -62296,8 +62285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6738/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  45%|▍| 6738/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  45%|▍| 6748/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  45%|▍| 6748/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -62305,8 +62294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6739/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  45%|▍| 6739/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  45%|▍| 6749/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  45%|▍| 6749/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -62314,8 +62303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6740/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  45%|▍| 6740/14932 [09:29<11:32, 11.82it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  45%|▍| 6750/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  45%|▍| 6750/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -62323,8 +62312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6741/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  45%|▍| 6741/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  45%|▍| 6751/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  45%|▍| 6751/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -62332,8 +62321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6742/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  45%|▍| 6742/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  45%|▍| 6752/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  45%|▍| 6752/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -62341,8 +62330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6743/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  45%|▍| 6743/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=4.97"
+      "Epoch 0:  45%|▍| 6753/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  45%|▍| 6753/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -62350,8 +62339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6744/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=4.97\r",
-      "Epoch 0:  45%|▍| 6744/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  45%|▍| 6754/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  45%|▍| 6754/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -62359,8 +62348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6745/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  45%|▍| 6745/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  45%|▍| 6755/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  45%|▍| 6755/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -62368,8 +62357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6746/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  45%|▍| 6746/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  45%|▍| 6756/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  45%|▍| 6756/14932 [09:27<11:27, 11.90it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -62377,8 +62366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6747/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  45%|▍| 6747/14932 [09:30<11:32, 11.83it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  45%|▍| 6757/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  45%|▍| 6757/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -62386,8 +62375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6748/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  45%|▍| 6748/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  45%|▍| 6758/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  45%|▍| 6758/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -62395,8 +62384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6749/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  45%|▍| 6749/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  45%|▍| 6759/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  45%|▍| 6759/14932 [09:28<11:27, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -62404,8 +62393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6750/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  45%|▍| 6750/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  45%|▍| 6760/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  45%|▍| 6760/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -62413,8 +62402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6751/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  45%|▍| 6751/14932 [09:30<11:31, 11.83it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  45%|▍| 6761/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  45%|▍| 6761/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -62422,8 +62411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6752/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  45%|▍| 6752/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  45%|▍| 6762/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  45%|▍| 6762/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -62431,8 +62420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6753/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  45%|▍| 6753/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  45%|▍| 6763/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  45%|▍| 6763/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -62440,8 +62429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6754/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  45%|▍| 6754/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  45%|▍| 6764/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  45%|▍| 6764/14932 [09:28<11:27, 11.89it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -62449,8 +62438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6755/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  45%|��| 6755/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  45%|▍| 6765/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  45%|▍| 6765/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -62458,8 +62447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6756/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  45%|▍| 6756/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  45%|▍| 6766/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  45%|▍| 6766/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -62467,8 +62456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6757/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  45%|▍| 6757/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  45%|▍| 6767/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  45%|▍| 6767/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -62476,8 +62465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6758/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  45%|▍| 6758/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  45%|▍| 6768/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  45%|▍| 6768/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -62485,8 +62474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6759/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  45%|▍| 6759/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  45%|▍| 6769/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  45%|▍| 6769/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -62494,7 +62483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6760/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  45%|▍| 6770/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  45%|▍| 6770/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -62502,7 +62492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6760/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  45%|▍| 6771/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  45%|▍| 6771/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -62510,8 +62501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6761/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  45%|▍| 6761/14932 [09:31<11:31, 11.82it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  45%|▍| 6772/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  45%|▍| 6772/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -62519,8 +62510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6762/14932 [09:31<11:30, 11.82it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  45%|▍| 6762/14932 [09:31<11:30, 11.82it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  45%|▍| 6773/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  45%|▍| 6773/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -62528,8 +62519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6763/14932 [09:31<11:30, 11.83it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  45%|▍| 6763/14932 [09:31<11:30, 11.83it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  45%|▍| 6774/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  45%|▍| 6774/14932 [09:29<11:26, 11.89it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -62537,8 +62528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6764/14932 [09:31<11:30, 11.83it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  45%|▍| 6764/14932 [09:31<11:30, 11.83it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  45%|▍| 6775/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  45%|▍| 6775/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -62546,8 +62537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6765/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  45%|▍| 6765/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  45%|▍| 6776/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  45%|▍| 6776/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -62555,8 +62546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6766/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  45%|▍| 6766/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  45%|▍| 6777/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  45%|▍| 6777/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -62564,8 +62555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6767/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  45%|▍| 6767/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  45%|▍| 6778/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  45%|▍| 6778/14932 [09:29<11:25, 11.89it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -62573,8 +62564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6768/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  45%|▍| 6768/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  45%|▍| 6779/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  45%|▍| 6779/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -62582,8 +62573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6769/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  45%|▍| 6769/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  45%|▍| 6780/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  45%|▍| 6780/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -62591,8 +62582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6770/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  45%|▍| 6770/14932 [09:32<11:30, 11.83it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  45%|▍| 6781/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  45%|▍| 6781/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -62600,8 +62591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6771/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  45%|▍| 6771/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  45%|▍| 6782/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  45%|▍| 6782/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -62609,8 +62600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6772/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  45%|▍| 6772/14932 [09:32<11:30, 11.82it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  45%|▍| 6783/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  45%|▍| 6783/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -62618,8 +62609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6773/14932 [09:32<11:29, 11.82it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  45%|▍| 6773/14932 [09:32<11:29, 11.82it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  45%|▍| 6784/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  45%|▍| 6784/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -62627,8 +62618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6774/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  45%|▍| 6774/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  45%|▍| 6785/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  45%|▍| 6785/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -62636,8 +62627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6775/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  45%|▍| 6775/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  45%|▍| 6786/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  45%|▍| 6786/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -62645,8 +62636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6776/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  45%|▍| 6776/14932 [09:32<11:29, 11.83it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  45%|▍| 6787/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  45%|▍| 6787/14932 [09:30<11:25, 11.89it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -62654,8 +62645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6777/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  45%|▍| 6777/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  45%|▍| 6788/14932 [09:30<11:24, 11.89it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  45%|▍| 6788/14932 [09:30<11:24, 11.89it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -62663,8 +62654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6778/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  45%|▍| 6778/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  45%|▍| 6789/14932 [09:30<11:24, 11.89it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  45%|▍| 6789/14932 [09:30<11:24, 11.89it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -62672,8 +62663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6779/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  45%|▍| 6779/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  45%|▍| 6790/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  45%|▍| 6790/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -62681,8 +62672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6780/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  45%|▍| 6780/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  45%|▍| 6791/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  45%|▍| 6791/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -62690,8 +62681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6781/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  45%|▍| 6781/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  45%|▍| 6792/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  45%|▍| 6792/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -62699,8 +62690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6782/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  45%|▍| 6782/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  45%|▍| 6793/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  45%|▍| 6793/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -62708,8 +62699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6783/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  45%|▍| 6783/14932 [09:33<11:29, 11.83it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  45%|▍| 6794/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  45%|▍| 6794/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -62717,8 +62708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6784/14932 [09:33<11:29, 11.82it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  45%|▍| 6784/14932 [09:33<11:29, 11.82it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  46%|▍| 6795/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  46%|▍| 6795/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -62726,8 +62717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6785/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  45%|▍| 6785/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  46%|▍| 6796/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  46%|▍| 6796/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -62735,8 +62726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6786/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  45%|▍| 6786/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  46%|▍| 6797/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  46%|▍| 6797/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -62744,8 +62735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6787/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  45%|▍| 6787/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  46%|▍| 6798/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  46%|▍| 6798/14932 [09:31<11:24, 11.89it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -62753,8 +62744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6788/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  45%|▍| 6788/14932 [09:33<11:28, 11.83it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  46%|▍| 6799/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  46%|▍| 6799/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -62762,8 +62753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6789/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  45%|▍| 6789/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=1.44"
+      "Epoch 0:  46%|▍| 6800/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  46%|▍| 6800/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -62771,8 +62762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6790/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=1.44\r",
-      "Epoch 0:  45%|▍| 6790/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  46%|▍| 6801/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  46%|▍| 6801/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -62780,8 +62771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6791/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  45%|▍| 6791/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  46%|▍| 6802/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  46%|▍| 6802/14932 [09:31<11:23, 11.89it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -62789,8 +62780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6792/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  45%|▍| 6792/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  46%|▍| 6803/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  46%|▍| 6803/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -62798,8 +62789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6793/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  45%|▍| 6793/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  46%|▍| 6804/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  46%|▍| 6804/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -62807,8 +62798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  45%|▍| 6794/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  45%|▍| 6794/14932 [09:34<11:28, 11.83it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  46%|▍| 6805/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  46%|▍| 6805/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -62816,8 +62807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6795/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  46%|▍| 6795/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  46%|▍| 6806/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  46%|▍| 6806/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=1.10"
      ]
     },
     {
@@ -62825,8 +62816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6796/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  46%|▍| 6796/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  46%|▍| 6807/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=1.10\r",
+      "Epoch 0:  46%|▍| 6807/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -62834,8 +62825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6797/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  46%|▍| 6797/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  46%|▍| 6808/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  46%|▍| 6808/14932 [09:32<11:23, 11.89it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -62843,8 +62834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6798/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  46%|▍| 6798/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  46%|▍| 6809/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  46%|▍| 6809/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -62852,8 +62843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6799/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  46%|▍| 6799/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  46%|▍| 6810/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  46%|▍| 6810/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -62861,8 +62852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6800/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  46%|▍| 6800/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  46%|▍| 6811/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  46%|▍| 6811/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -62870,8 +62861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6801/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  46%|▍| 6801/14932 [09:34<11:27, 11.83it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  46%|▍| 6812/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  46%|▍| 6812/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -62879,8 +62870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6802/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  46%|▍| 6802/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=0.90"
+      "Epoch 0:  46%|▍| 6813/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  46%|▍| 6813/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -62888,8 +62879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6803/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=0.90\r",
-      "Epoch 0:  46%|▍| 6803/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  46%|▍| 6814/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  46%|▍| 6814/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -62897,8 +62888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6804/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  46%|▍| 6804/14932 [09:35<11:27, 11.83it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  46%|▍| 6815/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  46%|▍| 6815/14932 [09:32<11:22, 11.89it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -62906,8 +62897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6805/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  46%|▍| 6805/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  46%|▍| 6816/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  46%|▍| 6816/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -62915,8 +62906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6806/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  46%|▍| 6806/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  46%|▍| 6817/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  46%|▍| 6817/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -62924,8 +62915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6807/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  46%|▍| 6807/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  46%|▍| 6818/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  46%|▍| 6818/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -62933,8 +62924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6808/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  46%|▍| 6808/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  46%|▍| 6819/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  46%|▍| 6819/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -62942,8 +62933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6809/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  46%|▍| 6809/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  46%|▍| 6820/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  46%|▍| 6820/14932 [09:33<11:22, 11.89it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -62951,7 +62942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6810/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  46%|▍| 6821/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  46%|▍| 6821/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -62959,7 +62951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6810/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  46%|▍| 6822/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  46%|▍| 6822/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -62967,8 +62960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6811/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  46%|▍| 6811/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  46%|▍| 6823/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  46%|▍| 6823/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -62976,8 +62969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6812/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  46%|▍| 6812/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  46%|▍| 6824/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  46%|▍| 6824/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -62985,8 +62978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6813/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  46%|▍| 6813/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  46%|▍| 6825/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  46%|▍| 6825/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -62994,8 +62987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6814/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  46%|▍| 6814/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  46%|▍| 6826/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  46%|▍| 6826/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -63003,8 +62996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6815/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  46%|▍| 6815/14932 [09:35<11:26, 11.83it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  46%|▍| 6827/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  46%|▍| 6827/14932 [09:33<11:21, 11.89it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -63012,8 +63005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6816/14932 [09:36<11:26, 11.83it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  46%|▍| 6816/14932 [09:36<11:26, 11.83it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  46%|▍| 6828/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  46%|▍| 6828/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -63021,8 +63014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6817/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  46%|▍| 6817/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  46%|▍| 6829/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  46%|▍| 6829/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -63030,8 +63023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6818/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  46%|▍| 6818/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  46%|▍| 6830/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  46%|▍| 6830/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -63039,8 +63032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6819/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  46%|▍| 6819/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  46%|▍| 6831/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  46%|▍| 6831/14932 [09:34<11:21, 11.89it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -63048,8 +63041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6820/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  46%|▍| 6820/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  46%|▍| 6832/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  46%|▍| 6832/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -63057,8 +63050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6821/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  46%|▍| 6821/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  46%|▍| 6833/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  46%|▍| 6833/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -63066,8 +63059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6822/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  46%|▍| 6822/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  46%|▍| 6834/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  46%|▍| 6834/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -63075,8 +63068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6823/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  46%|▍| 6823/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  46%|▍| 6835/14932 [09:34<11:20, 11.90it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  46%|▍| 6835/14932 [09:34<11:20, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -63084,8 +63077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6824/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  46%|▍| 6824/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  46%|▍| 6836/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  46%|▍| 6836/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -63093,8 +63086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6825/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  46%|▍| 6825/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  46%|▍| 6837/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  46%|▍| 6837/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -63102,8 +63095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6826/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  46%|▍| 6826/14932 [09:36<11:25, 11.83it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  46%|▍| 6838/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  46%|▍| 6838/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -63111,8 +63104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6827/14932 [09:36<11:24, 11.83it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  46%|▍| 6827/14932 [09:36<11:24, 11.83it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  46%|▍| 6839/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  46%|▍| 6839/14932 [09:34<11:20, 11.89it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -63120,8 +63113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6828/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  46%|▍| 6828/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  46%|▍| 6840/14932 [09:35<11:20, 11.89it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  46%|▍| 6840/14932 [09:35<11:20, 11.89it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -63129,8 +63122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6829/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  46%|▍| 6829/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  46%|▍| 6841/14932 [09:35<11:20, 11.90it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  46%|▍| 6841/14932 [09:35<11:20, 11.90it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -63138,8 +63131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6830/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  46%|▍| 6830/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  46%|▍| 6842/14932 [09:35<11:20, 11.90it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  46%|▍| 6842/14932 [09:35<11:20, 11.90it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -63147,8 +63140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6831/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  46%|▍| 6831/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  46%|▍| 6843/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  46%|▍| 6843/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -63156,8 +63149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6832/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  46%|▍| 6832/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  46%|▍| 6844/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  46%|▍| 6844/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -63165,8 +63158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6833/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  46%|▍| 6833/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  46%|▍| 6845/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  46%|▍| 6845/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=0.88"
      ]
     },
     {
@@ -63174,8 +63167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6834/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  46%|▍| 6834/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  46%|▍| 6846/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=0.88\r",
+      "Epoch 0:  46%|▍| 6846/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -63183,8 +63176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6835/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  46%|▍| 6835/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  46%|▍| 6847/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  46%|▍| 6847/14932 [09:35<11:19, 11.90it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -63192,8 +63185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6836/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  46%|▍| 6836/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  46%|▍| 6848/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  46%|▍| 6848/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -63201,8 +63194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6837/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  46%|▍| 6837/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  46%|▍| 6849/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  46%|▍| 6849/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -63210,8 +63203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6838/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  46%|▍| 6838/14932 [09:37<11:24, 11.83it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  46%|▍| 6850/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  46%|▍| 6850/14932 [09:35<11:19, 11.89it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -63219,8 +63212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6839/14932 [09:37<11:23, 11.83it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  46%|▍| 6839/14932 [09:37<11:23, 11.83it/s, v_num=o30c, train/loss=1.10"
+      "Epoch 0:  46%|▍| 6851/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  46%|▍| 6851/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -63228,8 +63221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6840/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=1.10\r",
-      "Epoch 0:  46%|▍| 6840/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  46%|▍| 6852/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  46%|▍| 6852/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=0.69"
      ]
     },
     {
@@ -63237,8 +63230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6841/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  46%|▍| 6841/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  46%|▍| 6853/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=0.69\r",
+      "Epoch 0:  46%|▍| 6853/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -63246,8 +63239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6842/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  46%|▍| 6842/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  46%|▍| 6854/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  46%|▍| 6854/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -63255,8 +63248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6843/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  46%|▍| 6843/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  46%|▍| 6855/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  46%|▍| 6855/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -63264,8 +63257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6844/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  46%|▍| 6844/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  46%|▍| 6856/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  46%|▍| 6856/14932 [09:36<11:19, 11.89it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -63273,8 +63266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6845/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  46%|▍| 6845/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  46%|▍| 6857/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  46%|▍| 6857/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -63282,8 +63275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6846/14932 [09:38<11:23, 11.84it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  46%|▍| 6846/14932 [09:38<11:23, 11.84it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  46%|▍| 6858/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  46%|▍| 6858/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -63291,8 +63284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6847/14932 [09:38<11:23, 11.84it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  46%|▍| 6847/14932 [09:38<11:23, 11.84it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  46%|▍| 6859/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  46%|▍| 6859/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -63300,8 +63293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6848/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  46%|▍| 6848/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  46%|▍| 6860/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  46%|▍| 6860/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -63309,8 +63302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6849/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  46%|▍| 6849/14932 [09:38<11:23, 11.83it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  46%|▍| 6861/14932 [09:36<11:18, 11.90it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  46%|▍| 6861/14932 [09:36<11:18, 11.89it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -63318,8 +63311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6850/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  46%|▍| 6850/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  46%|▍| 6862/14932 [09:36<11:18, 11.90it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  46%|▍| 6862/14932 [09:36<11:18, 11.90it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -63327,8 +63320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6851/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  46%|▍| 6851/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  46%|▍| 6863/14932 [09:36<11:18, 11.90it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  46%|▍| 6863/14932 [09:36<11:18, 11.90it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -63336,8 +63329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6852/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  46%|▍| 6852/14932 [09:38<11:22, 11.83it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  46%|▍| 6864/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  46%|▍| 6864/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -63345,8 +63338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6853/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  46%|▍| 6853/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  46%|▍| 6865/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  46%|▍| 6865/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -63354,8 +63347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6854/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  46%|▍| 6854/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  46%|▍| 6866/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  46%|▍| 6866/14932 [09:37<11:18, 11.90it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -63363,8 +63356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6855/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  46%|▍| 6855/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  46%|▍| 6867/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  46%|▍| 6867/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -63372,8 +63365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6856/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  46%|▍| 6856/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  46%|▍| 6868/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  46%|▍| 6868/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -63381,8 +63374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6857/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  46%|▍| 6857/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  46%|▍| 6869/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  46%|▍| 6869/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -63390,8 +63383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6858/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  46%|▍| 6858/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  46%|▍| 6870/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  46%|▍| 6870/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -63399,8 +63392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6859/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  46%|▍| 6859/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  46%|▍| 6871/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  46%|▍| 6871/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -63408,8 +63401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6860/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  46%|▍| 6860/14932 [09:39<11:22, 11.84it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  46%|▍| 6872/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  46%|▍| 6872/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -63417,8 +63410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6861/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  46%|▍| 6861/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  46%|▍| 6873/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  46%|▍| 6873/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -63426,8 +63419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6862/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  46%|▍| 6862/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  46%|▍| 6874/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  46%|▍| 6874/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -63435,8 +63428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6863/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  46%|▍| 6863/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  46%|▍| 6875/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  46%|▍| 6875/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -63444,8 +63437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6864/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  46%|▍| 6864/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  46%|▍| 6876/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  46%|▍| 6876/14932 [09:37<11:17, 11.90it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -63453,8 +63446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6865/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  46%|▍| 6865/14932 [09:39<11:21, 11.84it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  46%|▍| 6877/14932 [09:37<11:16, 11.90it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  46%|▍| 6877/14932 [09:37<11:16, 11.90it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -63462,8 +63455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6866/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  46%|▍| 6866/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  46%|▍| 6878/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  46%|▍| 6878/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -63471,8 +63464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6867/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  46%|▍| 6867/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  46%|▍| 6879/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  46%|▍| 6879/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -63480,8 +63473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6868/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  46%|▍| 6868/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  46%|▍| 6880/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  46%|▍| 6880/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -63489,8 +63482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6869/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  46%|▍| 6869/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  46%|▍| 6881/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  46%|▍| 6881/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -63498,8 +63491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6870/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  46%|▍| 6870/14932 [09:40<11:21, 11.84it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  46%|▍| 6882/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  46%|▍| 6882/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -63507,8 +63500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6871/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  46%|▍| 6871/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  46%|▍| 6883/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  46%|▍| 6883/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -63516,8 +63509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6872/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  46%|▍| 6872/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  46%|▍| 6884/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  46%|▍| 6884/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -63525,8 +63518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6873/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  46%|▍| 6873/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  46%|▍| 6885/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  46%|▍| 6885/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=0.42"
      ]
     },
     {
@@ -63534,8 +63527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6874/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  46%|▍| 6874/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  46%|▍| 6886/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=0.42\r",
+      "Epoch 0:  46%|▍| 6886/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -63543,8 +63536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6875/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  46%|▍| 6875/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  46%|▍| 6887/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  46%|▍| 6887/14932 [09:38<11:16, 11.90it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -63552,8 +63545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6876/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  46%|▍| 6876/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  46%|▍| 6888/14932 [09:39<11:16, 11.90it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  46%|▍| 6888/14932 [09:39<11:16, 11.90it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -63561,8 +63554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6877/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  46%|▍| 6877/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  46%|▍| 6889/14932 [09:39<11:16, 11.90it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  46%|▍| 6889/14932 [09:39<11:16, 11.90it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -63570,8 +63563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6878/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  46%|▍| 6878/14932 [09:40<11:20, 11.84it/s, v_num=o30c, train/loss=1.21"
+      "Epoch 0:  46%|▍| 6890/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  46%|▍| 6890/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -63579,8 +63572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6879/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=1.21\r",
-      "Epoch 0:  46%|▍| 6879/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  46%|▍| 6891/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  46%|▍| 6891/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -63588,8 +63581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6880/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  46%|▍| 6880/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  46%|▍| 6892/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  46%|▍| 6892/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -63597,8 +63590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6881/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  46%|▍| 6881/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  46%|▍| 6893/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  46%|▍| 6893/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -63606,8 +63599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6882/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  46%|▍| 6882/14932 [09:41<11:20, 11.84it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  46%|▍| 6894/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  46%|▍| 6894/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -63615,8 +63608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6883/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  46%|▍| 6883/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  46%|▍| 6895/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  46%|▍| 6895/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -63624,8 +63617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6884/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  46%|▍| 6884/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  46%|▍| 6896/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  46%|▍| 6896/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -63633,8 +63626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6885/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  46%|▍| 6885/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  46%|▍| 6897/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  46%|▍| 6897/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -63642,8 +63635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6886/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  46%|▍| 6886/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  46%|▍| 6898/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  46%|▍| 6898/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -63651,8 +63644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6887/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  46%|▍| 6887/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=0.74"
+      "Epoch 0:  46%|▍| 6899/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  46%|▍| 6899/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -63660,8 +63653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6888/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=0.74\r",
-      "Epoch 0:  46%|▍| 6888/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  46%|▍| 6900/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  46%|▍| 6900/14932 [09:39<11:15, 11.90it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -63669,8 +63662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6889/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  46%|▍| 6889/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  46%|▍| 6901/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  46%|▍| 6901/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=1.36"
      ]
     },
     {
@@ -63678,8 +63671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6890/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  46%|▍| 6890/14932 [09:41<11:19, 11.84it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  46%|▍| 6902/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=1.36\r",
+      "Epoch 0:  46%|▍| 6902/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -63687,8 +63680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6891/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  46%|▍| 6891/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  46%|▍| 6903/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  46%|▍| 6903/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -63696,8 +63689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6892/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  46%|▍| 6892/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  46%|▍| 6904/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  46%|▍| 6904/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -63705,8 +63698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6893/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  46%|▍| 6893/14932 [09:42<11:19, 11.84it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  46%|▍| 6905/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  46%|▍| 6905/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -63714,8 +63707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6894/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  46%|▍| 6894/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  46%|▍| 6906/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  46%|▍| 6906/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -63723,8 +63716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6895/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  46%|▍| 6895/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  46%|▍| 6907/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  46%|▍| 6907/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -63732,8 +63725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6896/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  46%|▍| 6896/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  46%|▍| 6908/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  46%|▍| 6908/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -63741,8 +63734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6897/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  46%|▍| 6897/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  46%|▍| 6909/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  46%|▍| 6909/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -63750,8 +63743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6898/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  46%|▍| 6898/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  46%|▍| 6910/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  46%|▍| 6910/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -63759,8 +63752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6899/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  46%|▍| 6899/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  46%|▍| 6911/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  46%|▍| 6911/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -63768,8 +63761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6900/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  46%|▍| 6900/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  46%|▍| 6912/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  46%|▍| 6912/14932 [09:40<11:14, 11.90it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -63777,7 +63770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6901/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  46%|▍| 6913/14932 [09:41<11:14, 11.90it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  46%|▍| 6913/14932 [09:41<11:14, 11.90it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -63785,7 +63779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6901/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  46%|▍| 6914/14932 [09:41<11:14, 11.90it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  46%|▍| 6914/14932 [09:41<11:14, 11.90it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -63793,8 +63788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6902/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  46%|▍| 6902/14932 [09:42<11:18, 11.84it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  46%|▍| 6915/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  46%|▍| 6915/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -63802,8 +63797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6903/14932 [09:43<11:18, 11.84it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  46%|▍| 6903/14932 [09:43<11:18, 11.84it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  46%|▍| 6916/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  46%|▍| 6916/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -63811,8 +63806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6904/14932 [09:43<11:18, 11.84it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  46%|▍| 6904/14932 [09:43<11:18, 11.84it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  46%|▍| 6917/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  46%|▍| 6917/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -63820,8 +63815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6905/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  46%|▍| 6905/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  46%|▍| 6918/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  46%|▍| 6918/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -63829,8 +63824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6906/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  46%|▍| 6906/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.09"
+      "Epoch 0:  46%|▍| 6919/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  46%|▍| 6919/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -63838,8 +63833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6907/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.09\r",
-      "Epoch 0:  46%|▍| 6907/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  46%|▍| 6920/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  46%|▍| 6920/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -63847,8 +63842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6908/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  46%|▍| 6908/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  46%|▍| 6921/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  46%|▍| 6921/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -63856,8 +63851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6909/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  46%|▍| 6909/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  46%|▍| 6922/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  46%|▍| 6922/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -63865,8 +63860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6910/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  46%|▍| 6910/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  46%|▍| 6923/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  46%|▍| 6923/14932 [09:41<11:13, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -63874,8 +63869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6911/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  46%|▍| 6911/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  46%|▍| 6924/14932 [09:42<11:13, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  46%|▍| 6924/14932 [09:42<11:13, 11.90it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -63883,8 +63878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6912/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  46%|▍| 6912/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  46%|▍| 6925/14932 [09:42<11:13, 11.90it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  46%|▍| 6925/14932 [09:42<11:13, 11.90it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -63892,8 +63887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6913/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  46%|▍| 6913/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  46%|▍| 6926/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  46%|▍| 6926/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -63901,8 +63896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6914/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  46%|▍| 6914/14932 [09:43<11:17, 11.84it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  46%|▍| 6927/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  46%|▍| 6927/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -63910,8 +63905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6915/14932 [09:44<11:17, 11.84it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  46%|▍| 6915/14932 [09:44<11:17, 11.84it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  46%|▍| 6928/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  46%|▍| 6928/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -63919,8 +63914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6916/14932 [09:44<11:17, 11.84it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  46%|▍| 6916/14932 [09:44<11:17, 11.84it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  46%|▍| 6929/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  46%|▍| 6929/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -63928,8 +63923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6917/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  46%|▍| 6917/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  46%|▍| 6930/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  46%|▍| 6930/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -63937,8 +63932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6918/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  46%|▍| 6918/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  46%|▍| 6931/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  46%|▍| 6931/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -63946,8 +63941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6919/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  46%|▍| 6919/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  46%|▍| 6932/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  46%|▍| 6932/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -63955,8 +63950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6920/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  46%|▍| 6920/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  46%|▍| 6933/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  46%|▍| 6933/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -63964,8 +63959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6921/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  46%|▍| 6921/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  46%|▍| 6934/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  46%|▍| 6934/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -63973,8 +63968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6922/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  46%|▍| 6922/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  46%|▍| 6935/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  46%|▍| 6935/14932 [09:42<11:12, 11.90it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -63982,8 +63977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6923/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  46%|▍| 6923/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  46%|▍| 6936/14932 [09:42<11:11, 11.90it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  46%|▍| 6936/14932 [09:42<11:11, 11.90it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -63991,8 +63986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6924/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  46%|▍| 6924/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  46%|▍| 6937/14932 [09:42<11:11, 11.90it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  46%|▍| 6937/14932 [09:42<11:11, 11.90it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -64000,8 +63995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6925/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  46%|▍| 6925/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  46%|▍| 6938/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  46%|▍| 6938/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -64009,8 +64004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6926/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  46%|▍| 6926/14932 [09:44<11:16, 11.84it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  46%|▍| 6939/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  46%|▍| 6939/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -64018,8 +64013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6927/14932 [09:44<11:15, 11.84it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  46%|▍| 6927/14932 [09:44<11:15, 11.84it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  46%|▍| 6940/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  46%|▍| 6940/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -64027,8 +64022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6928/14932 [09:44<11:15, 11.84it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  46%|▍| 6928/14932 [09:44<11:15, 11.84it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  46%|▍| 6941/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  46%|▍| 6941/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -64036,8 +64031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6929/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  46%|▍| 6929/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  46%|▍| 6942/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  46%|▍| 6942/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -64045,8 +64040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6930/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  46%|▍| 6930/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  46%|▍| 6943/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  46%|▍| 6943/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -64054,8 +64049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6931/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  46%|▍| 6931/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  47%|▍| 6944/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  47%|▍| 6944/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -64063,8 +64058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6932/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  46%|▍| 6932/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  47%|▍| 6945/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  47%|▍| 6945/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -64072,8 +64067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6933/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  46%|▍| 6933/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  47%|▍| 6946/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  47%|▍| 6946/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -64081,8 +64076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6934/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  46%|▍| 6934/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  47%|▍| 6947/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  47%|▍| 6947/14932 [09:43<11:11, 11.90it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -64090,8 +64085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6935/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  46%|▍| 6935/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  47%|▍| 6948/14932 [09:43<11:10, 11.90it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  47%|▍| 6948/14932 [09:43<11:10, 11.90it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -64099,8 +64094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6936/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  46%|▍| 6936/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  47%|▍| 6949/14932 [09:43<11:10, 11.90it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  47%|▍| 6949/14932 [09:43<11:10, 11.90it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -64108,8 +64103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6937/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  46%|▍| 6937/14932 [09:45<11:15, 11.84it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  47%|▍| 6950/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  47%|▍| 6950/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -64117,8 +64112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6938/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  46%|▍| 6938/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  47%|▍| 6951/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  47%|▍| 6951/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -64126,8 +64121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6939/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  46%|▍| 6939/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  47%|▍| 6952/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  47%|▍| 6952/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -64135,8 +64130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6940/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  46%|▍| 6940/14932 [09:45<11:14, 11.84it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  47%|▍| 6953/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  47%|▍| 6953/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -64144,8 +64139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6941/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  46%|▍| 6941/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  47%|▍| 6954/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  47%|▍| 6954/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -64153,8 +64148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6942/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  46%|▍| 6942/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  47%|▍| 6955/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  47%|▍| 6955/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -64162,8 +64157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  46%|▍| 6943/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  46%|▍| 6943/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  47%|▍| 6956/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  47%|▍| 6956/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -64171,7 +64166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6944/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  47%|▍| 6957/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  47%|▍| 6957/14932 [09:44<11:10, 11.90it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -64179,7 +64175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6944/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  47%|▍| 6958/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  47%|▍| 6958/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -64187,8 +64184,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6945/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  47%|▍| 6945/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  47%|▍| 6959/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -64196,8 +64192,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6946/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  47%|▍| 6946/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  47%|▍| 6959/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -64205,8 +64200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6947/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  47%|▍| 6947/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  47%|▍| 6960/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  47%|▍| 6960/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -64214,8 +64209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6948/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  47%|▍| 6948/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  47%|▍| 6961/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  47%|▍| 6961/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -64223,8 +64218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6949/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  47%|▍| 6949/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  47%|▍| 6962/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  47%|▍| 6962/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -64232,8 +64227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6950/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  47%|▍| 6950/14932 [09:46<11:14, 11.84it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  47%|▍| 6963/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  47%|▍| 6963/14932 [09:44<11:09, 11.90it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -64241,8 +64236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6951/14932 [09:46<11:13, 11.84it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  47%|▍| 6951/14932 [09:46<11:13, 11.84it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  47%|▍| 6964/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  47%|▍| 6964/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -64250,8 +64245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6952/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  47%|▍| 6952/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  47%|▍| 6965/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  47%|▍| 6965/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -64259,8 +64254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6953/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  47%|▍| 6953/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  47%|▍| 6966/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  47%|▍| 6966/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -64268,8 +64263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6954/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  47%|▍| 6954/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  47%|▍| 6967/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  47%|▍| 6967/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -64277,8 +64272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6955/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  47%|▍| 6955/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  47%|▍| 6968/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  47%|▍| 6968/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -64286,8 +64281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6956/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  47%|▍| 6956/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  47%|▍| 6969/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  47%|▍| 6969/14932 [09:45<11:09, 11.90it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -64295,8 +64290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6957/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  47%|▍| 6957/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  47%|▍| 6970/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  47%|▍| 6970/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -64304,8 +64299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6958/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  47%|▍| 6958/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  47%|▍| 6971/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  47%|▍| 6971/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -64313,8 +64308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6959/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  47%|▍| 6959/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  47%|▍| 6972/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  47%|▍| 6972/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -64322,8 +64317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6960/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  47%|▍| 6960/14932 [09:47<11:13, 11.84it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  47%|▍| 6973/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  47%|▍| 6973/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=0.79"
      ]
     },
     {
@@ -64331,8 +64326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6961/14932 [09:47<11:12, 11.84it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  47%|▍| 6961/14932 [09:47<11:12, 11.84it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  47%|▍| 6974/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=0.79\r",
+      "Epoch 0:  47%|▍| 6974/14932 [09:45<11:08, 11.90it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -64340,8 +64335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6962/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  47%|▍| 6962/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  47%|▍| 6975/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  47%|▍| 6975/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -64349,8 +64344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6963/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  47%|▍| 6963/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:  47%|▍| 6976/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  47%|▍| 6976/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -64358,8 +64353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6964/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:  47%|▍| 6964/14932 [09:47<11:12, 11.85it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  47%|▍| 6977/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  47%|▍| 6977/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -64367,8 +64362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6965/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  47%|▍| 6965/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  47%|▍| 6978/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  47%|▍| 6978/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -64376,8 +64371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6966/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  47%|▍| 6966/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  47%|▍| 6979/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  47%|▍| 6979/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -64385,8 +64380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6967/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  47%|▍| 6967/14932 [09:48<11:12, 11.84it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  47%|▍| 6980/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  47%|▍| 6980/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -64394,8 +64389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6968/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  47%|▍| 6968/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  47%|▍| 6981/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  47%|▍| 6981/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -64403,8 +64398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6969/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  47%|▍| 6969/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  47%|▍| 6982/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  47%|▍| 6982/14932 [09:46<11:08, 11.90it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -64412,8 +64407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6970/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  47%|▍| 6970/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  47%|▍| 6983/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  47%|▍| 6983/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -64421,8 +64416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6971/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  47%|▍| 6971/14932 [09:48<11:12, 11.85it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  47%|▍| 6984/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  47%|▍| 6984/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -64430,8 +64425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6972/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  47%|▍| 6972/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  47%|▍| 6985/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  47%|▍| 6985/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -64439,8 +64434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6973/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  47%|▍| 6973/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  47%|▍| 6986/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  47%|▍| 6986/14932 [09:46<11:07, 11.90it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -64448,8 +64443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6974/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  47%|▍| 6974/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  47%|▍| 6987/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  47%|▍| 6987/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -64457,8 +64452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6975/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  47%|▍| 6975/14932 [09:48<11:11, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  47%|▍| 6988/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  47%|▍| 6988/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -64466,8 +64461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6976/14932 [09:48<11:11, 11.84it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  47%|▍| 6976/14932 [09:48<11:11, 11.84it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  47%|▍| 6989/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  47%|▍| 6989/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -64475,8 +64470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6977/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  47%|▍| 6977/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  47%|▍| 6990/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  47%|▍| 6990/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -64484,8 +64479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6978/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  47%|▍| 6978/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  47%|▍| 6991/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  47%|▍| 6991/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -64493,8 +64488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6979/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  47%|▍| 6979/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  47%|▍| 6992/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  47%|▍| 6992/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -64502,7 +64497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6980/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  47%|▍| 6993/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  47%|▍| 6993/14932 [09:47<11:07, 11.90it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -64510,7 +64506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6980/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  47%|▍| 6994/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  47%|▍| 6994/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -64518,8 +64515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6981/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  47%|▍| 6981/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  47%|▍| 6995/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  47%|▍| 6995/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -64527,8 +64524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6982/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  47%|▍| 6982/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  47%|▍| 6996/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  47%|▍| 6996/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -64536,8 +64533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6983/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  47%|▍| 6983/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  47%|▍| 6997/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  47%|▍| 6997/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -64545,8 +64542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6984/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  47%|▍| 6984/14932 [09:49<11:11, 11.84it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  47%|▍| 6998/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  47%|▍| 6998/14932 [09:47<11:06, 11.90it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -64554,8 +64551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6985/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  47%|▍| 6985/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  47%|▍| 6999/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  47%|▍| 6999/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -64563,8 +64560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6986/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  47%|▍| 6986/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  47%|▍| 7000/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  47%|▍| 7000/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -64572,8 +64569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6987/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  47%|▍| 6987/14932 [09:49<11:10, 11.84it/s, v_num=o30c, train/loss=1.03"
+      "Epoch 0:  47%|▍| 7001/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  47%|▍| 7001/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -64581,8 +64578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6988/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=1.03\r",
-      "Epoch 0:  47%|▍| 6988/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  47%|▍| 7002/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  47%|▍| 7002/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -64590,8 +64587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6989/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  47%|▍| 6989/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  47%|▍| 7003/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  47%|▍| 7003/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -64599,8 +64596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6990/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  47%|▍| 6990/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  47%|▍| 7004/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  47%|▍| 7004/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -64608,8 +64605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6991/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  47%|▍| 6991/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  47%|▍| 7005/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  47%|▍| 7005/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -64617,8 +64614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6992/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  47%|▍| 6992/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  47%|▍| 7006/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  47%|▍| 7006/14932 [09:48<11:06, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -64626,8 +64623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6993/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  47%|▍| 6993/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  47%|▍| 7007/14932 [09:48<11:05, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  47%|▍| 7007/14932 [09:48<11:05, 11.90it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -64635,8 +64632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6994/14932 [09:50<11:10, 11.85it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  47%|▍| 6994/14932 [09:50<11:10, 11.85it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  47%|▍| 7008/14932 [09:48<11:05, 11.90it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  47%|▍| 7008/14932 [09:48<11:05, 11.90it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -64644,8 +64641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6995/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  47%|▍| 6995/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  47%|▍| 7009/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  47%|▍| 7009/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -64653,8 +64650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6996/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  47%|▍| 6996/14932 [09:50<11:10, 11.84it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  47%|▍| 7010/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  47%|▍| 7010/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -64662,8 +64659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6997/14932 [09:50<11:09, 11.84it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  47%|▍| 6997/14932 [09:50<11:09, 11.84it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  47%|▍| 7011/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  47%|▍| 7011/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -64671,8 +64668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6998/14932 [09:50<11:09, 11.84it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  47%|▍| 6998/14932 [09:50<11:09, 11.84it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  47%|▍| 7012/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  47%|▍| 7012/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -64680,8 +64677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 6999/14932 [09:50<11:09, 11.85it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  47%|▍| 6999/14932 [09:50<11:09, 11.85it/s, v_num=o30c, train/loss=5.03"
+      "Epoch 0:  47%|▍| 7013/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  47%|▍| 7013/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -64689,8 +64686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7000/14932 [09:50<11:09, 11.85it/s, v_num=o30c, train/loss=5.03\r",
-      "Epoch 0:  47%|▍| 7000/14932 [09:50<11:09, 11.85it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  47%|▍| 7014/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  47%|▍| 7014/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -64698,8 +64695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7001/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  47%|▍| 7001/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  47%|▍| 7015/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  47%|▍| 7015/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -64707,8 +64704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7002/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  47%|▍| 7002/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  47%|▍| 7016/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  47%|▍| 7016/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -64716,8 +64713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7003/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  47%|▍| 7003/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  47%|▍| 7017/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  47%|▍| 7017/14932 [09:49<11:05, 11.90it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -64725,8 +64722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7004/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  47%|▍| 7004/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  47%|▍| 7018/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  47%|▍| 7018/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -64734,8 +64731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7005/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  47%|▍| 7005/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  47%|▍| 7019/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  47%|▍| 7019/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -64743,8 +64740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7006/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  47%|▍| 7006/14932 [09:51<11:09, 11.85it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  47%|▍| 7020/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  47%|▍| 7020/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=0.78"
      ]
     },
     {
@@ -64752,8 +64749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7007/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  47%|▍| 7007/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  47%|▍| 7021/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=0.78\r",
+      "Epoch 0:  47%|▍| 7021/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -64761,8 +64758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7008/14932 [09:51<11:09, 11.84it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  47%|▍| 7008/14932 [09:51<11:09, 11.84it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  47%|▍| 7022/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  47%|▍| 7022/14932 [09:49<11:04, 11.90it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -64770,8 +64767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7009/14932 [09:51<11:08, 11.84it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  47%|▍| 7009/14932 [09:51<11:08, 11.84it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  47%|▍| 7023/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  47%|▍| 7023/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -64779,8 +64776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7010/14932 [09:51<11:08, 11.84it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  47%|▍| 7010/14932 [09:51<11:08, 11.84it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  47%|▍| 7024/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  47%|▍| 7024/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -64788,8 +64785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7011/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  47%|▍| 7011/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  47%|▍| 7025/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  47%|▍| 7025/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -64797,8 +64794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7012/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  47%|▍| 7012/14932 [09:51<11:08, 11.85it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  47%|▍| 7026/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  47%|▍| 7026/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -64806,8 +64803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7013/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  47%|▍| 7013/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  47%|▍| 7027/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  47%|▍| 7027/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -64815,8 +64812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7014/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  47%|▍| 7014/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  47%|▍| 7028/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  47%|▍| 7028/14932 [09:50<11:04, 11.90it/s, v_num=ui8w, train/loss=0.57"
      ]
     },
     {
@@ -64824,8 +64821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7015/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  47%|▍| 7015/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  47%|▍| 7029/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=0.57\r",
+      "Epoch 0:  47%|▍| 7029/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -64833,8 +64830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7016/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  47%|▍| 7016/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  47%|▍| 7030/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  47%|▍| 7030/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -64842,8 +64839,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7017/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  47%|▍| 7017/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  47%|▍| 7031/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -64851,8 +64847,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7018/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  47%|▍| 7018/14932 [09:52<11:08, 11.85it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  47%|▍| 7031/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -64860,8 +64855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7019/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  47%|▍| 7019/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  47%|▍| 7032/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  47%|▍| 7032/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -64869,8 +64864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7020/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  47%|▍| 7020/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=0.45"
+      "Epoch 0:  47%|▍| 7033/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  47%|▍| 7033/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -64878,8 +64873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7021/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=0.45\r",
-      "Epoch 0:  47%|▍| 7021/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  47%|▍| 7034/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  47%|▍| 7034/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -64887,8 +64882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7022/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  47%|▍| 7022/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  47%|▍| 7035/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  47%|▍| 7035/14932 [09:50<11:03, 11.90it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -64896,8 +64891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7023/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  47%|▍| 7023/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  47%|▍| 7036/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  47%|▍| 7036/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -64905,8 +64900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7024/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  47%|▍| 7024/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  47%|▍| 7037/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  47%|▍| 7037/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -64914,8 +64909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7025/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  47%|▍| 7025/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  47%|▍| 7038/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  47%|▍| 7038/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -64923,8 +64918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7026/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  47%|▍| 7026/14932 [09:52<11:07, 11.85it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  47%|▍| 7039/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  47%|▍| 7039/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -64932,8 +64927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7027/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  47%|▍| 7027/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  47%|▍| 7040/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  47%|▍| 7040/14932 [09:51<11:03, 11.90it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -64941,8 +64936,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7028/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  47%|▍| 7028/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  47%|▍| 7041/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -64950,8 +64944,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7029/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=0.89\r",
-      "Epoch 0:  47%|▍| 7029/14932 [09:53<11:07, 11.85it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  47%|▍| 7041/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -64959,8 +64952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7030/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  47%|▍| 7030/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  47%|▍| 7042/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  47%|▍| 7042/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -64968,8 +64961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7031/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  47%|▍| 7031/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  47%|▍| 7043/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  47%|▍| 7043/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -64977,8 +64970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7032/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  47%|▍| 7032/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  47%|▍| 7044/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  47%|▍| 7044/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -64986,8 +64979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7033/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  47%|▍| 7033/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  47%|▍| 7045/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  47%|▍| 7045/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -64995,8 +64988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7034/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  47%|▍| 7034/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  47%|▍| 7046/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  47%|▍| 7046/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -65004,8 +64997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7035/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  47%|▍| 7035/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  47%|▍| 7047/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  47%|▍| 7047/14932 [09:51<11:02, 11.90it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -65013,8 +65006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7036/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  47%|▍| 7036/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  47%|▍| 7048/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  47%|▍| 7048/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -65022,8 +65015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7037/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  47%|▍| 7037/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  47%|▍| 7049/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  47%|▍| 7049/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -65031,8 +65024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7038/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  47%|▍| 7038/14932 [09:53<11:06, 11.85it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  47%|▍| 7050/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  47%|▍| 7050/14932 [09:52<11:02, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -65040,8 +65033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7039/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  47%|▍| 7039/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  47%|▍| 7051/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  47%|▍| 7051/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -65049,8 +65042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7040/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  47%|▍| 7040/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  47%|▍| 7052/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  47%|▍| 7052/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -65058,7 +65051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7041/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  47%|▍| 7053/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  47%|▍| 7053/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -65066,7 +65060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7041/14932 [09:54<11:06, 11.85it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  47%|▍| 7054/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  47%|▍| 7054/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -65074,8 +65069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7042/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  47%|▍| 7042/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  47%|▍| 7055/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  47%|▍| 7055/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -65083,8 +65078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7043/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  47%|▍| 7043/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  47%|▍| 7056/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  47%|▍| 7056/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -65092,8 +65087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7044/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  47%|▍| 7044/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  47%|▍| 7057/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  47%|▍| 7057/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -65101,8 +65096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7045/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  47%|▍| 7045/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:  47%|▍| 7058/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  47%|▍| 7058/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -65110,8 +65105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7046/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:  47%|▍| 7046/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  47%|▍| 7059/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  47%|▍| 7059/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -65119,8 +65114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7047/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  47%|▍| 7047/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  47%|▍| 7060/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  47%|▍| 7060/14932 [09:52<11:01, 11.91it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -65128,8 +65123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7048/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  47%|▍| 7048/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  47%|▍| 7061/14932 [09:53<11:01, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  47%|▍| 7061/14932 [09:53<11:01, 11.91it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -65137,8 +65132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7049/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  47%|▍| 7049/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  47%|▍| 7062/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  47%|▍| 7062/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -65146,8 +65141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7050/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  47%|▍| 7050/14932 [09:54<11:05, 11.85it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  47%|▍| 7063/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  47%|▍| 7063/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -65155,8 +65150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7051/14932 [09:55<11:05, 11.85it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  47%|▍| 7051/14932 [09:55<11:05, 11.85it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  47%|▍| 7064/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  47%|▍| 7064/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -65164,8 +65159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7052/14932 [09:55<11:05, 11.85it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  47%|▍| 7052/14932 [09:55<11:05, 11.85it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  47%|▍| 7065/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  47%|▍| 7065/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -65173,8 +65168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7053/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  47%|▍| 7053/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  47%|▍| 7066/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  47%|▍| 7066/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -65182,8 +65177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7054/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  47%|▍| 7054/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  47%|▍| 7067/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  47%|▍| 7067/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -65191,8 +65186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7055/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  47%|▍| 7055/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  47%|▍| 7068/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  47%|▍| 7068/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -65200,8 +65195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7056/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  47%|▍| 7056/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  47%|▍| 7069/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  47%|▍| 7069/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -65209,8 +65204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7057/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  47%|▍| 7057/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=0.91"
+      "Epoch 0:  47%|▍| 7070/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  47%|▍| 7070/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -65218,8 +65213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7058/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=0.91\r",
-      "Epoch 0:  47%|▍| 7058/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  47%|▍| 7071/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  47%|▍| 7071/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -65227,8 +65222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7059/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  47%|▍| 7059/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  47%|▍| 7072/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  47%|▍| 7072/14932 [09:53<11:00, 11.91it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -65236,8 +65231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7060/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  47%|▍| 7060/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  47%|▍| 7073/14932 [09:54<11:00, 11.91it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  47%|▍| 7073/14932 [09:54<11:00, 11.91it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -65245,8 +65240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7061/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  47%|▍| 7061/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  47%|▍| 7074/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  47%|▍| 7074/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -65254,8 +65249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7062/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  47%|▍| 7062/14932 [09:55<11:04, 11.85it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  47%|▍| 7075/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  47%|▍| 7075/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -65263,8 +65258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7063/14932 [09:55<11:03, 11.85it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  47%|▍| 7063/14932 [09:55<11:03, 11.85it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  47%|▍| 7076/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  47%|▍| 7076/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -65272,8 +65267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7064/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  47%|▍| 7064/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  47%|▍| 7077/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  47%|▍| 7077/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -65281,8 +65276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7065/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  47%|▍| 7065/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  47%|▍| 7078/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  47%|▍| 7078/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -65290,8 +65285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7066/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  47%|▍| 7066/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  47%|▍| 7079/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  47%|▍| 7079/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -65299,8 +65294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7067/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  47%|▍| 7067/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  47%|▍| 7080/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  47%|▍| 7080/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -65308,8 +65303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7068/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  47%|▍| 7068/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  47%|▍| 7081/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  47%|▍| 7081/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -65317,8 +65312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7069/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  47%|▍| 7069/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  47%|▍| 7082/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  47%|▍| 7082/14932 [09:54<10:59, 11.90it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -65326,8 +65321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7070/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  47%|▍| 7070/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  47%|▍| 7083/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  47%|▍| 7083/14932 [09:54<10:59, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -65335,8 +65330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7071/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  47%|▍| 7071/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  47%|▍| 7084/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  47%|▍| 7084/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -65344,8 +65339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7072/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  47%|▍| 7072/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  47%|▍| 7085/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  47%|▍| 7085/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -65353,8 +65348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7073/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  47%|▍| 7073/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  47%|▍| 7086/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  47%|▍| 7086/14932 [09:55<10:59, 11.91it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -65362,8 +65357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7074/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  47%|▍| 7074/14932 [09:56<11:03, 11.85it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  47%|▍| 7087/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  47%|▍| 7087/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -65371,8 +65366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7075/14932 [09:57<11:03, 11.85it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  47%|▍| 7075/14932 [09:57<11:03, 11.85it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  47%|▍| 7088/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  47%|▍| 7088/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -65380,8 +65375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7076/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  47%|▍| 7076/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  47%|▍| 7089/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  47%|▍| 7089/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -65389,8 +65384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7077/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  47%|▍| 7077/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  47%|▍| 7090/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  47%|▍| 7090/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -65398,8 +65393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7078/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  47%|▍| 7078/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=0.71"
+      "Epoch 0:  47%|▍| 7091/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  47%|▍| 7091/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=0.68"
      ]
     },
     {
@@ -65407,8 +65402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7079/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=0.71\r",
-      "Epoch 0:  47%|▍| 7079/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  47%|▍| 7092/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=0.68\r",
+      "Epoch 0:  47%|▍| 7092/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -65416,8 +65411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7080/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  47%|▍| 7080/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  48%|▍| 7093/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  48%|▍| 7093/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -65425,8 +65420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7081/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  47%|▍| 7081/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  48%|▍| 7094/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  48%|▍| 7094/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -65434,8 +65429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7082/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  47%|▍| 7082/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  48%|▍| 7095/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  48%|▍| 7095/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -65443,8 +65438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7083/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  47%|▍| 7083/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  48%|▍| 7096/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  48%|▍| 7096/14932 [09:55<10:58, 11.91it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -65452,8 +65447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7084/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  47%|▍| 7084/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  48%|▍| 7097/14932 [09:55<10:57, 11.91it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  48%|▍| 7097/14932 [09:55<10:57, 11.91it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -65461,8 +65456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7085/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  47%|▍| 7085/14932 [09:57<11:02, 11.85it/s, v_num=o30c, train/loss=1.56"
+      "Epoch 0:  48%|▍| 7098/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  48%|▍| 7098/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -65470,8 +65465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7086/14932 [09:58<11:02, 11.85it/s, v_num=o30c, train/loss=1.56\r",
-      "Epoch 0:  47%|▍| 7086/14932 [09:58<11:02, 11.85it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  48%|▍| 7099/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  48%|▍| 7099/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -65479,8 +65474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7087/14932 [09:58<11:02, 11.85it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  47%|▍| 7087/14932 [09:58<11:02, 11.85it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  48%|▍| 7100/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  48%|▍| 7100/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -65488,8 +65483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7088/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  47%|▍| 7088/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  48%|▍| 7101/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  48%|▍| 7101/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -65497,8 +65492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7089/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  47%|▍| 7089/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  48%|▍| 7102/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  48%|▍| 7102/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -65506,8 +65501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7090/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  47%|▍| 7090/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  48%|▍| 7103/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  48%|▍| 7103/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -65515,8 +65510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7091/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  47%|▍| 7091/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  48%|▍| 7104/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  48%|▍| 7104/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -65524,8 +65519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  47%|▍| 7092/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  47%|▍| 7092/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  48%|▍| 7105/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  48%|▍| 7105/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=0.83"
      ]
     },
     {
@@ -65533,8 +65528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7093/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  48%|▍| 7093/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  48%|▍| 7106/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=0.83\r",
+      "Epoch 0:  48%|▍| 7106/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -65542,8 +65537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7094/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  48%|▍| 7094/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  48%|▍| 7107/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  48%|▍| 7107/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -65551,8 +65546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7095/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  48%|▍| 7095/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  48%|▍| 7108/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  48%|▍| 7108/14932 [09:56<10:57, 11.91it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -65560,8 +65555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7096/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  48%|▍| 7096/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  48%|▍| 7109/14932 [09:56<10:56, 11.91it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  48%|▍| 7109/14932 [09:56<10:56, 11.91it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -65569,8 +65564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7097/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  48%|▍| 7097/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  48%|▍| 7110/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  48%|▍| 7110/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -65578,8 +65573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7098/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  48%|▍| 7098/14932 [09:58<11:01, 11.85it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  48%|▍| 7111/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  48%|▍| 7111/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -65587,8 +65582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7099/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  48%|▍| 7099/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  48%|▍| 7112/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  48%|▍| 7112/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -65596,8 +65591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7100/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  48%|▍| 7100/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  48%|▍| 7113/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  48%|▍| 7113/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -65605,8 +65600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7101/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  48%|▍| 7101/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  48%|▍| 7114/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  48%|▍| 7114/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -65614,8 +65609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7102/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  48%|▍| 7102/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  48%|▍| 7115/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  48%|▍| 7115/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -65623,8 +65618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7103/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  48%|▍| 7103/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  48%|▍| 7116/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  48%|▍| 7116/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -65632,8 +65627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7104/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  48%|▍| 7104/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  48%|▍| 7117/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  48%|▍| 7117/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -65641,8 +65636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7105/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  48%|▍| 7105/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  48%|▍| 7118/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  48%|▍| 7118/14932 [09:57<10:56, 11.91it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -65650,8 +65645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7106/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  48%|▍| 7106/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  48%|▍| 7119/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  48%|▍| 7119/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -65659,8 +65654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7107/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  48%|▍| 7107/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  48%|▍| 7120/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  48%|▍| 7120/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -65668,8 +65663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7108/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  48%|▍| 7108/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  48%|▍| 7121/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  48%|▍| 7121/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -65677,8 +65672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7109/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  48%|▍| 7109/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  48%|▍| 7122/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  48%|▍| 7122/14932 [09:57<10:55, 11.91it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -65686,8 +65681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7110/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  48%|▍| 7110/14932 [09:59<11:00, 11.85it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  48%|▍| 7123/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  48%|▍| 7123/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -65695,8 +65690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7111/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  48%|▍| 7111/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  48%|▍| 7124/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  48%|▍| 7124/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -65704,8 +65699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7112/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.84\r",
-      "Epoch 0:  48%|▍| 7112/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  48%|▍| 7125/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  48%|▍| 7125/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -65713,8 +65708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7113/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  48%|▍| 7113/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  48%|▍| 7126/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  48%|▍| 7126/14932 [09:58<10:55, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -65722,8 +65717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7114/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  48%|▍| 7114/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  48%|▍| 7127/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  48%|▍| 7127/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -65731,8 +65726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7115/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  48%|▍| 7115/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  48%|▍| 7128/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  48%|▍| 7128/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -65740,8 +65735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7116/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  48%|▍| 7116/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  48%|▍| 7129/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  48%|▍| 7129/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -65749,8 +65744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7117/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  48%|▍| 7117/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  48%|▍| 7130/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  48%|▍| 7130/14932 [09:58<10:55, 11.90it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -65758,7 +65753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7118/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  48%|▍| 7131/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  48%|▍| 7131/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -65766,7 +65762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7118/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  48%|▍| 7132/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  48%|▍| 7132/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -65774,8 +65771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7119/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  48%|▍| 7119/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  48%|▍| 7133/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  48%|▍| 7133/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -65783,8 +65780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7120/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  48%|▍| 7120/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  48%|▍| 7134/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  48%|▍| 7134/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -65792,8 +65789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7121/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  48%|▍| 7121/14932 [10:00<10:59, 11.85it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  48%|▍| 7135/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  48%|▍| 7135/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -65801,8 +65798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7122/14932 [10:00<10:58, 11.85it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  48%|▍| 7122/14932 [10:00<10:58, 11.85it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  48%|▍| 7136/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  48%|▍| 7136/14932 [09:59<10:55, 11.90it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -65810,8 +65807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7123/14932 [10:00<10:58, 11.85it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  48%|▍| 7123/14932 [10:00<10:58, 11.85it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  48%|▍| 7137/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  48%|▍| 7137/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -65819,8 +65816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7124/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  48%|▍| 7124/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  48%|▍| 7138/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  48%|▍| 7138/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -65828,8 +65825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7125/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  48%|▍| 7125/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  48%|▍| 7139/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  48%|▍| 7139/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -65837,8 +65834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7126/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  48%|▍| 7126/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  48%|▍| 7140/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  48%|▍| 7140/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -65846,8 +65843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7127/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  48%|▍| 7127/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  48%|▍| 7141/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  48%|▍| 7141/14932 [09:59<10:54, 11.90it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -65855,8 +65852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7128/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  48%|▍| 7128/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  48%|▍| 7142/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  48%|▍| 7142/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -65864,8 +65861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7129/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  48%|▍| 7129/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  48%|▍| 7143/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  48%|▍| 7143/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -65873,8 +65870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7130/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  48%|▍| 7130/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  48%|▍| 7144/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  48%|▍| 7144/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -65882,8 +65879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7131/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  48%|▍| 7131/14932 [10:01<10:58, 11.85it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  48%|▍| 7145/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  48%|▍| 7145/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -65891,7 +65888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7132/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  48%|▍| 7146/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  48%|▍| 7146/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -65899,7 +65897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7132/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  48%|▍| 7147/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  48%|▍| 7147/14932 [10:00<10:54, 11.90it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -65907,8 +65906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7133/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  48%|▍| 7133/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=1.08"
+      "Epoch 0:  48%|▍| 7148/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  48%|▍| 7148/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -65916,8 +65915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7134/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=1.08\r",
-      "Epoch 0:  48%|▍| 7134/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  48%|▍| 7149/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  48%|▍| 7149/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -65925,8 +65924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7135/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  48%|▍| 7135/14932 [10:01<10:57, 11.85it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  48%|▍| 7150/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  48%|▍| 7150/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -65934,8 +65933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7136/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  48%|▍| 7136/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  48%|▍| 7151/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  48%|▍| 7151/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -65943,8 +65942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7137/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  48%|▍| 7137/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  48%|▍| 7152/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  48%|▍| 7152/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -65952,8 +65951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7138/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  48%|▍| 7138/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  48%|▍| 7153/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  48%|▍| 7153/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -65961,8 +65960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7139/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  48%|▍| 7139/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  48%|▍| 7154/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  48%|▍| 7154/14932 [10:00<10:53, 11.90it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -65970,8 +65969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7140/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  48%|▍| 7140/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  48%|▍| 7155/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  48%|▍| 7155/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -65979,8 +65978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7141/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  48%|▍| 7141/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  48%|▍| 7156/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  48%|▍| 7156/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -65988,8 +65987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7142/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  48%|▍| 7142/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=0.70"
+      "Epoch 0:  48%|▍| 7157/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  48%|▍| 7157/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -65997,8 +65996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7143/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=0.70\r",
-      "Epoch 0:  48%|▍| 7143/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  48%|▍| 7158/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  48%|▍| 7158/14932 [10:01<10:53, 11.90it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -66006,8 +66005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7144/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  48%|▍| 7144/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  48%|▍| 7159/14932 [10:01<10:52, 11.90it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  48%|▍| 7159/14932 [10:01<10:52, 11.90it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -66015,8 +66014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7145/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  48%|▍| 7145/14932 [10:02<10:57, 11.85it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  48%|��| 7160/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  48%|▍| 7160/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -66024,8 +66023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7146/14932 [10:02<10:56, 11.85it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  48%|▍| 7146/14932 [10:02<10:56, 11.85it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  48%|▍| 7161/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  48%|▍| 7161/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -66033,8 +66032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7147/14932 [10:02<10:56, 11.85it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  48%|▍| 7147/14932 [10:02<10:56, 11.85it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  48%|▍| 7162/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  48%|▍| 7162/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -66042,8 +66041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7148/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  48%|▍| 7148/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  48%|▍| 7163/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  48%|▍| 7163/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -66051,8 +66050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7149/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  48%|▍| 7149/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  48%|▍| 7164/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  48%|▍| 7164/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -66060,8 +66059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7150/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  48%|▍| 7150/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  48%|▍| 7165/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  48%|▍| 7165/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -66069,8 +66068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7151/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  48%|▍| 7151/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  48%|▍| 7166/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  48%|▍| 7166/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -66078,8 +66077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7152/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  48%|▍| 7152/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  48%|▍| 7167/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  48%|▍| 7167/14932 [10:01<10:52, 11.91it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -66087,8 +66086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7153/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  48%|▍| 7153/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  48%|▍| 7168/14932 [10:02<10:52, 11.90it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  48%|▍| 7168/14932 [10:02<10:52, 11.90it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -66096,8 +66095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7154/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  48%|▍| 7154/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  48%|▍| 7169/14932 [10:02<10:52, 11.90it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  48%|▍| 7169/14932 [10:02<10:52, 11.90it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -66105,8 +66104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7155/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  48%|▍| 7155/14932 [10:03<10:56, 11.85it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  48%|▍| 7170/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  48%|▍| 7170/14932 [10:02<10:51, 11.90it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -66114,8 +66113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7156/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  48%|▍| 7156/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  48%|▍| 7171/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  48%|▍| 7171/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -66123,8 +66122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7157/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  48%|▍| 7157/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  48%|▍| 7172/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  48%|▍| 7172/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -66132,8 +66131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7158/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  48%|▍| 7158/14932 [10:03<10:55, 11.86it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  48%|▍| 7173/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  48%|▍| 7173/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -66141,8 +66140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7159/14932 [10:03<10:55, 11.85it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  48%|▍| 7159/14932 [10:03<10:55, 11.85it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  48%|▍| 7174/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  48%|▍| 7174/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -66150,8 +66149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7160/14932 [10:03<10:55, 11.85it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  48%|▍| 7160/14932 [10:03<10:55, 11.85it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  48%|▍| 7175/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  48%|▍| 7175/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -66159,8 +66158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7161/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  48%|▍| 7161/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  48%|▍| 7176/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  48%|▍| 7176/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -66168,8 +66167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7162/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  48%|▍| 7162/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  48%|▍| 7177/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  48%|▍| 7177/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -66177,8 +66176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7163/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  48%|▍| 7163/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  48%|▍| 7178/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  48%|▍| 7178/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -66186,8 +66185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7164/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  48%|▍| 7164/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  48%|▍| 7179/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  48%|▍| 7179/14932 [10:02<10:51, 11.91it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -66195,8 +66194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7165/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  48%|▍| 7165/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  48%|▍| 7180/14932 [10:03<10:51, 11.91it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  48%|▍| 7180/14932 [10:03<10:51, 11.91it/s, v_num=ui8w, train/loss=0.85"
      ]
     },
     {
@@ -66204,8 +66203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7166/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  48%|▍| 7166/14932 [10:04<10:55, 11.86it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  48%|▍| 7181/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=0.85\r",
+      "Epoch 0:  48%|▍| 7181/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -66213,8 +66212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7167/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  48%|▍| 7167/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  48%|▍| 7182/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  48%|▍| 7182/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -66222,8 +66221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7168/14932 [10:04<10:54, 11.85it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  48%|▍| 7168/14932 [10:04<10:54, 11.85it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  48%|▍| 7183/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  48%|▍| 7183/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -66231,8 +66230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7169/14932 [10:04<10:54, 11.85it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  48%|▍| 7169/14932 [10:04<10:54, 11.85it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  48%|▍| 7184/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  48%|▍| 7184/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -66240,8 +66239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7170/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  48%|▍| 7170/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  48%|▍| 7185/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  48%|▍| 7185/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -66249,8 +66248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7171/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  48%|▍| 7171/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  48%|▍| 7186/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  48%|▍| 7186/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -66258,8 +66257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7172/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  48%|▍| 7172/14932 [10:04<10:54, 11.86it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  48%|▍| 7187/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  48%|▍| 7187/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -66267,8 +66266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7173/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  48%|▍| 7173/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  48%|▍| 7188/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  48%|▍| 7188/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -66276,8 +66275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7174/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  48%|▍| 7174/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  48%|▍| 7189/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  48%|▍| 7189/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -66285,8 +66284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7175/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  48%|▍| 7175/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  48%|▍| 7190/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  48%|▍| 7190/14932 [10:03<10:50, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -66294,8 +66293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7176/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  48%|▍| 7176/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  48%|▍| 7191/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  48%|▍| 7191/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -66303,8 +66302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7177/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  48%|▍| 7177/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  48%|▍| 7192/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  48%|▍| 7192/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -66312,8 +66311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7178/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  48%|▍| 7178/14932 [10:05<10:54, 11.86it/s, v_num=o30c, train/loss=1.06"
+      "Epoch 0:  48%|▍| 7193/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  48%|▍| 7193/14932 [10:03<10:49, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -66321,8 +66320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7179/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=1.06\r",
-      "Epoch 0:  48%|▍| 7179/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  48%|▍| 7194/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  48%|▍| 7194/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -66330,8 +66329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7180/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  48%|▍| 7180/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  48%|▍| 7195/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  48%|▍| 7195/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -66339,8 +66338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7181/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  48%|▍| 7181/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  48%|▍| 7196/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  48%|▍| 7196/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -66348,8 +66347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7182/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  48%|▍| 7182/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  48%|▍| 7197/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  48%|▍| 7197/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -66357,8 +66356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7183/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  48%|▍| 7183/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  48%|▍| 7198/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  48%|▍| 7198/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -66366,8 +66365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7184/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  48%|▍| 7184/14932 [10:05<10:53, 11.86it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  48%|▍| 7199/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  48%|▍| 7199/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -66375,8 +66374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7185/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  48%|▍| 7185/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  48%|▍| 7200/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  48%|▍| 7200/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -66384,8 +66383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7186/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  48%|▍| 7186/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  48%|▍| 7201/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  48%|▍| 7201/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -66393,8 +66392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7187/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  48%|▍| 7187/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  48%|▍| 7202/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  48%|▍| 7202/14932 [10:04<10:49, 11.91it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -66402,8 +66401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7188/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  48%|▍| 7188/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  48%|▍| 7203/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  48%|▍| 7203/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -66411,8 +66410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7189/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  48%|▍| 7189/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  48%|▍| 7204/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  48%|▍| 7204/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -66420,8 +66419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7190/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  48%|▍| 7190/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  48%|▍| 7205/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  48%|▍| 7205/14932 [10:04<10:48, 11.91it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -66429,8 +66428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7191/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  48%|▍| 7191/14932 [10:06<10:53, 11.85it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  48%|▍| 7206/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  48%|▍| 7206/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -66438,8 +66437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7192/14932 [10:06<10:52, 11.85it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  48%|▍| 7192/14932 [10:06<10:52, 11.85it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  48%|▍| 7207/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  48%|▍| 7207/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -66447,8 +66446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7193/14932 [10:06<10:52, 11.85it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  48%|▍| 7193/14932 [10:06<10:52, 11.85it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  48%|▍| 7208/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  48%|▍| 7208/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -66456,8 +66455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7194/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  48%|▍| 7194/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  48%|▍| 7209/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  48%|▍| 7209/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -66465,8 +66464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7195/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  48%|▍| 7195/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  48%|▍| 7210/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  48%|▍| 7210/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -66474,8 +66473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7196/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  48%|▍| 7196/14932 [10:06<10:52, 11.86it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  48%|▍| 7211/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  48%|▍| 7211/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -66483,8 +66482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7197/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  48%|▍| 7197/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  48%|▍| 7212/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  48%|▍| 7212/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -66492,8 +66491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7198/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  48%|▍| 7198/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  48%|▍| 7213/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  48%|▍| 7213/14932 [10:05<10:48, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -66501,8 +66500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7199/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  48%|▍| 7199/14932 [10:07<10:52, 11.86it/s, v_num=o30c, train/loss=1.06"
+      "Epoch 0:  48%|▍| 7214/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  48%|▍| 7214/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -66510,8 +66509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7200/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=1.06\r",
-      "Epoch 0:  48%|▍| 7200/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  48%|▍| 7215/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  48%|▍| 7215/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -66519,8 +66518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7201/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  48%|▍| 7201/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  48%|▍| 7216/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  48%|▍| 7216/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -66528,8 +66527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7202/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  48%|▍| 7202/14932 [10:07<10:52, 11.85it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  48%|▍| 7217/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  48%|▍| 7217/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -66537,8 +66536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7203/14932 [10:07<10:51, 11.85it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  48%|▍| 7203/14932 [10:07<10:51, 11.85it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  48%|▍| 7218/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  48%|▍| 7218/14932 [10:05<10:47, 11.91it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -66546,8 +66545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7204/14932 [10:07<10:51, 11.85it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  48%|▍| 7204/14932 [10:07<10:51, 11.85it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  48%|▍| 7219/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  48%|▍| 7219/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -66555,8 +66554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7205/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  48%|▍| 7205/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  48%|▍| 7220/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  48%|▍| 7220/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -66564,7 +66563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7206/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  48%|▍| 7221/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  48%|▍| 7221/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -66572,7 +66572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7206/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  48%|▍| 7222/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  48%|▍| 7222/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -66580,8 +66581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7207/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  48%|▍| 7207/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  48%|▍| 7223/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  48%|▍| 7223/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -66589,8 +66590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7208/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  48%|▍| 7208/14932 [10:07<10:51, 11.86it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  48%|▍| 7224/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  48%|▍| 7224/14932 [10:06<10:47, 11.91it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -66598,8 +66599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7209/14932 [10:08<10:51, 11.85it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  48%|▍| 7209/14932 [10:08<10:51, 11.85it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  48%|▍| 7225/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  48%|▍| 7225/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -66607,8 +66608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7210/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  48%|▍| 7210/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  48%|▍| 7226/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  48%|▍| 7226/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -66616,8 +66617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7211/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  48%|▍| 7211/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  48%|▍| 7227/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  48%|▍| 7227/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -66625,8 +66626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7212/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  48%|▍| 7212/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  48%|▍| 7228/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  48%|▍| 7228/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -66634,8 +66635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7213/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  48%|▍| 7213/14932 [10:08<10:51, 11.86it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  48%|▍| 7229/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  48%|▍| 7229/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -66643,8 +66644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7214/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  48%|▍| 7214/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  48%|▍| 7230/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  48%|▍| 7230/14932 [10:06<10:46, 11.91it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -66652,8 +66653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7215/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  48%|▍| 7215/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  48%|▍| 7231/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  48%|▍| 7231/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -66661,8 +66662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7216/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  48%|▍| 7216/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  48%|▍| 7232/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  48%|▍| 7232/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -66670,8 +66671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7217/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  48%|▍| 7217/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=0.83"
+      "Epoch 0:  48%|▍| 7233/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  48%|▍| 7233/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -66679,8 +66680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7218/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=0.83\r",
-      "Epoch 0:  48%|▍| 7218/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  48%|▍| 7234/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  48%|▍| 7234/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -66688,8 +66689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7219/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  48%|▍| 7219/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  48%|▍| 7235/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  48%|▍| 7235/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -66697,8 +66698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7220/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  48%|▍| 7220/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  48%|▍| 7236/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  48%|▍| 7236/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -66706,8 +66707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7221/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  48%|▍| 7221/14932 [10:08<10:50, 11.86it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  48%|▍| 7237/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  48%|▍| 7237/14932 [10:07<10:46, 11.91it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -66715,8 +66716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7222/14932 [10:09<10:50, 11.86it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  48%|▍| 7222/14932 [10:09<10:50, 11.86it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  48%|▍| 7238/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  48%|▍| 7238/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -66724,8 +66725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7223/14932 [10:09<10:50, 11.86it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  48%|▍| 7223/14932 [10:09<10:50, 11.86it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  48%|▍| 7239/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  48%|▍| 7239/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -66733,8 +66734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7224/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  48%|▍| 7224/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  48%|▍| 7240/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  48%|▍| 7240/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -66742,8 +66743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7225/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  48%|▍| 7225/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  48%|▍| 7241/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  48%|▍| 7241/14932 [10:07<10:45, 11.91it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -66751,8 +66752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7226/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  48%|▍| 7226/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  48%|▍| 7242/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  48%|▍| 7242/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -66760,8 +66761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7227/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  48%|▍| 7227/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  49%|▍| 7243/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  49%|▍| 7243/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -66769,8 +66770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7228/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  48%|▍| 7228/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  49%|▍| 7244/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  49%|▍| 7244/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -66778,8 +66779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7229/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  48%|▍| 7229/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  49%|▍| 7245/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  49%|▍| 7245/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -66787,8 +66788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7230/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  48%|▍| 7230/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  49%|▍| 7246/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  49%|▍| 7246/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -66796,8 +66797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7231/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  48%|▍| 7231/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  49%|▍| 7247/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  49%|▍| 7247/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -66805,8 +66806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7232/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  48%|▍| 7232/14932 [10:09<10:49, 11.86it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  49%|▍| 7248/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  49%|▍| 7248/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -66814,8 +66815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7233/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  48%|▍| 7233/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  49%|▍| 7249/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  49%|▍| 7249/14932 [10:08<10:45, 11.91it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -66823,8 +66824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7234/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  48%|▍| 7234/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  49%|▍| 7250/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  49%|▍| 7250/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -66832,8 +66833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7235/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  48%|▍| 7235/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  49%|▍| 7251/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  49%|▍| 7251/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -66841,8 +66842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7236/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  48%|▍| 7236/14932 [10:10<10:49, 11.86it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  49%|▍| 7252/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  49%|▍| 7252/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -66850,8 +66851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7237/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  48%|▍| 7237/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  49%|▍| 7253/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  49%|▍| 7253/14932 [10:08<10:44, 11.91it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -66859,8 +66860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7238/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  48%|▍| 7238/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  49%|▍| 7254/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  49%|▍| 7254/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -66868,8 +66869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7239/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  48%|▍| 7239/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  49%|▍| 7255/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  49%|▍| 7255/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -66877,8 +66878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7240/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  48%|▍| 7240/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  49%|▍| 7256/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  49%|���| 7256/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -66886,8 +66887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7241/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  48%|▍| 7241/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=1.20"
+      "Epoch 0:  49%|▍| 7257/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  49%|▍| 7257/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -66895,8 +66896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  48%|▍| 7242/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=1.20\r",
-      "Epoch 0:  48%|▍| 7242/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  49%|▍| 7258/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  49%|▍| 7258/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -66904,8 +66905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7243/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  49%|▍| 7243/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  49%|▍| 7259/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  49%|▍| 7259/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -66913,8 +66914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7244/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  49%|▍| 7244/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  49%|▍| 7260/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  49%|▍| 7260/14932 [10:09<10:44, 11.91it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -66922,8 +66923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7245/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  49%|▍| 7245/14932 [10:10<10:48, 11.86it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  49%|▍| 7261/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  49%|▍| 7261/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -66931,8 +66932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7246/14932 [10:11<10:48, 11.86it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  49%|▍| 7246/14932 [10:11<10:48, 11.86it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  49%|▍| 7262/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  49%|▍| 7262/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -66940,8 +66941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7247/14932 [10:11<10:48, 11.86it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  49%|▍| 7247/14932 [10:11<10:48, 11.86it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  49%|▍| 7263/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  49%|▍| 7263/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -66949,8 +66950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7248/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  49%|▍| 7248/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  49%|▍| 7264/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  49%|▍| 7264/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -66958,8 +66959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7249/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  49%|▍| 7249/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  49%|▍| 7265/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  49%|▍| 7265/14932 [10:09<10:43, 11.91it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -66967,8 +66968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7250/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  49%|▍| 7250/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  49%|▍| 7266/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  49%|▍| 7266/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -66976,8 +66977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7251/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  49%|▍| 7251/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  49%|▍| 7267/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  49%|▍| 7267/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -66985,8 +66986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7252/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  49%|▍| 7252/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  49%|▍| 7268/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  49%|▍| 7268/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -66994,8 +66995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7253/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  49%|▍| 7253/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  49%|▍| 7269/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  49%|▍| 7269/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -67003,8 +67004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7254/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  49%|▍| 7254/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  49%|▍| 7270/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  49%|▍| 7270/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -67012,8 +67013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7255/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  49%|▍| 7255/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  49%|▍| 7271/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  49%|▍| 7271/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -67021,8 +67022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7256/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  49%|▍| 7256/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  49%|▍| 7272/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  49%|▍| 7272/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -67030,8 +67031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7257/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  49%|▍| 7257/14932 [10:11<10:47, 11.86it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  49%|▍| 7273/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  49%|▍| 7273/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -67039,8 +67040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7258/14932 [10:11<10:46, 11.86it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  49%|▍| 7258/14932 [10:11<10:46, 11.86it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  49%|▍| 7274/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  49%|▍| 7274/14932 [10:10<10:43, 11.91it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -67048,8 +67049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7259/14932 [10:11<10:46, 11.86it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  49%|▍| 7259/14932 [10:11<10:46, 11.86it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  49%|▍| 7275/14932 [10:10<10:42, 11.91it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  49%|▍| 7275/14932 [10:10<10:42, 11.91it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -67057,8 +67058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7260/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  49%|▍| 7260/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  49%|▍| 7276/14932 [10:10<10:42, 11.91it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  49%|▍| 7276/14932 [10:10<10:42, 11.91it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -67066,8 +67067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7261/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  49%|▍| 7261/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  49%|▍| 7277/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  49%|▍| 7277/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -67075,8 +67076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7262/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  49%|▍| 7262/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  49%|▍| 7278/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  49%|▍| 7278/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -67084,8 +67085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7263/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  49%|▍| 7263/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  49%|▍| 7279/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  49%|▍| 7279/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -67093,8 +67094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7264/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  49%|▍| 7264/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  49%|▍| 7280/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  49%|▍| 7280/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -67102,7 +67103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7265/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  49%|▍| 7281/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  49%|▍| 7281/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -67110,7 +67112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7265/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  49%|▍| 7282/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  49%|▍| 7282/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -67118,8 +67121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7266/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  49%|▍| 7266/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  49%|▍| 7283/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  49%|▍| 7283/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -67127,7 +67130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7267/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  49%|▍| 7284/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  49%|▍| 7284/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -67135,7 +67139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7267/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  49%|▍| 7285/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  49%|▍| 7285/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -67143,8 +67148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7268/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  49%|▍| 7268/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  49%|▍| 7286/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  49%|▍| 7286/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -67152,8 +67157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7269/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  49%|▍| 7269/14932 [10:12<10:46, 11.86it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  49%|▍| 7287/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  49%|▍| 7287/14932 [10:11<10:42, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -67161,8 +67166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7270/14932 [10:12<10:45, 11.86it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  49%|▍| 7270/14932 [10:12<10:45, 11.86it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  49%|▍| 7288/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  49%|▍| 7288/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -67170,8 +67175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7271/14932 [10:12<10:45, 11.86it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  49%|▍| 7271/14932 [10:12<10:45, 11.86it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  49%|▍| 7289/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  49%|▍| 7289/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -67179,8 +67184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7272/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  49%|▍| 7272/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  49%|▍| 7290/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  49%|▍| 7290/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -67188,8 +67193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7273/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  49%|▍| 7273/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  49%|▍| 7291/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  49%|▍| 7291/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -67197,8 +67202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7274/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  49%|▍| 7274/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  49%|▍| 7292/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  49%|▍| 7292/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -67206,8 +67211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7275/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  49%|▍| 7275/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  49%|▍| 7293/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  49%|▍| 7293/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -67215,8 +67220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7276/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  49%|▍| 7276/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  49%|▍| 7294/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  49%|▍| 7294/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -67224,8 +67229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7277/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  49%|▍| 7277/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  49%|▍| 7295/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  49%|▍| 7295/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -67233,8 +67238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7278/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  49%|▍| 7278/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  49%|▍| 7296/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  49%|▍| 7296/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -67242,8 +67247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7279/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  49%|▍| 7279/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  49%|▍| 7297/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  49%|▍| 7297/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -67251,8 +67256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7280/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  49%|▍| 7280/14932 [10:13<10:45, 11.86it/s, v_num=o30c, train/loss=1.26"
+      "Epoch 0:  49%|▍| 7298/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  49%|▍| 7298/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -67260,8 +67265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7281/14932 [10:13<10:44, 11.86it/s, v_num=o30c, train/loss=1.26\r",
-      "Epoch 0:  49%|▍| 7281/14932 [10:13<10:44, 11.86it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  49%|▍| 7299/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  49%|▍| 7299/14932 [10:12<10:41, 11.91it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -67269,8 +67274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7282/14932 [10:13<10:44, 11.86it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  49%|▍| 7282/14932 [10:13<10:44, 11.86it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  49%|▍| 7300/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  49%|▍| 7300/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -67278,8 +67283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7283/14932 [10:14<10:45, 11.86it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  49%|▍| 7283/14932 [10:14<10:45, 11.86it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  49%|▍| 7301/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  49%|▍| 7301/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -67287,8 +67292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7284/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  49%|▍| 7284/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  49%|▍| 7302/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  49%|▍| 7302/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -67296,8 +67301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7285/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  49%|▍| 7285/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  49%|▍| 7303/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  49%|▍| 7303/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -67305,8 +67310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7286/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  49%|▍| 7286/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  49%|▍| 7304/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  49%|▍| 7304/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -67314,8 +67319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7287/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  49%|▍| 7287/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  49%|▍| 7305/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  49%|▍| 7305/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -67323,8 +67328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7288/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  49%|▍| 7288/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  49%|▍| 7306/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  49%|▍| 7306/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -67332,8 +67337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7289/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  49%|▍| 7289/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  49%|▍| 7307/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  49%|▍| 7307/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -67341,8 +67346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7290/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  49%|▍| 7290/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  49%|▍| 7308/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  49%|▍| 7308/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -67350,8 +67355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7291/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  49%|▍| 7291/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  49%|▍| 7309/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  49%|▍| 7309/14932 [10:13<10:40, 11.91it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -67359,8 +67364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7292/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  49%|▍| 7292/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  49%|▍| 7310/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  49%|▍| 7310/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -67368,8 +67373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7293/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  49%|▍| 7293/14932 [10:14<10:44, 11.86it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  49%|▍| 7311/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  49%|▍| 7311/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -67377,8 +67382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7294/14932 [10:14<10:43, 11.86it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  49%|▍| 7294/14932 [10:14<10:43, 11.86it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  49%|▍| 7312/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  49%|▍| 7312/14932 [10:13<10:39, 11.91it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -67386,8 +67391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7295/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  49%|▍| 7295/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  49%|▍| 7313/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  49%|▍| 7313/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -67395,8 +67400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7296/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  49%|▍| 7296/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  49%|▍| 7314/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  49%|▍| 7314/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -67404,8 +67409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7297/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  49%|▍| 7297/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  49%|▍| 7315/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  49%|▍| 7315/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -67413,8 +67418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7298/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  49%|▍| 7298/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  49%|▍| 7316/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  49%|▍| 7316/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -67422,8 +67427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7299/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  49%|▍| 7299/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  49%|▍| 7317/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  49%|▍| 7317/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -67431,8 +67436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7300/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  49%|▍| 7300/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  49%|▍| 7318/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  49%|▍| 7318/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -67440,8 +67445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7301/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  49%|▍| 7301/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  49%|▍| 7319/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  49%|▍| 7319/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -67449,8 +67454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7302/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  49%|▍| 7302/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  49%|▍| 7320/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  49%|▍| 7320/14932 [10:14<10:39, 11.91it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -67458,8 +67463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7303/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  49%|▍| 7303/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  49%|▍| 7321/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  49%|▍| 7321/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -67467,8 +67472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7304/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  49%|▍| 7304/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  49%|▍| 7322/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  49%|▍| 7322/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -67476,8 +67481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7305/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  49%|▍| 7305/14932 [10:15<10:43, 11.86it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  49%|▍| 7323/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  49%|▍| 7323/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -67485,8 +67490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7306/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  49%|▍| 7306/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  49%|▍| 7324/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  49%|▍| 7324/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -67494,8 +67499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7307/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  49%|▍| 7307/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  49%|▍| 7325/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  49%|▍| 7325/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -67503,8 +67508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7308/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  49%|▍| 7308/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  49%|▍| 7326/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  49%|▍| 7326/14932 [10:14<10:38, 11.91it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -67512,8 +67517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7309/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  49%|▍| 7309/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  49%|▍| 7327/14932 [10:15<10:38, 11.91it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  49%|▍| 7327/14932 [10:15<10:38, 11.91it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -67521,8 +67526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7310/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  49%|▍| 7310/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  49%|▍| 7328/14932 [10:15<10:38, 11.91it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  49%|▍| 7328/14932 [10:15<10:38, 11.91it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -67530,8 +67535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7311/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  49%|▍| 7311/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  49%|▍| 7329/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  49%|▍| 7329/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -67539,8 +67544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7312/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  49%|▍| 7312/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  49%|▍| 7330/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  49%|▍| 7330/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -67548,8 +67553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7313/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  49%|▍| 7313/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  49%|▍| 7331/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  49%|▍| 7331/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -67557,8 +67562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7314/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  49%|▍| 7314/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  49%|▍| 7332/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  49%|▍| 7332/14932 [10:15<10:38, 11.90it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -67566,8 +67571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7315/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  49%|▍| 7315/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  49%|▍| 7333/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  49%|▍| 7333/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -67575,8 +67580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7316/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  49%|▍| 7316/14932 [10:16<10:42, 11.86it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  49%|▍| 7334/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  49%|▍| 7334/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -67584,8 +67589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7317/14932 [10:16<10:41, 11.86it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  49%|▍| 7317/14932 [10:16<10:41, 11.86it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  49%|▍| 7335/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  49%|▍| 7335/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -67593,8 +67598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7318/14932 [10:16<10:41, 11.86it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  49%|▍| 7318/14932 [10:16<10:41, 11.86it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  49%|▍| 7336/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  49%|▍| 7336/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -67602,8 +67607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7319/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  49%|▍| 7319/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  49%|▍| 7337/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  49%|▍| 7337/14932 [10:16<10:38, 11.90it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -67611,8 +67616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7320/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  49%|▍| 7320/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  49%|▍| 7338/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  49%|▍| 7338/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -67620,8 +67625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7321/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  49%|▍| 7321/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  49%|▍| 7339/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  49%|▍| 7339/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -67629,8 +67634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7322/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  49%|▍| 7322/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  49%|▍| 7340/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  49%|▍| 7340/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -67638,8 +67643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7323/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  49%|▍| 7323/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  49%|▍| 7341/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  49%|▍| 7341/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -67647,8 +67652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7324/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  49%|▍| 7324/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  49%|▍| 7342/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  49%|▍| 7342/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -67656,8 +67661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7325/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  49%|▍| 7325/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  49%|▍| 7343/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:  49%|▍| 7343/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=0.96"
      ]
     },
     {
@@ -67665,8 +67670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7326/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  49%|▍| 7326/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  49%|▍| 7344/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=0.96\r",
+      "Epoch 0:  49%|▍| 7344/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -67674,8 +67679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7327/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  49%|▍| 7327/14932 [10:17<10:41, 11.86it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  49%|▍| 7345/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  49%|▍| 7345/14932 [10:16<10:37, 11.90it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -67683,8 +67688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7328/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  49%|▍| 7328/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  49%|▍| 7346/14932 [10:17<10:37, 11.90it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  49%|▍| 7346/14932 [10:17<10:37, 11.90it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -67692,8 +67697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7329/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  49%|▍| 7329/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  49%|▍| 7347/14932 [10:17<10:37, 11.90it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  49%|▍| 7347/14932 [10:17<10:37, 11.90it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -67701,8 +67706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7330/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  49%|▍| 7330/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  49%|▍| 7348/14932 [10:17<10:37, 11.91it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  49%|▍| 7348/14932 [10:17<10:37, 11.91it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -67710,8 +67715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7331/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  49%|▍| 7331/14932 [10:18<10:41, 11.86it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  49%|▍| 7349/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  49%|▍| 7349/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -67719,8 +67724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7332/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  49%|▍| 7332/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  49%|▍| 7350/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  49%|▍| 7350/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -67728,8 +67733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7333/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  49%|▍| 7333/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  49%|▍| 7351/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  49%|▍| 7351/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -67737,8 +67742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7334/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  49%|▍| 7334/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  49%|▍| 7352/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  49%|▍| 7352/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -67746,8 +67751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7335/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  49%|▍| 7335/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  49%|▍| 7353/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  49%|▍| 7353/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -67755,8 +67760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7336/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  49%|▍| 7336/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  49%|▍| 7354/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  49%|▍| 7354/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -67764,8 +67769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7337/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  49%|▍| 7337/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  49%|▍| 7355/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  49%|▍| 7355/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -67773,8 +67778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7338/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  49%|▍| 7338/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  49%|▍| 7356/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  49%|▍| 7356/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -67782,8 +67787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7339/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  49%|▍| 7339/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  49%|▍| 7357/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  49%|▍| 7357/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -67791,7 +67796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7340/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  49%|▍| 7358/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  49%|▍| 7358/14932 [10:17<10:36, 11.91it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -67799,7 +67805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7340/14932 [10:18<10:40, 11.86it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  49%|▍| 7359/14932 [10:17<10:35, 11.91it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  49%|▍| 7359/14932 [10:17<10:35, 11.91it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -67807,8 +67814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7341/14932 [10:19<10:40, 11.86it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  49%|▍| 7341/14932 [10:19<10:40, 11.86it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  49%|▍| 7360/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  49%|▍| 7360/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -67816,8 +67823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7342/14932 [10:19<10:40, 11.86it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  49%|▍| 7342/14932 [10:19<10:40, 11.86it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  49%|▍| 7361/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  49%|▍| 7361/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -67825,8 +67832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7343/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  49%|▍| 7343/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  49%|▍| 7362/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  49%|▍| 7362/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -67834,8 +67841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7344/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  49%|▍| 7344/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  49%|▍| 7363/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  49%|▍| 7363/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -67843,8 +67850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7345/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  49%|▍| 7345/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  49%|▍| 7364/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  49%|▍| 7364/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -67852,8 +67859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7346/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  49%|▍| 7346/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  49%|▍| 7365/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  49%|▍| 7365/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -67861,8 +67868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7347/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  49%|▍| 7347/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  49%|▍| 7366/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  49%|▍| 7366/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -67870,8 +67877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7348/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  49%|▍| 7348/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  49%|▍| 7367/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  49%|▍| 7367/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -67879,8 +67886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7349/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  49%|▍| 7349/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  49%|▍| 7368/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  49%|▍| 7368/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=1.51"
      ]
     },
     {
@@ -67888,8 +67895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7350/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  49%|▍| 7350/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  49%|▍| 7369/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=1.51\r",
+      "Epoch 0:  49%|▍| 7369/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -67897,8 +67904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7351/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  49%|▍| 7351/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  49%|▍| 7370/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  49%|▍| 7370/14932 [10:18<10:35, 11.91it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -67906,8 +67913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7352/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  49%|▍| 7352/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  49%|▍| 7371/14932 [10:18<10:34, 11.91it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  49%|▍| 7371/14932 [10:18<10:34, 11.91it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -67915,8 +67922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7353/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  49%|▍| 7353/14932 [10:19<10:39, 11.86it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  49%|▍| 7372/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  49%|▍| 7372/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -67924,8 +67931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7354/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  49%|▍| 7354/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  49%|▍| 7373/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  49%|▍| 7373/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -67933,8 +67940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7355/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  49%|▍| 7355/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=0.85"
+      "Epoch 0:  49%|▍| 7374/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  49%|▍| 7374/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -67942,8 +67949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7356/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=0.85\r",
-      "Epoch 0:  49%|▍| 7356/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  49%|▍| 7375/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  49%|▍| 7375/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -67951,8 +67958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7357/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  49%|▍| 7357/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  49%|▍| 7376/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  49%|▍| 7376/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -67960,8 +67967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7358/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  49%|▍| 7358/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  49%|▍| 7377/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  49%|▍| 7377/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -67969,8 +67976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7359/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  49%|▍| 7359/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  49%|▍| 7378/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  49%|▍| 7378/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -67978,8 +67985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7360/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  49%|▍| 7360/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  49%|▍| 7379/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  49%|▍| 7379/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -67987,8 +67994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7361/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  49%|▍| 7361/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  49%|▍| 7380/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  49%|▍| 7380/14932 [10:19<10:34, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -67996,8 +68003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7362/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  49%|▍| 7362/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  49%|▍| 7381/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  49%|▍| 7381/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -68005,8 +68012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7363/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  49%|▍| 7363/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  49%|▍| 7382/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  49%|▍| 7382/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -68014,8 +68021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7364/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  49%|▍| 7364/14932 [10:20<10:38, 11.86it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  49%|▍| 7383/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  49%|▍| 7383/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -68023,8 +68030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7365/14932 [10:20<10:37, 11.86it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  49%|▍| 7365/14932 [10:20<10:37, 11.86it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  49%|▍| 7384/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  49%|▍| 7384/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -68032,8 +68039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7366/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  49%|▍| 7366/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  49%|▍| 7385/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  49%|▍| 7385/14932 [10:19<10:33, 11.91it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -68041,8 +68048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7367/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  49%|▍| 7367/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  49%|▍| 7386/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  49%|▍| 7386/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -68050,8 +68057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7368/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  49%|▍| 7368/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  49%|▍| 7387/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  49%|▍| 7387/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -68059,8 +68066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7369/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  49%|▍| 7369/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  49%|▍| 7388/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  49%|▍| 7388/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -68068,8 +68075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7370/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  49%|▍| 7370/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  49%|▍| 7389/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  49%|▍| 7389/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -68077,8 +68084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7371/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  49%|▍| 7371/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  49%|▍| 7390/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  49%|▍| 7390/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -68086,8 +68093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7372/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  49%|▍| 7372/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  49%|▍| 7391/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  49%|▍| 7391/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -68095,8 +68102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7373/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  49%|▍| 7373/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  50%|▍| 7392/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  50%|▍| 7392/14932 [10:20<10:33, 11.91it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -68104,8 +68111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7374/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  49%|▍| 7374/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  50%|▍| 7393/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  50%|▍| 7393/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -68113,8 +68120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7375/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  49%|▍| 7375/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  50%|▍| 7394/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  50%|▍| 7394/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=0.71"
      ]
     },
     {
@@ -68122,8 +68129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7376/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  49%|▍| 7376/14932 [10:21<10:37, 11.86it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  50%|▍| 7395/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=0.71\r",
+      "Epoch 0:  50%|▍| 7395/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -68131,8 +68138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7377/14932 [10:21<10:36, 11.86it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  49%|▍| 7377/14932 [10:21<10:36, 11.86it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  50%|▍| 7396/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  50%|▍| 7396/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -68140,8 +68147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7378/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  49%|▍| 7378/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  50%|▍| 7397/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  50%|▍| 7397/14932 [10:20<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -68149,8 +68156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7379/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  49%|▍| 7379/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  50%|▍| 7398/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  50%|▍| 7398/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -68158,8 +68165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7380/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  49%|▍| 7380/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  50%|▍| 7399/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  50%|▍| 7399/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -68167,8 +68174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7381/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  49%|▍| 7381/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  50%|▍| 7400/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  50%|▍| 7400/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -68176,8 +68183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7382/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  49%|▍| 7382/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  50%|▍| 7401/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  50%|▍| 7401/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -68185,8 +68192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7383/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  49%|▍| 7383/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  50%|▍| 7402/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  50%|▍| 7402/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -68194,7 +68201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7384/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  50%|▍| 7403/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  50%|▍| 7403/14932 [10:21<10:32, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -68202,7 +68210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7384/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  50%|▍| 7404/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  50%|▍| 7404/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -68210,8 +68219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7385/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  49%|▍| 7385/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  50%|▍| 7405/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  50%|▍| 7405/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -68219,8 +68228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7386/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  49%|▍| 7386/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  50%|▍| 7406/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  50%|▍| 7406/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -68228,8 +68237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7387/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  49%|▍| 7387/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  50%|▍| 7407/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  50%|▍| 7407/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -68237,8 +68246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7388/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  49%|▍| 7388/14932 [10:22<10:36, 11.86it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  50%|▍| 7408/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  50%|▍| 7408/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -68246,8 +68255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7389/14932 [10:22<10:35, 11.86it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  49%|▍| 7389/14932 [10:22<10:35, 11.86it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  50%|▍| 7409/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  50%|▍| 7409/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -68255,8 +68264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7390/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  49%|▍| 7390/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  50%|▍| 7410/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  50%|▍| 7410/14932 [10:21<10:31, 11.91it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -68264,8 +68273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  49%|▍| 7391/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  49%|▍| 7391/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  50%|▍| 7411/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  50%|▍| 7411/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -68273,8 +68282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7392/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  50%|▍| 7392/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  50%|▍| 7412/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  50%|▍| 7412/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -68282,8 +68291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7393/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  50%|▍| 7393/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  50%|▍| 7413/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  50%|▍| 7413/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -68291,8 +68300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7394/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  50%|▍| 7394/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  50%|▍| 7414/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  50%|▍| 7414/14932 [10:22<10:31, 11.91it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -68300,8 +68309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7395/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  50%|▍| 7395/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  50%|▍| 7415/14932 [10:22<10:30, 11.91it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  50%|▍| 7415/14932 [10:22<10:30, 11.91it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -68309,8 +68318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7396/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  50%|▍| 7396/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  50%|▍| 7416/14932 [10:22<10:30, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  50%|▍| 7416/14932 [10:22<10:30, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -68318,8 +68327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7397/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  50%|▍| 7397/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  50%|▍| 7417/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  50%|▍| 7417/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -68327,8 +68336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7398/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  50%|▍| 7398/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  50%|▍| 7418/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  50%|▍| 7418/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -68336,8 +68345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7399/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  50%|▍| 7399/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  50%|▍| 7419/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  50%|▍| 7419/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -68345,8 +68354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7400/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  50%|▍| 7400/14932 [10:23<10:35, 11.86it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  50%|▍| 7420/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  50%|▍| 7420/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -68354,8 +68363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7401/14932 [10:23<10:34, 11.86it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  50%|▍| 7401/14932 [10:23<10:34, 11.86it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  50%|▍| 7421/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  50%|▍| 7421/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -68363,8 +68372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7402/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  50%|▍| 7402/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  50%|▍| 7422/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  50%|▍| 7422/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -68372,8 +68381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7403/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  50%|▍| 7403/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  50%|▍| 7423/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  50%|▍| 7423/14932 [10:22<10:30, 11.92it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -68381,8 +68390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7404/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  50%|▍| 7404/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  50%|▍| 7424/14932 [10:23<10:30, 11.91it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  50%|▍| 7424/14932 [10:23<10:30, 11.91it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -68390,8 +68399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7405/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  50%|▍| 7405/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  50%|▍| 7425/14932 [10:23<10:30, 11.91it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  50%|▍| 7425/14932 [10:23<10:30, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -68399,8 +68408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7406/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  50%|▍| 7406/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  50%|▍| 7426/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  50%|▍| 7426/14932 [10:23<10:29, 11.91it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -68408,8 +68417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7407/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  50%|▍| 7407/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  50%|▍| 7427/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  50%|▍| 7427/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -68417,8 +68426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7408/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  50%|▍| 7408/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  50%|▍| 7428/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  50%|▍| 7428/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -68426,8 +68435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7409/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  50%|▍| 7409/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  50%|▍| 7429/14932 [10:23<10:29, 11.91it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  50%|▍| 7429/14932 [10:23<10:29, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -68435,8 +68444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7410/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  50%|▍| 7410/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  50%|▍| 7430/14932 [10:23<10:29, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  50%|▍| 7430/14932 [10:23<10:29, 11.91it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -68444,8 +68453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7411/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  50%|▍| 7411/14932 [10:24<10:34, 11.86it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  50%|▍| 7431/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  50%|▍| 7431/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -68453,8 +68462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7412/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  50%|▍| 7412/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  50%|▍| 7432/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  50%|▍| 7432/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -68462,8 +68471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7413/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  50%|▍| 7413/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  50%|▍| 7433/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  50%|▍| 7433/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -68471,8 +68480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7414/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  50%|▍| 7414/14932 [10:24<10:33, 11.86it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  50%|▍| 7434/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  50%|▍| 7434/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -68480,8 +68489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7415/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  50%|▍| 7415/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  50%|▍| 7435/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  50%|▍| 7435/14932 [10:23<10:29, 11.92it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -68489,8 +68498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7416/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  50%|▍| 7416/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  50%|▍| 7436/14932 [10:24<10:29, 11.92it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  50%|▍| 7436/14932 [10:24<10:29, 11.92it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -68498,8 +68507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7417/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  50%|▍| 7417/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=0.81"
+      "Epoch 0:  50%|▍| 7437/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  50%|▍| 7437/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -68507,8 +68516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7418/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=0.81\r",
-      "Epoch 0:  50%|▍| 7418/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  50%|▍| 7438/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  50%|▍| 7438/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -68516,8 +68525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7419/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  50%|▍| 7419/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  50%|▍| 7439/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  50%|▍| 7439/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -68525,8 +68534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7420/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  50%|▍| 7420/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  50%|▍| 7440/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  50%|▍| 7440/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=0.73"
      ]
     },
     {
@@ -68534,8 +68543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7421/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  50%|▍| 7421/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  50%|▍| 7441/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=0.73\r",
+      "Epoch 0:  50%|▍| 7441/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -68543,8 +68552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7422/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  50%|▍| 7422/14932 [10:25<10:33, 11.86it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  50%|▍| 7442/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  50%|▍| 7442/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -68552,8 +68561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7423/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  50%|▍| 7423/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=1.11"
+      "Epoch 0:  50%|▍| 7443/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  50%|▍| 7443/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -68561,8 +68570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7424/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=1.11\r",
-      "Epoch 0:  50%|▍| 7424/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  50%|▍| 7444/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  50%|▍| 7444/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -68570,8 +68579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7425/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  50%|▍| 7425/14932 [10:25<10:32, 11.86it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  50%|▍| 7445/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  50%|▍| 7445/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -68579,8 +68588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7426/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  50%|▍| 7426/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  50%|▍| 7446/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  50%|▍| 7446/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -68588,8 +68597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7427/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  50%|▍| 7427/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  50%|▍| 7447/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  50%|▍| 7447/14932 [10:24<10:28, 11.92it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -68597,8 +68606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7428/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  50%|▍| 7428/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  50%|▍| 7448/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  50%|▍| 7448/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -68606,8 +68615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7429/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  50%|▍| 7429/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  50%|▍| 7449/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  50%|▍| 7449/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -68615,8 +68624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7430/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  50%|▍| 7430/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  50%|▍| 7450/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  50%|▍| 7450/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -68624,8 +68633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7431/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  50%|▍| 7431/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  50%|▍| 7451/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  50%|▍| 7451/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -68633,8 +68642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7432/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  50%|▍| 7432/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  50%|▍| 7452/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  50%|▍| 7452/14932 [10:25<10:28, 11.91it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -68642,8 +68651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7433/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  50%|▍| 7433/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  50%|▍| 7453/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  50%|▍| 7453/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -68651,8 +68660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7434/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  50%|▍| 7434/14932 [10:26<10:32, 11.86it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  50%|▍| 7454/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  50%|▍| 7454/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -68660,8 +68669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7435/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  50%|▍| 7435/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  50%|▍| 7455/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  50%|▍| 7455/14932 [10:25<10:27, 11.91it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -68669,8 +68678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7436/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  50%|▍| 7436/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  50%|▍| 7456/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  50%|▍| 7456/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -68678,8 +68687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7437/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  50%|▍| 7437/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  50%|▍| 7457/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  50%|▍| 7457/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -68687,8 +68696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7438/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  50%|▍| 7438/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  50%|▍| 7458/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  50%|▍| 7458/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -68696,8 +68705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7439/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  50%|▍| 7439/14932 [10:26<10:31, 11.86it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  50%|▍| 7459/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  50%|▍| 7459/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -68705,8 +68714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7440/14932 [10:27<10:31, 11.86it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  50%|▍| 7440/14932 [10:27<10:31, 11.86it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  50%|▍| 7460/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  50%|▍| 7460/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -68714,8 +68723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7441/14932 [10:27<10:31, 11.86it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  50%|▍| 7441/14932 [10:27<10:31, 11.86it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  50%|▍| 7461/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  50%|▍| 7461/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -68723,8 +68732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7442/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  50%|▍| 7442/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  50%|▍| 7462/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  50%|▍| 7462/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -68732,8 +68741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7443/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  50%|▍| 7443/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  50%|▍| 7463/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  50%|▍| 7463/14932 [10:26<10:27, 11.91it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -68741,8 +68750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7444/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  50%|▍| 7444/14932 [10:27<10:31, 11.87it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  50%|▍| 7464/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  50%|▍| 7464/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -68750,8 +68759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7445/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  50%|▍| 7445/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  50%|▍| 7465/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  50%|▍| 7465/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -68759,8 +68768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7446/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  50%|▍| 7446/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  50%|▌| 7466/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  50%|▌| 7466/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -68768,8 +68777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7447/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  50%|▍| 7447/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  50%|▌| 7467/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  50%|▌| 7467/14932 [10:26<10:26, 11.91it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -68777,8 +68786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7448/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  50%|▍| 7448/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  50%|▌| 7468/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  50%|▌| 7468/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -68786,8 +68795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7449/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  50%|▍| 7449/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  50%|▌| 7469/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  50%|▌| 7469/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -68795,8 +68804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7450/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  50%|▍| 7450/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  50%|▌| 7470/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  50%|▌| 7470/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -68804,8 +68813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7451/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  50%|▍| 7451/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  50%|▌| 7471/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  50%|▌| 7471/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -68813,8 +68822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7452/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  50%|▍| 7452/14932 [10:27<10:30, 11.87it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  50%|▌| 7472/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  50%|▌| 7472/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -68822,8 +68831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7453/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  50%|▍| 7453/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=0.69"
+      "Epoch 0:  50%|▌| 7473/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  50%|▌| 7473/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -68831,8 +68840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7454/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=0.69\r",
-      "Epoch 0:  50%|▍| 7454/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  50%|▌| 7474/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  50%|▌| 7474/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -68840,8 +68849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7455/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  50%|▍| 7455/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  50%|▌| 7475/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  50%|▌| 7475/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -68849,8 +68858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7456/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  50%|▍| 7456/14932 [10:28<10:30, 11.87it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  50%|▌| 7476/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  50%|▌| 7476/14932 [10:27<10:26, 11.91it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -68858,8 +68867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7457/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  50%|▍| 7457/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  50%|▌| 7477/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  50%|▌| 7477/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -68867,8 +68876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7458/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  50%|▍| 7458/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  50%|▌| 7478/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  50%|▌| 7478/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -68876,8 +68885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7459/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  50%|▍| 7459/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  50%|▌| 7479/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  50%|▌| 7479/14932 [10:27<10:25, 11.91it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -68885,8 +68894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7460/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  50%|▍| 7460/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  50%|▌| 7480/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  50%|▌| 7480/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -68894,8 +68903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7461/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  50%|▍| 7461/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  50%|▌| 7481/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  50%|▌| 7481/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -68903,8 +68912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7462/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  50%|▍| 7462/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  50%|▌| 7482/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  50%|▌| 7482/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -68912,8 +68921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7463/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  50%|▍| 7463/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=0.83"
+      "Epoch 0:  50%|▌| 7483/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  50%|▌| 7483/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -68921,8 +68930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7464/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=0.83\r",
-      "Epoch 0:  50%|▍| 7464/14932 [10:28<10:29, 11.87it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  50%|▌| 7484/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  50%|▌| 7484/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -68930,8 +68939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▍| 7465/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  50%|▍| 7465/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  50%|▌| 7485/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  50%|▌| 7485/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -68939,8 +68948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7466/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  50%|▌| 7466/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  50%|▌| 7486/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  50%|▌| 7486/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -68948,8 +68957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7467/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  50%|▌| 7467/14932 [10:29<10:29, 11.87it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  50%|▌| 7487/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  50%|▌| 7487/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -68957,8 +68966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7468/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  50%|▌| 7468/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  50%|▌| 7488/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  50%|▌| 7488/14932 [10:28<10:25, 11.91it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -68966,8 +68975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7469/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  50%|▌| 7469/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  50%|▌| 7489/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  50%|▌| 7489/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -68975,8 +68984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7470/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  50%|▌| 7470/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  50%|▌| 7490/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  50%|▌| 7490/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -68984,8 +68993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7471/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  50%|▌| 7471/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  50%|▌| 7491/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  50%|▌| 7491/14932 [10:28<10:24, 11.91it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -68993,8 +69002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7472/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  50%|▌| 7472/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  50%|▌| 7492/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  50%|▌| 7492/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -69002,8 +69011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7473/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  50%|▌| 7473/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  50%|▌| 7493/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  50%|▌| 7493/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -69011,8 +69020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7474/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  50%|▌| 7474/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  50%|▌| 7494/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  50%|▌| 7494/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -69020,8 +69029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7475/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  50%|▌| 7475/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  50%|▌| 7495/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  50%|▌| 7495/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -69029,8 +69038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7476/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  50%|▌| 7476/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  50%|▌| 7496/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  50%|▌| 7496/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -69038,8 +69047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7477/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  50%|▌| 7477/14932 [10:29<10:28, 11.87it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  50%|▌| 7497/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  50%|▌| 7497/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -69047,8 +69056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7478/14932 [10:30<10:28, 11.87it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  50%|▌| 7478/14932 [10:30<10:28, 11.87it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  50%|▌| 7498/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  50%|▌| 7498/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -69056,8 +69065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7479/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  50%|▌| 7479/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  50%|▌| 7499/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  50%|▌| 7499/14932 [10:29<10:24, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -69065,8 +69074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7480/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  50%|▌| 7480/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  50%|▌| 7500/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  50%|▌| 7500/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -69074,8 +69083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7481/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  50%|▌| 7481/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  50%|▌| 7501/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  50%|▌| 7501/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -69083,8 +69092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7482/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  50%|▌| 7482/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  50%|▌| 7502/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  50%|▌| 7502/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -69092,8 +69101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7483/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  50%|▌| 7483/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  50%|▌| 7503/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  50%|▌| 7503/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -69101,8 +69110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7484/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  50%|▌| 7484/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  50%|▌| 7504/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  50%|▌| 7504/14932 [10:29<10:23, 11.91it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -69110,8 +69119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7485/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  50%|▌| 7485/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  50%|▌| 7505/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  50%|▌| 7505/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -69119,8 +69128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7486/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  50%|▌| 7486/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  50%|▌| 7506/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  50%|▌| 7506/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -69128,8 +69137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7487/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  50%|▌| 7487/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  50%|▌| 7507/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  50%|▌| 7507/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -69137,8 +69146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7488/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  50%|▌| 7488/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  50%|▌| 7508/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  50%|▌| 7508/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -69146,8 +69155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7489/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  50%|▌| 7489/14932 [10:30<10:27, 11.87it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  50%|▌| 7509/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  50%|▌| 7509/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -69155,8 +69164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7490/14932 [10:31<10:27, 11.87it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  50%|▌| 7490/14932 [10:31<10:27, 11.87it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  50%|▌| 7510/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  50%|▌| 7510/14932 [10:30<10:23, 11.91it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -69164,8 +69173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7491/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  50%|▌| 7491/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  50%|▌| 7511/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  50%|▌| 7511/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -69173,8 +69182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7492/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  50%|▌| 7492/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  50%|▌| 7512/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  50%|▌| 7512/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -69182,8 +69191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7493/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  50%|▌| 7493/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  50%|▌| 7513/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  50%|▌| 7513/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -69191,8 +69200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7494/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  50%|▌| 7494/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  50%|▌| 7514/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  50%|▌| 7514/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -69200,8 +69209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7495/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  50%|▌| 7495/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  50%|▌| 7515/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  50%|▌| 7515/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -69209,8 +69218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7496/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  50%|▌| 7496/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  50%|▌| 7516/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  50%|▌| 7516/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -69218,8 +69227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7497/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  50%|▌| 7497/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  50%|▌| 7517/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  50%|▌| 7517/14932 [10:30<10:22, 11.91it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -69227,8 +69236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7498/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  50%|▌| 7498/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  50%|▌| 7518/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  50%|▌| 7518/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -69236,8 +69245,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7499/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  50%|▌| 7499/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  50%|▌| 7519/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -69245,8 +69253,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7500/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  50%|▌| 7500/14932 [10:31<10:26, 11.87it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  50%|▌| 7519/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -69254,8 +69261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7501/14932 [10:31<10:25, 11.87it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  50%|▌| 7501/14932 [10:31<10:25, 11.87it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  50%|▌| 7520/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  50%|▌| 7520/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -69263,8 +69270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7502/14932 [10:31<10:25, 11.87it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  50%|▌| 7502/14932 [10:31<10:25, 11.87it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  50%|▌| 7521/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  50%|▌| 7521/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -69272,8 +69279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7503/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  50%|▌| 7503/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  50%|▌| 7522/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  50%|▌| 7522/14932 [10:31<10:22, 11.91it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -69281,8 +69288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7504/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  50%|▌| 7504/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  50%|▌| 7523/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  50%|▌| 7523/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -69290,8 +69297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7505/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  50%|▌| 7505/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  50%|▌| 7524/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  50%|▌| 7524/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -69299,8 +69306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7506/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  50%|▌| 7506/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  50%|▌| 7525/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  50%|▌| 7525/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -69308,8 +69315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7507/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  50%|▌| 7507/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=0.94"
+      "Epoch 0:  50%|▌| 7526/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  50%|▌| 7526/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -69317,8 +69324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7508/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=0.94\r",
-      "Epoch 0:  50%|▌| 7508/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  50%|▌| 7527/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  50%|▌| 7527/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -69326,8 +69333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7509/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  50%|▌| 7509/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  50%|▌| 7528/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  50%|▌| 7528/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -69335,8 +69342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7510/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  50%|▌| 7510/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  50%|▌| 7529/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  50%|▌| 7529/14932 [10:31<10:21, 11.91it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -69344,8 +69351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7511/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  50%|▌| 7511/14932 [10:32<10:25, 11.87it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  50%|▌| 7530/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  50%|▌| 7530/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -69353,8 +69360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7512/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  50%|▌| 7512/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  50%|▌| 7531/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  50%|▌| 7531/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -69362,8 +69369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7513/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  50%|▌| 7513/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  50%|▌| 7532/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  50%|▌| 7532/14932 [10:32<10:21, 11.91it/s, v_num=ui8w, train/loss=1.19"
      ]
     },
     {
@@ -69371,8 +69378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7514/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  50%|▌| 7514/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  50%|▌| 7533/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=1.19\r",
+      "Epoch 0:  50%|▌| 7533/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -69380,8 +69387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7515/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  50%|▌| 7515/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  50%|▌| 7534/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  50%|▌| 7534/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -69389,8 +69396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7516/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  50%|▌| 7516/14932 [10:32<10:24, 11.87it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  50%|▌| 7535/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  50%|▌| 7535/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -69398,8 +69405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7517/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  50%|▌| 7517/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  50%|▌| 7536/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  50%|▌| 7536/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -69407,8 +69414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7518/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  50%|▌| 7518/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  50%|▌| 7537/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  50%|▌| 7537/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -69416,8 +69423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7519/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  50%|▌| 7519/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  50%|▌| 7538/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  50%|▌| 7538/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -69425,8 +69432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7520/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  50%|▌| 7520/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  50%|▌| 7539/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  50%|▌| 7539/14932 [10:32<10:20, 11.91it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -69434,8 +69441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7521/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  50%|▌| 7521/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  50%|▌| 7540/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  50%|▌| 7540/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -69443,8 +69450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7522/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  50%|▌| 7522/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  51%|▌| 7541/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  51%|▌| 7541/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -69452,8 +69459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7523/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  50%|▌| 7523/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  51%|▌| 7542/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  51%|▌| 7542/14932 [10:32<10:20, 11.92it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -69461,8 +69468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7524/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  50%|▌| 7524/14932 [10:33<10:24, 11.87it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  51%|▌| 7543/14932 [10:33<10:20, 11.92it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  51%|▌| 7543/14932 [10:33<10:20, 11.92it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -69470,8 +69477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7525/14932 [10:33<10:23, 11.87it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  50%|▌| 7525/14932 [10:33<10:23, 11.87it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  51%|▌| 7544/14932 [10:33<10:20, 11.92it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  51%|▌| 7544/14932 [10:33<10:20, 11.92it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -69479,8 +69486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7526/14932 [10:33<10:23, 11.87it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  50%|▌| 7526/14932 [10:33<10:23, 11.87it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  51%|▌| 7545/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  51%|▌| 7545/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -69488,8 +69495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7527/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  50%|▌| 7527/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  51%|▌| 7546/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  51%|▌| 7546/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -69497,8 +69504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7528/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  50%|▌| 7528/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  51%|▌| 7547/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  51%|▌| 7547/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -69506,8 +69513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7529/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  50%|▌| 7529/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  51%|▌| 7548/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  51%|▌| 7548/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -69515,8 +69522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7530/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  50%|▌| 7530/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  51%|▌| 7549/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  51%|▌| 7549/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -69524,8 +69531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7531/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  50%|▌| 7531/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  51%|▌| 7550/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  51%|▌| 7550/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -69533,8 +69540,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7532/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  50%|▌| 7532/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  51%|▌| 7551/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -69542,8 +69548,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7533/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  50%|▌| 7533/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  51%|▌| 7551/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -69551,8 +69556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7534/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  50%|▌| 7534/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  51%|▌| 7552/14932 [10:33<10:19, 11.91it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  51%|▌| 7552/14932 [10:33<10:19, 11.91it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -69560,8 +69565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7535/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  50%|▌| 7535/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  51%|▌| 7553/14932 [10:33<10:19, 11.91it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  51%|▌| 7553/14932 [10:33<10:19, 11.91it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -69569,8 +69574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7536/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  50%|▌| 7536/14932 [10:34<10:23, 11.87it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  51%|▌| 7554/14932 [10:33<10:19, 11.92it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  51%|▌| 7554/14932 [10:33<10:19, 11.91it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -69578,8 +69583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|��| 7537/14932 [10:34<10:22, 11.87it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  50%|▌| 7537/14932 [10:34<10:22, 11.87it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  51%|▌| 7555/14932 [10:34<10:19, 11.92it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  51%|▌| 7555/14932 [10:34<10:19, 11.92it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -69587,8 +69592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7538/14932 [10:34<10:22, 11.87it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  50%|▌| 7538/14932 [10:34<10:22, 11.87it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  51%|▌| 7556/14932 [10:34<10:19, 11.92it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  51%|▌| 7556/14932 [10:34<10:19, 11.92it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -69596,8 +69601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7539/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  50%|▌| 7539/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  51%|▌| 7557/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  51%|▌| 7557/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -69605,8 +69610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  50%|▌| 7540/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  50%|▌| 7540/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  51%|▌| 7558/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  51%|▌| 7558/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -69614,8 +69619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7541/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  51%|▌| 7541/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  51%|▌| 7559/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  51%|▌| 7559/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -69623,8 +69628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7542/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  51%|▌| 7542/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  51%|▌| 7560/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  51%|▌| 7560/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -69632,8 +69637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7543/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  51%|▌| 7543/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  51%|▌| 7561/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  51%|▌| 7561/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -69641,8 +69646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7544/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  51%|▌| 7544/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  51%|▌| 7562/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  51%|▌| 7562/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -69650,8 +69655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7545/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  51%|▌| 7545/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  51%|▌| 7563/14932 [10:34<10:18, 11.91it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  51%|▌| 7563/14932 [10:34<10:18, 11.91it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -69659,8 +69664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7546/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  51%|▌| 7546/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  51%|▌| 7564/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  51%|▌| 7564/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -69668,8 +69673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7547/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  51%|▌| 7547/14932 [10:35<10:22, 11.87it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  51%|▌| 7565/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  51%|▌| 7565/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -69677,8 +69682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7548/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  51%|▌| 7548/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  51%|▌| 7566/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  51%|▌| 7566/14932 [10:34<10:18, 11.92it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -69686,8 +69691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7549/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  51%|▌| 7549/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  51%|▌| 7567/14932 [10:35<10:18, 11.92it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  51%|▌| 7567/14932 [10:35<10:18, 11.92it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -69695,8 +69700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7550/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  51%|▌| 7550/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  51%|▌| 7568/14932 [10:35<10:18, 11.92it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  51%|▌| 7568/14932 [10:35<10:18, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -69704,8 +69709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7551/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  51%|▌| 7551/14932 [10:35<10:21, 11.87it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  51%|▌| 7569/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  51%|▌| 7569/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -69713,8 +69718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7552/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  51%|▌| 7552/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  51%|▌| 7570/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  51%|▌| 7570/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -69722,8 +69727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7553/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  51%|▌| 7553/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  51%|▌| 7571/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  51%|▌| 7571/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -69731,8 +69736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7554/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  51%|▌| 7554/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  51%|▌| 7572/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  51%|▌| 7572/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -69740,8 +69745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7555/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  51%|▌| 7555/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  51%|▌| 7573/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  51%|▌| 7573/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -69749,8 +69754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7556/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  51%|▌| 7556/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  51%|▌| 7574/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  51%|▌| 7574/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -69758,8 +69763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7557/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  51%|▌| 7557/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  51%|▌| 7575/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  51%|▌| 7575/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -69767,8 +69772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7558/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  51%|▌| 7558/14932 [10:36<10:21, 11.87it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  51%|▌| 7576/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  51%|▌| 7576/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -69776,8 +69781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7559/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  51%|▌| 7559/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  51%|▌| 7577/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  51%|▌| 7577/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -69785,8 +69790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7560/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  51%|▌| 7560/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  51%|▌| 7578/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  51%|▌| 7578/14932 [10:35<10:17, 11.92it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -69794,8 +69799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7561/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  51%|▌| 7561/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  51%|▌| 7579/14932 [10:36<10:17, 11.92it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  51%|▌| 7579/14932 [10:36<10:17, 11.92it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -69803,8 +69808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7562/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  51%|▌| 7562/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  51%|▌| 7580/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  51%|▌| 7580/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -69812,8 +69817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7563/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  51%|▌| 7563/14932 [10:36<10:20, 11.87it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  51%|▌| 7581/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  51%|▌| 7581/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -69821,8 +69826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7564/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  51%|▌| 7564/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  51%|▌| 7582/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  51%|▌| 7582/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -69830,8 +69835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7565/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  51%|▌| 7565/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  51%|▌| 7583/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  51%|▌| 7583/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -69839,8 +69844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7566/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  51%|▌| 7566/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=1.99"
+      "Epoch 0:  51%|▌| 7584/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  51%|▌| 7584/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -69848,8 +69853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7567/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=1.99\r",
-      "Epoch 0:  51%|▌| 7567/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  51%|▌| 7585/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  51%|▌| 7585/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -69857,8 +69862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7568/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  51%|▌| 7568/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  51%|▌| 7586/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  51%|▌| 7586/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -69866,8 +69871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7569/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  51%|▌| 7569/14932 [10:37<10:20, 11.87it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  51%|▌| 7587/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  51%|▌| 7587/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -69875,8 +69880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7570/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  51%|▌| 7570/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  51%|▌| 7588/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  51%|▌| 7588/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -69884,8 +69889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7571/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  51%|▌| 7571/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  51%|▌| 7589/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  51%|▌| 7589/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -69893,8 +69898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7572/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  51%|▌| 7572/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  51%|▌| 7590/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  51%|▌| 7590/14932 [10:36<10:16, 11.92it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -69902,8 +69907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7573/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  51%|▌| 7573/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  51%|▌| 7591/14932 [10:37<10:16, 11.92it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  51%|▌| 7591/14932 [10:37<10:16, 11.92it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -69911,8 +69916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7574/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  51%|▌| 7574/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  51%|▌| 7592/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  51%|▌| 7592/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -69920,8 +69925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7575/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  51%|▌| 7575/14932 [10:37<10:19, 11.87it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  51%|▌| 7593/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  51%|▌| 7593/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -69929,8 +69934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7576/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  51%|▌| 7576/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  51%|▌| 7594/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  51%|▌| 7594/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -69938,8 +69943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7577/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  51%|▌| 7577/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  51%|▌| 7595/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  51%|▌| 7595/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -69947,8 +69952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7578/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  51%|▌| 7578/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  51%|▌| 7596/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  51%|▌| 7596/14932 [10:37<10:15, 11.92it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -69956,8 +69961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7579/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  51%|▌| 7579/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  51%|▌| 7597/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  51%|▌| 7597/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -69965,8 +69970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7580/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  51%|▌| 7580/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  51%|▌| 7598/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  51%|▌| 7598/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -69974,8 +69979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7581/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  51%|▌| 7581/14932 [10:38<10:19, 11.87it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  51%|▌| 7599/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  51%|▌| 7599/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -69983,8 +69988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7582/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  51%|▌| 7582/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  51%|▌| 7600/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  51%|▌| 7600/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -69992,8 +69997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7583/14932 [10:38<10:18, 11.88it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  51%|▌| 7583/14932 [10:38<10:18, 11.88it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  51%|▌| 7601/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  51%|▌| 7601/14932 [10:37<10:15, 11.91it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -70001,8 +70006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7584/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  51%|▌| 7584/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  51%|▌| 7602/14932 [10:38<10:15, 11.91it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  51%|▌| 7602/14932 [10:38<10:15, 11.91it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -70010,8 +70015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7585/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  51%|▌| 7585/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  51%|▌| 7603/14932 [10:38<10:15, 11.91it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  51%|▌| 7603/14932 [10:38<10:15, 11.91it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -70019,8 +70024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7586/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  51%|▌| 7586/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  51%|▌| 7604/14932 [10:38<10:15, 11.92it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  51%|▌| 7604/14932 [10:38<10:15, 11.92it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -70028,8 +70033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7587/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  51%|▌| 7587/14932 [10:38<10:18, 11.87it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  51%|▌| 7605/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  51%|▌| 7605/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -70037,8 +70042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7588/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  51%|▌| 7588/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  51%|▌| 7606/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  51%|▌| 7606/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -70046,8 +70051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7589/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  51%|▌| 7589/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  51%|▌| 7607/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  51%|▌| 7607/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -70055,8 +70060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7590/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  51%|▌| 7590/14932 [10:39<10:18, 11.87it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  51%|▌| 7608/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  51%|▌| 7608/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -70064,8 +70069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7591/14932 [10:39<10:18, 11.88it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  51%|▌| 7591/14932 [10:39<10:18, 11.88it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  51%|▌| 7609/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  51%|▌| 7609/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -70073,8 +70078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7592/14932 [10:39<10:18, 11.88it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  51%|▌| 7592/14932 [10:39<10:18, 11.88it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  51%|▌| 7610/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  51%|▌| 7610/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -70082,8 +70087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7593/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  51%|▌| 7593/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  51%|▌| 7611/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  51%|▌| 7611/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -70091,8 +70096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7594/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  51%|▌| 7594/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  51%|▌| 7612/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  51%|▌| 7612/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -70100,8 +70105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7595/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  51%|▌| 7595/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  51%|▌| 7613/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  51%|▌| 7613/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -70109,8 +70114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7596/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  51%|▌| 7596/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  51%|▌| 7614/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  51%|▌| 7614/14932 [10:38<10:14, 11.92it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -70118,8 +70123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7597/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  51%|▌| 7597/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  51%|▌| 7615/14932 [10:39<10:14, 11.92it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  51%|▌| 7615/14932 [10:39<10:14, 11.92it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -70127,8 +70132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7598/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  51%|▌| 7598/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  51%|▌| 7616/14932 [10:39<10:14, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  51%|▌| 7616/14932 [10:39<10:14, 11.91it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -70136,8 +70141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7599/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  51%|▌| 7599/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  51%|▌| 7617/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  51%|▌| 7617/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -70145,8 +70150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7600/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  51%|▌| 7600/14932 [10:39<10:17, 11.88it/s, v_num=o30c, train/loss=0.85"
+      "Epoch 0:  51%|▌| 7618/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  51%|▌| 7618/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -70154,8 +70159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7601/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=0.85\r",
-      "Epoch 0:  51%|▌| 7601/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  51%|▌| 7619/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  51%|▌| 7619/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -70163,8 +70168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7602/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  51%|▌| 7602/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  51%|▌| 7620/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  51%|▌| 7620/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -70172,8 +70177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7603/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  51%|▌| 7603/14932 [10:40<10:17, 11.88it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  51%|▌| 7621/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  51%|▌| 7621/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -70181,8 +70186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7604/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  51%|▌| 7604/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  51%|▌| 7622/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  51%|▌| 7622/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -70190,8 +70195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7605/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  51%|▌| 7605/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  51%|▌| 7623/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  51%|▌| 7623/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -70199,8 +70204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7606/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  51%|▌| 7606/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  51%|▌| 7624/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  51%|▌| 7624/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -70208,8 +70213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7607/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  51%|▌| 7607/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  51%|▌| 7625/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  51%|▌| 7625/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -70217,8 +70222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7608/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  51%|▌| 7608/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  51%|▌| 7626/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  51%|▌| 7626/14932 [10:39<10:13, 11.92it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -70226,8 +70231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7609/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  51%|▌| 7609/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  51%|▌| 7627/14932 [10:40<10:13, 11.92it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  51%|▌| 7627/14932 [10:40<10:13, 11.92it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -70235,8 +70240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7610/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  51%|▌| 7610/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  51%|▌| 7628/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  51%|▌| 7628/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -70244,8 +70249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7611/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  51%|▌| 7611/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  51%|▌| 7629/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  51%|▌| 7629/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -70253,8 +70258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7612/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  51%|▌| 7612/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  51%|▌| 7630/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  51%|▌| 7630/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -70262,8 +70267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7613/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  51%|▌| 7613/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  51%|▌| 7631/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  51%|▌| 7631/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -70271,7 +70276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7614/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  51%|▌| 7632/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  51%|▌| 7632/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -70279,7 +70285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7614/14932 [10:40<10:16, 11.88it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  51%|▌| 7633/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  51%|▌| 7633/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -70287,8 +70294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7615/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  51%|▌| 7615/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  51%|▌| 7634/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  51%|▌| 7634/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -70296,8 +70303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7616/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  51%|▌| 7616/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  51%|▌| 7635/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  51%|▌| 7635/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -70305,8 +70312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7617/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  51%|▌| 7617/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  51%|▌| 7636/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  51%|▌| 7636/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -70314,8 +70321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7618/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  51%|▌| 7618/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  51%|▌| 7637/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  51%|▌| 7637/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -70323,8 +70330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7619/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  51%|▌| 7619/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  51%|▌| 7638/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  51%|▌| 7638/14932 [10:40<10:12, 11.92it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -70332,8 +70339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7620/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  51%|▌| 7620/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  51%|▌| 7639/14932 [10:41<10:12, 11.92it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  51%|▌| 7639/14932 [10:41<10:12, 11.92it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -70341,8 +70348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7621/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  51%|▌| 7621/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  51%|▌| 7640/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  51%|▌| 7640/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -70350,8 +70357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7622/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  51%|▌| 7622/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  51%|▌| 7641/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  51%|▌| 7641/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -70359,8 +70366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7623/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  51%|▌| 7623/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  51%|▌| 7642/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  51%|▌| 7642/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -70368,8 +70375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7624/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  51%|▌| 7624/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  51%|▌| 7643/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  51%|▌| 7643/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -70377,8 +70384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7625/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  51%|▌| 7625/14932 [10:41<10:15, 11.88it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  51%|▌| 7644/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  51%|▌| 7644/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -70386,8 +70393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7626/14932 [10:41<10:14, 11.88it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  51%|▌| 7626/14932 [10:41<10:14, 11.88it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  51%|▌| 7645/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  51%|▌| 7645/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -70395,8 +70402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7627/14932 [10:41<10:14, 11.88it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  51%|▌| 7627/14932 [10:41<10:14, 11.88it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  51%|▌| 7646/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  51%|▌| 7646/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -70404,8 +70411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7628/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  51%|▌| 7628/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  51%|▌| 7647/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  51%|▌| 7647/14932 [10:41<10:11, 11.92it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -70413,8 +70420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7629/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  51%|▌| 7629/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  51%|▌| 7648/14932 [10:41<10:11, 11.91it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  51%|▌| 7648/14932 [10:41<10:11, 11.91it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -70422,8 +70429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7630/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  51%|▌| 7630/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  51%|▌| 7649/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  51%|▌| 7649/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -70431,8 +70438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7631/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  51%|▌| 7631/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  51%|▌| 7650/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  51%|▌| 7650/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -70440,8 +70447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7632/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  51%|���| 7632/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  51%|▌| 7651/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  51%|▌| 7651/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -70449,8 +70456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7633/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  51%|▌| 7633/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  51%|▌| 7652/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  51%|▌| 7652/14932 [10:42<10:11, 11.91it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -70458,8 +70465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7634/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  51%|▌| 7634/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  51%|▌| 7653/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  51%|▌| 7653/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -70467,8 +70474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7635/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  51%|▌| 7635/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.94"
+      "Epoch 0:  51%|▌| 7654/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  51%|▌| 7654/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -70476,8 +70483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7636/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.94\r",
-      "Epoch 0:  51%|▌| 7636/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  51%|▌| 7655/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  51%|▌| 7655/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -70485,8 +70492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7637/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  51%|▌| 7637/14932 [10:42<10:14, 11.88it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  51%|▌| 7656/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  51%|▌| 7656/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -70494,8 +70501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7638/14932 [10:42<10:13, 11.88it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  51%|▌| 7638/14932 [10:42<10:13, 11.88it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  51%|▌| 7657/14932 [10:42<10:10, 11.92it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  51%|▌| 7657/14932 [10:42<10:10, 11.92it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -70503,8 +70510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7639/14932 [10:42<10:13, 11.88it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  51%|▌| 7639/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  51%|▌| 7658/14932 [10:42<10:10, 11.92it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  51%|▌| 7658/14932 [10:42<10:10, 11.92it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -70512,8 +70519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7640/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  51%|▌| 7640/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  51%|▌| 7659/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  51%|▌| 7659/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -70521,8 +70528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7641/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  51%|▌| 7641/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  51%|▌| 7660/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  51%|▌| 7660/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -70530,8 +70537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7642/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  51%|▌| 7642/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  51%|▌| 7661/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  51%|▌| 7661/14932 [10:42<10:10, 11.91it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -70539,8 +70546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7643/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  51%|▌| 7643/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  51%|▌| 7662/14932 [10:43<10:10, 11.92it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  51%|▌| 7662/14932 [10:43<10:10, 11.92it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -70548,8 +70555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7644/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  51%|▌| 7644/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  51%|▌| 7663/14932 [10:43<10:10, 11.92it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  51%|▌| 7663/14932 [10:43<10:10, 11.92it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -70557,8 +70564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7645/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  51%|▌| 7645/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=0.76"
+      "Epoch 0:  51%|▌| 7664/14932 [10:43<10:09, 11.92it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  51%|▌| 7664/14932 [10:43<10:09, 11.92it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -70566,8 +70573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7646/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=0.76\r",
-      "Epoch 0:  51%|▌| 7646/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  51%|▌| 7665/14932 [10:43<10:09, 11.92it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  51%|▌| 7665/14932 [10:43<10:09, 11.92it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -70575,8 +70582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7647/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  51%|▌| 7647/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  51%|▌| 7666/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  51%|▌| 7666/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -70584,8 +70591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7648/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  51%|▌| 7648/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  51%|▌| 7667/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  51%|▌| 7667/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -70593,8 +70600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7649/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  51%|▌| 7649/14932 [10:43<10:13, 11.88it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  51%|▌| 7668/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  51%|▌| 7668/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -70602,8 +70609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7650/14932 [10:44<10:13, 11.88it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  51%|▌| 7650/14932 [10:44<10:13, 11.88it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  51%|▌| 7669/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  51%|▌| 7669/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -70611,8 +70618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7651/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  51%|▌| 7651/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  51%|▌| 7670/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  51%|▌| 7670/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -70620,8 +70627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7652/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  51%|▌| 7652/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  51%|▌| 7671/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  51%|▌| 7671/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -70629,8 +70636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7653/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  51%|▌| 7653/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  51%|▌| 7672/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  51%|▌| 7672/14932 [10:43<10:09, 11.91it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -70638,8 +70645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7654/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  51%|▌| 7654/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  51%|▌| 7673/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  51%|▌| 7673/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -70647,8 +70654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7655/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  51%|▌| 7655/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  51%|▌| 7674/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  51%|▌| 7674/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -70656,8 +70663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7656/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  51%|▌| 7656/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  51%|▌| 7675/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  51%|▌| 7675/14932 [10:44<10:09, 11.91it/s, v_num=ui8w, train/loss=5.03"
      ]
     },
     {
@@ -70665,8 +70672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7657/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  51%|▌| 7657/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  51%|▌| 7676/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=5.03\r",
+      "Epoch 0:  51%|▌| 7676/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -70674,8 +70681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7658/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  51%|▌| 7658/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  51%|▌| 7677/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  51%|▌| 7677/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -70683,8 +70690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7659/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  51%|▌| 7659/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  51%|▌| 7678/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  51%|▌| 7678/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -70692,8 +70699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7660/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  51%|▌| 7660/14932 [10:44<10:12, 11.88it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  51%|▌| 7679/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  51%|▌| 7679/14932 [10:44<10:08, 11.92it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -70701,8 +70708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7661/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  51%|▌| 7661/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  51%|▌| 7680/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  51%|▌| 7680/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -70710,8 +70717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7662/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  51%|▌| 7662/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  51%|▌| 7681/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  51%|▌| 7681/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -70719,8 +70726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7663/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  51%|▌| 7663/14932 [10:44<10:11, 11.88it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  51%|▌| 7682/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  51%|▌| 7682/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -70728,8 +70735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7664/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  51%|▌| 7664/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=0.94"
+      "Epoch 0:  51%|▌| 7683/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  51%|▌| 7683/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -70737,8 +70744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7665/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=0.94\r",
-      "Epoch 0:  51%|▌| 7665/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  51%|▌| 7684/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  51%|▌| 7684/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -70746,8 +70753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7666/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  51%|▌| 7666/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  51%|▌| 7685/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  51%|▌| 7685/14932 [10:44<10:08, 11.91it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -70755,8 +70762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7667/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  51%|▌| 7667/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  51%|▌| 7686/14932 [10:45<10:08, 11.91it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  51%|▌| 7686/14932 [10:45<10:08, 11.91it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -70764,8 +70771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7668/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  51%|▌| 7668/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  51%|▌| 7687/14932 [10:45<10:08, 11.92it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  51%|▌| 7687/14932 [10:45<10:08, 11.92it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -70773,8 +70780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7669/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  51%|▌| 7669/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  51%|▌| 7688/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  51%|▌| 7688/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -70782,8 +70789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7670/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  51%|▌| 7670/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  51%|▌| 7689/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  51%|▌| 7689/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -70791,8 +70798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7671/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  51%|▌| 7671/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  52%|▌| 7690/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  52%|▌| 7690/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -70800,8 +70807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7672/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  51%|▌| 7672/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  52%|▌| 7691/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  52%|▌| 7691/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -70809,8 +70816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7673/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  51%|▌| 7673/14932 [10:45<10:11, 11.88it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  52%|▌| 7692/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  52%|▌| 7692/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -70818,8 +70825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7674/14932 [10:45<10:10, 11.88it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  51%|▌| 7674/14932 [10:45<10:10, 11.88it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  52%|▌| 7693/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  52%|▌| 7693/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -70827,8 +70834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7675/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  51%|▌| 7675/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  52%|▌| 7694/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  52%|▌| 7694/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -70836,8 +70843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7676/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  51%|▌| 7676/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=1.32"
+      "Epoch 0:  52%|▌| 7695/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  52%|▌| 7695/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -70845,8 +70852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7677/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=1.32\r",
-      "Epoch 0:  51%|▌| 7677/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  52%|▌| 7696/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  52%|▌| 7696/14932 [10:45<10:07, 11.92it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -70854,8 +70861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7678/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  51%|▌| 7678/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  52%|▌| 7697/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  52%|▌| 7697/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -70863,8 +70870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7679/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  51%|▌| 7679/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  52%|▌| 7698/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  52%|▌| 7698/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -70872,8 +70879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7680/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  51%|▌| 7680/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  52%|▌| 7699/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  52%|▌| 7699/14932 [10:46<10:07, 11.91it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -70881,8 +70888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7681/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  51%|▌| 7681/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  52%|▌| 7700/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  52%|▌| 7700/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -70890,8 +70897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7682/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  51%|▌| 7682/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  52%|▌| 7701/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  52%|▌| 7701/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -70899,8 +70906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7683/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  51%|▌| 7683/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  52%|▌| 7702/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  52%|▌| 7702/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -70908,8 +70915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7684/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  51%|▌| 7684/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  52%|▌| 7703/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  52%|▌| 7703/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -70917,8 +70924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7685/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  51%|▌| 7685/14932 [10:46<10:10, 11.88it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  52%|▌| 7704/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  52%|▌| 7704/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -70926,8 +70933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7686/14932 [10:46<10:09, 11.88it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  51%|▌| 7686/14932 [10:46<10:09, 11.88it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  52%|▌| 7705/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  52%|▌| 7705/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -70935,8 +70942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7687/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  51%|▌| 7687/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  52%|▌| 7706/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  52%|▌| 7706/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -70944,8 +70951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7688/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  51%|▌| 7688/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  52%|▌| 7707/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  52%|▌| 7707/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -70953,8 +70960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  51%|▌| 7689/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  51%|▌| 7689/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  52%|▌| 7708/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  52%|▌| 7708/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -70962,8 +70969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7690/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  52%|▌| 7690/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  52%|▌| 7709/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  52%|▌| 7709/14932 [10:46<10:06, 11.92it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -70971,8 +70978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7691/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  52%|▌| 7691/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  52%|▌| 7710/14932 [10:46<10:05, 11.92it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  52%|▌| 7710/14932 [10:46<10:05, 11.92it/s, v_num=ui8w, train/loss=1.57"
      ]
     },
     {
@@ -70980,8 +70987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7692/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  52%|▌| 7692/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  52%|▌| 7711/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=1.57\r",
+      "Epoch 0:  52%|▌| 7711/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -70989,8 +70996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7693/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  52%|▌| 7693/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  52%|▌| 7712/14932 [10:47<10:05, 11.91it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  52%|▌| 7712/14932 [10:47<10:05, 11.91it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -70998,8 +71005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7694/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  52%|▌| 7694/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  52%|▌| 7713/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  52%|▌| 7713/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -71007,8 +71014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7695/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  52%|▌| 7695/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  52%|▌| 7714/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  52%|▌| 7714/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -71016,8 +71023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7696/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  52%|▌| 7696/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  52%|▌| 7715/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  52%|▌| 7715/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -71025,8 +71032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7697/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  52%|▌| 7697/14932 [10:47<10:09, 11.88it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  52%|▌| 7716/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  52%|▌| 7716/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -71034,8 +71041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7698/14932 [10:47<10:08, 11.88it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  52%|▌| 7698/14932 [10:47<10:08, 11.88it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  52%|▌| 7717/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  52%|▌| 7717/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -71043,8 +71050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7699/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  52%|▌| 7699/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  52%|▌| 7718/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  52%|▌| 7718/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -71052,8 +71059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7700/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  52%|▌| 7700/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  52%|▌| 7719/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  52%|▌| 7719/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -71061,8 +71068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7701/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  52%|▌| 7701/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  52%|▌| 7720/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  52%|▌| 7720/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -71070,8 +71077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7702/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  52%|▌| 7702/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  52%|▌| 7721/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  52%|▌| 7721/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -71079,8 +71086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7703/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  52%|▌| 7703/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  52%|▌| 7722/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  52%|▌| 7722/14932 [10:47<10:05, 11.92it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -71088,8 +71095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7704/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  52%|▌| 7704/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  52%|▌| 7723/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  52%|▌| 7723/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -71097,8 +71104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7705/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  52%|▌| 7705/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  52%|▌| 7724/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  52%|▌| 7724/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -71106,8 +71113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7706/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  52%|▌| 7706/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  52%|▌| 7725/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  52%|▌| 7725/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -71115,8 +71122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7707/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  52%|▌| 7707/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  52%|▌| 7726/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  52%|▌| 7726/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -71124,8 +71131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7708/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  52%|▌| 7708/14932 [10:48<10:08, 11.88it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  52%|▌| 7727/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  52%|▌| 7727/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -71133,8 +71140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7709/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  52%|▌| 7709/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  52%|▌| 7728/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  52%|▌| 7728/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -71142,8 +71149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7710/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  52%|▌| 7710/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  52%|▌| 7729/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  52%|▌| 7729/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -71151,8 +71158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7711/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  52%|▌| 7711/14932 [10:48<10:07, 11.88it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  52%|▌| 7730/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  52%|▌| 7730/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -71160,8 +71167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7712/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  52%|▌| 7712/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  52%|▌| 7731/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  52%|▌| 7731/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -71169,8 +71176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7713/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  52%|▌| 7713/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  52%|▌| 7732/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  52%|▌| 7732/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -71178,8 +71185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7714/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  52%|▌| 7714/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  52%|▌| 7733/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  52%|▌| 7733/14932 [10:48<10:04, 11.92it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -71187,8 +71194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7715/14932 [10:49<10:07, 11.87it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  52%|▌| 7715/14932 [10:49<10:07, 11.87it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  52%|▌| 7734/14932 [10:48<10:03, 11.92it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  52%|▌| 7734/14932 [10:48<10:03, 11.92it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -71196,8 +71203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7716/14932 [10:49<10:07, 11.87it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  52%|▌| 7716/14932 [10:49<10:07, 11.87it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  52%|▌| 7735/14932 [10:48<10:03, 11.92it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  52%|▌| 7735/14932 [10:48<10:03, 11.92it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -71205,8 +71212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7717/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  52%|▌| 7717/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  52%|▌| 7736/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  52%|▌| 7736/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -71214,8 +71221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7718/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  52%|▌| 7718/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  52%|▌| 7737/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  52%|▌| 7737/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -71223,8 +71230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7719/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  52%|▌| 7719/14932 [10:49<10:07, 11.88it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  52%|▌| 7738/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  52%|▌| 7738/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -71232,8 +71239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7720/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  52%|▌| 7720/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  52%|▌| 7739/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  52%|▌| 7739/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -71241,8 +71248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7721/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  52%|▌| 7721/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  52%|▌| 7740/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  52%|▌| 7740/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -71250,8 +71257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7722/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  52%|▌| 7722/14932 [10:50<10:07, 11.88it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  52%|▌| 7741/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  52%|▌| 7741/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -71259,8 +71266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7723/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  52%|▌| 7723/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  52%|▌| 7742/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  52%|▌| 7742/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -71268,8 +71275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7724/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  52%|▌| 7724/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  52%|▌| 7743/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  52%|▌| 7743/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -71277,8 +71284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7725/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  52%|▌| 7725/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  52%|▌| 7744/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  52%|▌| 7744/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -71286,8 +71293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7726/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  52%|▌| 7726/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  52%|▌| 7745/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  52%|▌| 7745/14932 [10:49<10:03, 11.92it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -71295,8 +71302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7727/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  52%|▌| 7727/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  52%|▌| 7746/14932 [10:49<10:02, 11.92it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  52%|▌| 7746/14932 [10:49<10:02, 11.92it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -71304,8 +71311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7728/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  52%|▌| 7728/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  52%|▌| 7747/14932 [10:49<10:02, 11.92it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  52%|▌| 7747/14932 [10:49<10:02, 11.92it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -71313,8 +71320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7729/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  52%|▌| 7729/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  52%|▌| 7748/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  52%|▌| 7748/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -71322,8 +71329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7730/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  52%|▌| 7730/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  52%|▌| 7749/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  52%|▌| 7749/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -71331,8 +71338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7731/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  52%|▌| 7731/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  52%|▌| 7750/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  52%|▌| 7750/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=6.50"
      ]
     },
     {
@@ -71340,8 +71347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7732/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  52%|▌| 7732/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  52%|▌| 7751/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=6.50\r",
+      "Epoch 0:  52%|▌| 7751/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -71349,8 +71356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7733/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  52%|▌| 7733/14932 [10:50<10:06, 11.88it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  52%|▌| 7752/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  52%|▌| 7752/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -71358,8 +71365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7734/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  52%|▌| 7734/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  52%|▌| 7753/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  52%|▌| 7753/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -71367,8 +71374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7735/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  52%|▌| 7735/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  52%|▌| 7754/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  52%|▌| 7754/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -71376,8 +71383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7736/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  52%|▌| 7736/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  52%|▌| 7755/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  52%|▌| 7755/14932 [10:50<10:02, 11.92it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -71385,8 +71392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7737/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  52%|▌| 7737/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  52%|▌| 7756/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  52%|▌| 7756/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -71394,8 +71401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7738/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  52%|▌| 7738/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  52%|▌| 7757/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  52%|▌| 7757/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -71403,8 +71410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7739/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  52%|▌| 7739/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  52%|▌| 7758/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  52%|▌| 7758/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=1.61"
      ]
     },
     {
@@ -71412,8 +71419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7740/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  52%|▌| 7740/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  52%|▌| 7759/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=1.61\r",
+      "Epoch 0:  52%|▌| 7759/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -71421,8 +71428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7741/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  52%|▌| 7741/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  52%|▌| 7760/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  52%|▌| 7760/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -71430,8 +71437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7742/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  52%|▌| 7742/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  52%|▌| 7761/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  52%|▌| 7761/14932 [10:50<10:01, 11.92it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -71439,8 +71446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7743/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  52%|▌| 7743/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  52%|▌| 7762/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  52%|▌| 7762/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -71448,8 +71455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7744/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  52%|▌| 7744/14932 [10:51<10:05, 11.88it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  52%|▌| 7763/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  52%|▌| 7763/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -71457,8 +71464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7745/14932 [10:51<10:04, 11.88it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  52%|▌| 7745/14932 [10:51<10:04, 11.88it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  52%|▌| 7764/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  52%|▌| 7764/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -71466,8 +71473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7746/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  52%|▌| 7746/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  52%|▌| 7765/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  52%|▌| 7765/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -71475,8 +71482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7747/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  52%|▌| 7747/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  52%|▌| 7766/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  52%|▌| 7766/14932 [10:51<10:01, 11.92it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -71484,8 +71491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7748/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  52%|▌| 7748/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  52%|▌| 7767/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  52%|▌| 7767/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -71493,8 +71500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7749/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  52%|▌| 7749/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  52%|▌| 7768/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  52%|▌| 7768/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -71502,8 +71509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7750/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  52%|▌| 7750/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  52%|▌| 7769/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  52%|▌| 7769/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -71511,8 +71518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7751/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  52%|▌| 7751/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  52%|▌| 7770/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  52%|▌| 7770/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -71520,8 +71527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7752/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  52%|▌| 7752/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  52%|▌| 7771/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  52%|▌| 7771/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -71529,8 +71536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7753/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  52%|▌| 7753/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  52%|▌| 7772/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  52%|▌| 7772/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -71538,8 +71545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7754/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  52%|▌| 7754/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  52%|▌| 7773/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  52%|▌| 7773/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -71547,8 +71554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7755/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  52%|▌| 7755/14932 [10:52<10:04, 11.88it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  52%|▌| 7774/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  52%|▌| 7774/14932 [10:51<10:00, 11.92it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -71556,8 +71563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7756/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  52%|▌| 7756/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  52%|▌| 7775/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  52%|▌| 7775/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -71565,8 +71572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7757/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  52%|▌| 7757/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  52%|▌| 7776/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  52%|▌| 7776/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -71574,8 +71581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7758/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  52%|▌| 7758/14932 [10:52<10:03, 11.88it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  52%|▌| 7777/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  52%|▌| 7777/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -71583,8 +71590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7759/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  52%|▌| 7759/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  52%|▌| 7778/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  52%|▌| 7778/14932 [10:52<10:00, 11.92it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -71592,8 +71599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7760/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  52%|▌| 7760/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  52%|▌| 7779/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  52%|▌| 7779/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -71601,8 +71608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7761/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  52%|▌| 7761/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  52%|▌| 7780/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  52%|▌| 7780/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -71610,8 +71617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7762/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  52%|▌| 7762/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  52%|▌| 7781/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  52%|▌| 7781/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -71619,8 +71626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7763/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  52%|▌| 7763/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  52%|▌| 7782/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  52%|▌| 7782/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -71628,8 +71635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7764/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  52%|▌| 7764/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  52%|▌| 7783/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  52%|▌| 7783/14932 [10:52<09:59, 11.92it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -71637,8 +71644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7765/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  52%|▌| 7765/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  52%|▌| 7784/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  52%|▌| 7784/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -71646,8 +71653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7766/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  52%|▌| 7766/14932 [10:53<10:03, 11.88it/s, v_num=o30c, train/loss=1.44"
+      "Epoch 0:  52%|▌| 7785/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  52%|▌| 7785/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -71655,8 +71662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7767/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=1.44\r",
-      "Epoch 0:  52%|▌| 7767/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:  52%|▌| 7786/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  52%|▌| 7786/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -71664,8 +71671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7768/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:  52%|▌| 7768/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  52%|▌| 7787/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  52%|▌| 7787/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -71673,8 +71680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7769/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  52%|▌| 7769/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  52%|▌| 7788/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  52%|▌| 7788/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -71682,8 +71689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7770/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  52%|▌| 7770/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  52%|▌| 7789/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  52%|▌| 7789/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -71691,8 +71698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7771/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  52%|▌| 7771/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  52%|▌| 7790/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  52%|▌| 7790/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -71700,8 +71707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7772/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  52%|▌| 7772/14932 [10:53<10:02, 11.88it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  52%|▌| 7791/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  52%|▌| 7791/14932 [10:53<09:59, 11.92it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -71709,8 +71716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7773/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  52%|▌| 7773/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  52%|▌| 7792/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  52%|▌| 7792/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -71718,8 +71725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7774/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  52%|▌| 7774/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  52%|▌| 7793/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  52%|▌| 7793/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -71727,8 +71734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7775/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  52%|▌| 7775/14932 [10:54<10:02, 11.89it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  52%|▌| 7794/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  52%|▌| 7794/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -71736,8 +71743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7776/14932 [10:54<10:02, 11.88it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  52%|▌| 7776/14932 [10:54<10:02, 11.88it/s, v_num=o30c, train/loss=0.75"
+      "Epoch 0:  52%|▌| 7795/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  52%|▌| 7795/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -71745,8 +71752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7777/14932 [10:54<10:02, 11.88it/s, v_num=o30c, train/loss=0.75\r",
-      "Epoch 0:  52%|▌| 7777/14932 [10:54<10:02, 11.88it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  52%|▌| 7796/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  52%|▌| 7796/14932 [10:53<09:58, 11.92it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -71754,8 +71761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7778/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  52%|▌| 7778/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  52%|▌| 7797/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  52%|▌| 7797/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -71763,8 +71770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7779/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  52%|▌| 7779/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  52%|▌| 7798/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  52%|▌| 7798/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -71772,8 +71779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7780/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  52%|▌| 7780/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  52%|▌| 7799/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  52%|▌| 7799/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -71781,8 +71788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7781/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  52%|▌| 7781/14932 [10:54<10:01, 11.88it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  52%|▌| 7800/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  52%|▌| 7800/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -71790,8 +71797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7782/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  52%|▌| 7782/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  52%|▌| 7801/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  52%|▌| 7801/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -71799,8 +71806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7783/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  52%|▌| 7783/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  52%|▌| 7802/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  52%|▌| 7802/14932 [10:54<09:58, 11.92it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -71808,8 +71815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7784/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  52%|▌| 7784/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  52%|▌| 7803/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  52%|▌| 7803/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -71817,8 +71824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7785/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  52%|▌| 7785/14932 [10:54<10:01, 11.89it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  52%|▌| 7804/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  52%|▌| 7804/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -71826,8 +71833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7786/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  52%|▌| 7786/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  52%|▌| 7805/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  52%|▌| 7805/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -71835,8 +71842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7787/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  52%|▌| 7787/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  52%|▌| 7806/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  52%|▌| 7806/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -71844,8 +71851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7788/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  52%|▌| 7788/14932 [10:55<10:01, 11.89it/s, v_num=o30c, train/loss=1.00"
+      "Epoch 0:  52%|▌| 7807/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  52%|▌| 7807/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -71853,8 +71860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7789/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=1.00\r",
-      "Epoch 0:  52%|▌| 7789/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  52%|▌| 7808/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  52%|▌| 7808/14932 [10:54<09:57, 11.92it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -71862,8 +71869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7790/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  52%|▌| 7790/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  52%|▌| 7809/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  52%|▌| 7809/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -71871,8 +71878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7791/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  52%|▌| 7791/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  52%|▌| 7810/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  52%|▌| 7810/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -71880,8 +71887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7792/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  52%|▌| 7792/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  52%|▌| 7811/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  52%|▌| 7811/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -71889,8 +71896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7793/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  52%|▌| 7793/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  52%|▌| 7812/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  52%|▌| 7812/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -71898,8 +71905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7794/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  52%|▌| 7794/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  52%|▌| 7813/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  52%|▌| 7813/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -71907,8 +71914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7795/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  52%|▌| 7795/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  52%|▌| 7814/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  52%|▌| 7814/14932 [10:55<09:57, 11.92it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -71916,8 +71923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7796/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  52%|▌| 7796/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=1.17"
+      "Epoch 0:  52%|▌| 7815/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  52%|▌| 7815/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -71925,8 +71932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7797/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=1.17\r",
-      "Epoch 0:  52%|▌| 7797/14932 [10:55<10:00, 11.89it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  52%|▌| 7816/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  52%|▌| 7816/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -71934,8 +71941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7798/14932 [10:56<10:00, 11.89it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  52%|▌| 7798/14932 [10:56<10:00, 11.89it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  52%|▌| 7817/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  52%|▌| 7817/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -71943,8 +71950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7799/14932 [10:56<10:00, 11.89it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  52%|▌| 7799/14932 [10:56<10:00, 11.89it/s, v_num=o30c, train/loss=0.93"
+      "Epoch 0:  52%|▌| 7818/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  52%|▌| 7818/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -71952,8 +71959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7800/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=0.93\r",
-      "Epoch 0:  52%|▌| 7800/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  52%|▌| 7819/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  52%|▌| 7819/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -71961,8 +71968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7801/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  52%|▌| 7801/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  52%|▌| 7820/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  52%|▌| 7820/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -71970,8 +71977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7802/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  52%|▌| 7802/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  52%|▌| 7821/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  52%|▌| 7821/14932 [10:55<09:56, 11.92it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -71979,8 +71986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7803/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  52%|▌| 7803/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  52%|▌| 7822/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  52%|▌| 7822/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -71988,8 +71995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7804/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  52%|▌| 7804/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  52%|▌| 7823/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  52%|▌| 7823/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -71997,8 +72004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7805/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  52%|▌| 7805/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  52%|▌| 7824/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  52%|▌| 7824/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -72006,8 +72013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7806/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  52%|▌| 7806/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  52%|▌| 7825/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  52%|▌| 7825/14932 [10:56<09:56, 11.92it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -72015,8 +72022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7807/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  52%|▌| 7807/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  52%|▌| 7826/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  52%|▌| 7826/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -72024,8 +72031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7808/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  52%|▌| 7808/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  52%|▌| 7827/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  52%|▌| 7827/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -72033,8 +72040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7809/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  52%|▌| 7809/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  52%|▌| 7828/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  52%|▌| 7828/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -72042,8 +72049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7810/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  52%|▌| 7810/14932 [10:56<09:59, 11.89it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  52%|▌| 7829/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  52%|▌| 7829/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -72051,8 +72058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7811/14932 [10:57<09:59, 11.89it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  52%|▌| 7811/14932 [10:57<09:59, 11.89it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  52%|▌| 7830/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  52%|▌| 7830/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -72060,8 +72067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7812/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  52%|▌| 7812/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  52%|▌| 7831/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  52%|▌| 7831/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -72069,8 +72076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7813/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  52%|▌| 7813/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  52%|▌| 7832/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  52%|▌| 7832/14932 [10:56<09:55, 11.92it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -72078,8 +72085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7814/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  52%|▌| 7814/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  52%|▌| 7833/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  52%|▌| 7833/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -72087,8 +72094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7815/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  52%|▌| 7815/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  52%|▌| 7834/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  52%|▌| 7834/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -72096,8 +72103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7816/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  52%|▌| 7816/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  52%|▌| 7835/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  52%|▌| 7835/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -72105,8 +72112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7817/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  52%|▌| 7817/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  52%|▌| 7836/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  52%|▌| 7836/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -72114,8 +72121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7818/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  52%|▌| 7818/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  52%|▌| 7837/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  52%|▌| 7837/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -72123,8 +72130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7819/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  52%|▌| 7819/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  52%|▌| 7838/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  52%|▌| 7838/14932 [10:57<09:55, 11.92it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -72132,8 +72139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7820/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  52%|▌| 7820/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  52%|▌| 7839/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  52%|▌| 7839/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -72141,8 +72148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7821/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  52%|▌| 7821/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  53%|▌| 7840/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  53%|▌| 7840/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -72150,8 +72157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7822/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  52%|▌| 7822/14932 [10:57<09:58, 11.89it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  53%|▌| 7841/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  53%|▌| 7841/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -72159,8 +72166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7823/14932 [10:57<09:57, 11.89it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  52%|▌| 7823/14932 [10:57<09:57, 11.89it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  53%|▌| 7842/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  53%|▌| 7842/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -72168,8 +72175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7824/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  52%|▌| 7824/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  53%|▌| 7843/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  53%|▌| 7843/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -72177,8 +72184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7825/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  52%|▌| 7825/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  53%|▌| 7844/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  53%|▌| 7844/14932 [10:57<09:54, 11.92it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -72186,8 +72193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7826/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  52%|▌| 7826/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  53%|▌| 7845/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  53%|▌| 7845/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -72195,8 +72202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7827/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  52%|▌| 7827/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  53%|▌| 7846/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  53%|▌| 7846/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -72204,8 +72211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7828/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  52%|▌| 7828/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  53%|▌| 7847/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  53%|▌| 7847/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -72213,8 +72220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7829/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  52%|▌| 7829/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  53%|▌| 7848/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  53%|▌| 7848/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -72222,8 +72229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7830/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  52%|▌| 7830/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=5.00"
+      "Epoch 0:  53%|▌| 7849/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  53%|▌| 7849/14932 [10:58<09:54, 11.92it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -72231,8 +72238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7831/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=5.00\r",
-      "Epoch 0:  52%|▌| 7831/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  53%|▌| 7850/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  53%|▌| 7850/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -72240,8 +72247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7832/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  52%|▌| 7832/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  53%|▌| 7851/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  53%|▌| 7851/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -72249,8 +72256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7833/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  52%|▌| 7833/14932 [10:58<09:57, 11.89it/s, v_num=o30c, train/loss=0.99"
+      "Epoch 0:  53%|▌| 7852/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  53%|▌| 7852/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -72258,8 +72265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7834/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=0.99\r",
-      "Epoch 0:  52%|▌| 7834/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  53%|▌| 7853/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  53%|▌| 7853/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -72267,8 +72274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7835/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  52%|▌| 7835/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  53%|▌| 7854/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  53%|▌| 7854/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -72276,8 +72283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7836/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  52%|▌| 7836/14932 [10:58<09:56, 11.89it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  53%|▌| 7855/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  53%|▌| 7855/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -72285,8 +72292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7837/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  52%|▌| 7837/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  53%|▌| 7856/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  53%|▌| 7856/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -72294,8 +72301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7838/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  52%|▌| 7838/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  53%|▌| 7857/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  53%|▌| 7857/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -72303,8 +72310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  52%|▌| 7839/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  52%|▌| 7839/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  53%|▌| 7858/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  53%|▌| 7858/14932 [10:58<09:53, 11.92it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -72312,8 +72319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7840/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  53%|▌| 7840/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  53%|▌| 7859/14932 [10:59<09:53, 11.92it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  53%|▌| 7859/14932 [10:59<09:53, 11.92it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -72321,8 +72328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7841/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  53%|▌| 7841/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  53%|▌| 7860/14932 [10:59<09:53, 11.92it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  53%|▌| 7860/14932 [10:59<09:53, 11.92it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -72330,8 +72337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7842/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  53%|▌| 7842/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  53%|▌| 7861/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  53%|▌| 7861/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -72339,8 +72346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7843/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  53%|▌| 7843/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  53%|▌| 7862/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  53%|▌| 7862/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.05"
      ]
     },
     {
@@ -72348,8 +72355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7844/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  53%|▌| 7844/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  53%|▌| 7863/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.05\r",
+      "Epoch 0:  53%|▌| 7863/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -72357,8 +72364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7845/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  53%|▌| 7845/14932 [10:59<09:56, 11.89it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  53%|▌| 7864/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  53%|▌| 7864/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -72366,8 +72373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7846/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  53%|▌| 7846/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  53%|▌| 7865/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  53%|▌| 7865/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -72375,8 +72382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7847/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  53%|▌| 7847/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  53%|▌| 7866/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  53%|▌| 7866/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -72384,8 +72391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7848/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  53%|▌| 7848/14932 [10:59<09:55, 11.89it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  53%|▌| 7867/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  53%|▌| 7867/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -72393,8 +72400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7849/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  53%|▌| 7849/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  53%|▌| 7868/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  53%|▌| 7868/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -72402,8 +72409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7850/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  53%|▌| 7850/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  53%|▌| 7869/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  53%|▌| 7869/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -72411,8 +72418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7851/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  53%|▌| 7851/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  53%|▌| 7870/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  53%|▌| 7870/14932 [10:59<09:52, 11.93it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -72420,8 +72427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7852/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  53%|▌| 7852/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  53%|▌| 7871/14932 [10:59<09:51, 11.93it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  53%|▌| 7871/14932 [10:59<09:51, 11.93it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -72429,8 +72436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7853/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  53%|▌| 7853/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  53%|▌| 7872/14932 [11:00<09:52, 11.93it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  53%|▌| 7872/14932 [11:00<09:52, 11.93it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -72438,8 +72445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7854/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  53%|▌| 7854/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  53%|▌| 7873/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  53%|▌| 7873/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -72447,8 +72454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7855/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  53%|▌| 7855/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  53%|▌| 7874/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  53%|▌| 7874/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -72456,8 +72463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7856/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  53%|▌| 7856/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  53%|▌| 7875/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  53%|▌| 7875/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -72465,8 +72472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7857/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  53%|▌| 7857/14932 [11:00<09:55, 11.89it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  53%|▌| 7876/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  53%|▌| 7876/14932 [11:00<09:51, 11.92it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -72474,8 +72481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7858/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  53%|▌| 7858/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  53%|▌| 7877/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  53%|▌| 7877/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -72483,8 +72490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7859/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  53%|▌| 7859/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  53%|▌| 7878/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  53%|▌| 7878/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=0.40"
      ]
     },
     {
@@ -72492,8 +72499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7860/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  53%|▌| 7860/14932 [11:00<09:54, 11.89it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  53%|▌| 7879/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=0.40\r",
+      "Epoch 0:  53%|▌| 7879/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -72501,8 +72508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7861/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  53%|▌| 7861/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  53%|▌| 7880/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  53%|▌| 7880/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -72510,8 +72517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7862/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  53%|▌| 7862/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  53%|▌| 7881/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  53%|▌| 7881/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -72519,8 +72526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7863/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  53%|▌| 7863/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  53%|▌| 7882/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  53%|▌| 7882/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -72528,8 +72535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7864/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  53%|▌| 7864/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  53%|▌| 7883/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  53%|▌| 7883/14932 [11:00<09:51, 11.93it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -72537,8 +72544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7865/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  53%|▌| 7865/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  53%|▌| 7884/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  53%|▌| 7884/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -72546,8 +72553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7866/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  53%|▌| 7866/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  53%|▌| 7885/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  53%|▌| 7885/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -72555,8 +72562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7867/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  53%|▌| 7867/14932 [11:01<09:54, 11.89it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  53%|▌| 7886/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  53%|▌| 7886/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -72564,8 +72571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7868/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  53%|▌| 7868/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  53%|▌| 7887/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  53%|▌| 7887/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -72573,8 +72580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7869/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  53%|▌| 7869/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  53%|▌| 7888/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  53%|▌| 7888/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -72582,8 +72589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7870/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  53%|▌| 7870/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  53%|▌| 7889/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  53%|▌| 7889/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -72591,8 +72598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7871/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  53%|▌| 7871/14932 [11:01<09:53, 11.89it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  53%|▌| 7890/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  53%|▌| 7890/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -72600,8 +72607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7872/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  53%|▌| 7872/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  53%|▌| 7891/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  53%|▌| 7891/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -72609,8 +72616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7873/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  53%|▌| 7873/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  53%|▌| 7892/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  53%|▌| 7892/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -72618,8 +72625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7874/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  53%|▌| 7874/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  53%|▌| 7893/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  53%|▌| 7893/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -72627,8 +72634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7875/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  53%|▌| 7875/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  53%|▌| 7894/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  53%|▌| 7894/14932 [11:01<09:50, 11.93it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -72636,8 +72643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7876/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  53%|▌| 7876/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  53%|▌| 7895/14932 [11:01<09:49, 11.93it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  53%|▌| 7895/14932 [11:01<09:49, 11.93it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -72645,8 +72652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7877/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  53%|▌| 7877/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  53%|▌| 7896/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  53%|▌| 7896/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -72654,8 +72661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7878/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  53%|▌| 7878/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  53%|▌| 7897/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  53%|▌| 7897/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -72663,8 +72670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7879/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  53%|▌| 7879/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  53%|▌| 7898/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  53%|▌| 7898/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -72672,8 +72679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7880/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  53%|▌| 7880/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  53%|▌| 7899/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  53%|▌| 7899/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -72681,8 +72688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7881/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  53%|▌| 7881/14932 [11:02<09:53, 11.89it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  53%|▌| 7900/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  53%|▌| 7900/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -72690,8 +72697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7882/14932 [11:02<09:52, 11.89it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  53%|▌| 7882/14932 [11:02<09:52, 11.89it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  53%|▌| 7901/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  53%|▌| 7901/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -72699,8 +72706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7883/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  53%|▌| 7883/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  53%|▌| 7902/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  53%|▌| 7902/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -72708,8 +72715,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7884/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  53%|▌| 7884/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  53%|▌| 7903/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -72717,8 +72723,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7885/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  53%|▌| 7885/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  53%|▌| 7903/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -72726,8 +72731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7886/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  53%|▌| 7886/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  53%|▌| 7904/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  53%|▌| 7904/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -72735,8 +72740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7887/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  53%|▌| 7887/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  53%|▌| 7905/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  53%|▌| 7905/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -72744,8 +72749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7888/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  53%|▌| 7888/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  53%|▌| 7906/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  53%|▌| 7906/14932 [11:02<09:49, 11.93it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -72753,8 +72758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7889/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  53%|▌| 7889/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  53%|▌| 7907/14932 [11:03<09:49, 11.93it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  53%|▌| 7907/14932 [11:03<09:49, 11.93it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -72762,8 +72767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7890/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  53%|▌| 7890/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  53%|▌| 7908/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  53%|▌| 7908/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -72771,8 +72776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7891/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  53%|▌| 7891/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  53%|▌| 7909/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  53%|▌| 7909/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -72780,8 +72785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7892/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  53%|▌| 7892/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  53%|▌| 7910/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  53%|▌| 7910/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -72789,8 +72794,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7893/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  53%|▌| 7893/14932 [11:03<09:52, 11.89it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  53%|▌| 7911/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -72798,8 +72802,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7894/14932 [11:03<09:51, 11.89it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  53%|▌| 7894/14932 [11:03<09:51, 11.89it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  53%|▌| 7911/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -72807,8 +72810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7895/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  53%|▌| 7895/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  53%|▌| 7912/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  53%|▌| 7912/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -72816,8 +72819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7896/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  53%|▌| 7896/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  53%|▌| 7913/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  53%|▌| 7913/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -72825,8 +72828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7897/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  53%|▌| 7897/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  53%|▌| 7914/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  53%|▌| 7914/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -72834,8 +72837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7898/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  53%|▌| 7898/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  53%|▌| 7915/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  53%|▌| 7915/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -72843,8 +72846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7899/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  53%|▌| 7899/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  53%|▌| 7916/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  53%|▌| 7916/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -72852,8 +72855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7900/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  53%|▌| 7900/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  53%|▌| 7917/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  53%|▌| 7917/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -72861,8 +72864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7901/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  53%|▌| 7901/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  53%|▌| 7918/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  53%|▌| 7918/14932 [11:03<09:48, 11.93it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -72870,8 +72873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7902/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  53%|▌| 7902/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  53%|▌| 7919/14932 [11:03<09:47, 11.93it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  53%|▌| 7919/14932 [11:03<09:47, 11.93it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -72879,8 +72882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7903/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  53%|▌| 7903/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  53%|▌| 7920/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  53%|▌| 7920/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -72888,8 +72891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7904/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  53%|▌| 7904/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  53%|▌| 7921/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  53%|▌| 7921/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -72897,8 +72900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7905/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  53%|▌| 7905/14932 [11:04<09:51, 11.89it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  53%|▌| 7922/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  53%|▌| 7922/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -72906,8 +72909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7906/14932 [11:05<09:51, 11.89it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  53%|▌| 7906/14932 [11:05<09:51, 11.89it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  53%|▌| 7923/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  53%|▌| 7923/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -72915,8 +72918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7907/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  53%|▌| 7907/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  53%|▌| 7924/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  53%|▌| 7924/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -72924,8 +72927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7908/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  53%|▌| 7908/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  53%|▌| 7925/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  53%|▌| 7925/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -72933,8 +72936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7909/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  53%|▌| 7909/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  53%|▌| 7926/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  53%|▌| 7926/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -72942,8 +72945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7910/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  53%|▌| 7910/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  53%|▌| 7927/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  53%|▌| 7927/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -72951,8 +72954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7911/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  53%|▌| 7911/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  53%|▌| 7928/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  53%|▌| 7928/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -72960,8 +72963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7912/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  53%|▌| 7912/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  53%|▌| 7929/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  53%|▌| 7929/14932 [11:04<09:47, 11.93it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -72969,8 +72972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7913/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  53%|▌| 7913/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  53%|▌| 7930/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  53%|▌| 7930/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -72978,8 +72981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7914/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  53%|▌| 7914/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  53%|▌| 7931/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  53%|▌| 7931/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -72987,8 +72990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7915/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  53%|▌| 7915/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  53%|▌| 7932/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  53%|▌| 7932/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -72996,8 +72999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7916/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  53%|▌| 7916/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  53%|▌| 7933/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  53%|▌| 7933/14932 [11:04<09:46, 11.93it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -73005,8 +73008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7917/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  53%|▌| 7917/14932 [11:05<09:50, 11.89it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  53%|▌| 7934/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  53%|▌| 7934/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -73014,8 +73017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7918/14932 [11:05<09:49, 11.89it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  53%|▌| 7918/14932 [11:05<09:49, 11.89it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  53%|▌| 7935/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  53%|▌| 7935/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -73023,8 +73026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7919/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  53%|▌| 7919/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  53%|▌| 7936/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  53%|▌| 7936/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -73032,8 +73035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7920/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  53%|▌| 7920/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  53%|���| 7937/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  53%|▌| 7937/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -73041,8 +73044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7921/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  53%|▌| 7921/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  53%|▌| 7938/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  53%|▌| 7938/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -73050,8 +73053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7922/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  53%|▌| 7922/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  53%|▌| 7939/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  53%|▌| 7939/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -73059,8 +73062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7923/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  53%|▌| 7923/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  53%|▌| 7940/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  53%|▌| 7940/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -73068,8 +73071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7924/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  53%|▌| 7924/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  53%|▌| 7941/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  53%|▌| 7941/14932 [11:05<09:46, 11.93it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -73077,8 +73080,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7925/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  53%|▌| 7925/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  53%|▌| 7942/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -73086,8 +73088,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7926/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  53%|▌| 7926/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  53%|▌| 7942/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -73095,8 +73096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7927/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  53%|▌| 7927/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  53%|▌| 7943/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  53%|▌| 7943/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -73104,8 +73105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7928/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  53%|▌| 7928/14932 [11:06<09:49, 11.89it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  53%|▌| 7944/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  53%|▌| 7944/14932 [11:05<09:45, 11.93it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -73113,8 +73114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7929/14932 [11:06<09:48, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  53%|▌| 7929/14932 [11:06<09:48, 11.89it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  53%|▌| 7945/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  53%|▌| 7945/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -73122,8 +73123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7930/14932 [11:06<09:48, 11.89it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  53%|▌| 7930/14932 [11:06<09:48, 11.89it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  53%|▌| 7946/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  53%|▌| 7946/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -73131,8 +73132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7931/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  53%|▌| 7931/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  53%|▌| 7947/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  53%|▌| 7947/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -73140,8 +73141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7932/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  53%|▌| 7932/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=1.87"
+      "Epoch 0:  53%|▌| 7948/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  53%|▌| 7948/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -73149,8 +73150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7933/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=1.87\r",
-      "Epoch 0:  53%|▌| 7933/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  53%|▌| 7949/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  53%|▌| 7949/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -73158,8 +73159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7934/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  53%|▌| 7934/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  53%|▌| 7950/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  53%|▌| 7950/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -73167,8 +73168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7935/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  53%|▌| 7935/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  53%|▌| 7951/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  53%|▌| 7951/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -73176,8 +73177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7936/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  53%|▌| 7936/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  53%|▌| 7952/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  53%|▌| 7952/14932 [11:06<09:45, 11.93it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -73185,8 +73186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7937/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  53%|▌| 7937/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  53%|▌| 7953/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  53%|▌| 7953/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -73194,8 +73195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7938/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  53%|▌| 7938/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  53%|▌| 7954/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  53%|▌| 7954/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -73203,8 +73204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7939/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  53%|▌| 7939/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  53%|▌| 7955/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  53%|▌| 7955/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -73212,8 +73213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7940/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  53%|▌| 7940/14932 [11:07<09:48, 11.89it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  53%|▌| 7956/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  53%|▌| 7956/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -73221,8 +73222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7941/14932 [11:07<09:47, 11.89it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  53%|▌| 7941/14932 [11:07<09:47, 11.89it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  53%|▌| 7957/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  53%|▌| 7957/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -73230,8 +73231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7942/14932 [11:07<09:47, 11.89it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  53%|▌| 7942/14932 [11:07<09:47, 11.89it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  53%|▌| 7958/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  53%|▌| 7958/14932 [11:06<09:44, 11.93it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -73239,8 +73240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7943/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  53%|▌| 7943/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  53%|▌| 7959/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  53%|▌| 7959/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -73248,8 +73249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7944/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  53%|▌| 7944/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  53%|▌| 7960/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  53%|▌| 7960/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -73257,8 +73258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7945/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  53%|▌| 7945/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  53%|▌| 7961/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  53%|▌| 7961/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -73266,8 +73267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7946/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  53%|▌| 7946/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  53%|▌| 7962/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  53%|▌| 7962/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -73275,8 +73276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7947/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  53%|▌| 7947/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  53%|▌| 7963/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  53%|▌| 7963/14932 [11:07<09:44, 11.93it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -73284,8 +73285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7948/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  53%|▌| 7948/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  53%|▌| 7964/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  53%|▌| 7964/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -73293,8 +73294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7949/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  53%|▌| 7949/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  53%|▌| 7965/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  53%|▌| 7965/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -73302,8 +73303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7950/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  53%|▌| 7950/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  53%|▌| 7966/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  53%|▌| 7966/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -73311,8 +73312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7951/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  53%|▌| 7951/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  53%|▌| 7967/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  53%|▌| 7967/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -73320,8 +73321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7952/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  53%|▌| 7952/14932 [11:08<09:47, 11.89it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  53%|▌| 7968/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  53%|▌| 7968/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -73329,8 +73330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7953/14932 [11:08<09:46, 11.89it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  53%|▌| 7953/14932 [11:08<09:46, 11.89it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  53%|▌| 7969/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  53%|▌| 7969/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -73338,8 +73339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7954/14932 [11:08<09:46, 11.89it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  53%|▌| 7954/14932 [11:08<09:46, 11.89it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  53%|▌| 7970/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  53%|▌| 7970/14932 [11:07<09:43, 11.93it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -73347,8 +73348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7955/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  53%|▌| 7955/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  53%|▌| 7971/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  53%|▌| 7971/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -73356,8 +73357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7956/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  53%|▌| 7956/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  53%|▌| 7972/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  53%|▌| 7972/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -73365,8 +73366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7957/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  53%|▌| 7957/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  53%|▌| 7973/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  53%|▌| 7973/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -73374,8 +73375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7958/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  53%|▌| 7958/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  53%|▌| 7974/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  53%|▌| 7974/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -73383,8 +73384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7959/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  53%|▌| 7959/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  53%|▌| 7975/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  53%|▌| 7975/14932 [11:08<09:43, 11.93it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -73392,8 +73393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7960/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  53%|▌| 7960/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  53%|▌| 7976/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  53%|▌| 7976/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -73401,8 +73402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7961/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  53%|▌| 7961/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  53%|▌| 7977/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  53%|▌| 7977/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -73410,8 +73411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7962/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  53%|▌| 7962/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  53%|▌| 7978/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  53%|▌| 7978/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -73419,8 +73420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7963/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  53%|▌| 7963/14932 [11:09<09:46, 11.89it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  53%|▌| 7979/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  53%|▌| 7979/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -73428,8 +73429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7964/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  53%|▌| 7964/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  53%|▌| 7980/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  53%|▌| 7980/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -73437,8 +73438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7965/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  53%|▌| 7965/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  53%|▌| 7981/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  53%|▌| 7981/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -73446,7 +73447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7966/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  53%|▌| 7982/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  53%|▌| 7982/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -73454,7 +73456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7966/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  53%|▌| 7983/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  53%|▌| 7983/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -73462,8 +73465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7967/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  53%|▌| 7967/14932 [11:09<09:45, 11.89it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  53%|▌| 7984/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  53%|▌| 7984/14932 [11:08<09:42, 11.93it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -73471,8 +73474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7968/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  53%|▌| 7968/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  53%|▌| 7985/14932 [11:09<09:42, 11.93it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  53%|▌| 7985/14932 [11:09<09:42, 11.93it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -73480,8 +73483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7969/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  53%|▌| 7969/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  53%|▌| 7986/14932 [11:09<09:41, 11.93it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  53%|▌| 7986/14932 [11:09<09:41, 11.93it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -73489,8 +73492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7970/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  53%|▌| 7970/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  53%|▌| 7987/14932 [11:09<09:41, 11.93it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  53%|▌| 7987/14932 [11:09<09:41, 11.93it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -73498,8 +73501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7971/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  53%|▌| 7971/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  53%|▌| 7988/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  53%|▌| 7988/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -73507,8 +73510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7972/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  53%|▌| 7972/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  54%|▌| 7989/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  54%|▌| 7989/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -73516,8 +73519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7973/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  53%|▌| 7973/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  54%|▌| 7990/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  54%|▌| 7990/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=0.93"
      ]
     },
     {
@@ -73525,8 +73528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7974/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  53%|▌| 7974/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=4.78"
+      "Epoch 0:  54%|▌| 7991/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=0.93\r",
+      "Epoch 0:  54%|▌| 7991/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -73534,8 +73537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7975/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=4.78\r",
-      "Epoch 0:  53%|▌| 7975/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  54%|▌| 7992/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  54%|▌| 7992/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -73543,8 +73546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7976/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  53%|▌| 7976/14932 [11:10<09:45, 11.89it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  54%|▌| 7993/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  54%|▌| 7993/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -73552,8 +73555,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7977/14932 [11:10<09:44, 11.89it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  53%|▌| 7977/14932 [11:10<09:44, 11.89it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  54%|▌| 7994/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -73561,8 +73563,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7978/14932 [11:10<09:44, 11.89it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  53%|▌| 7978/14932 [11:10<09:44, 11.89it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  54%|▌| 7994/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -73570,8 +73571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7979/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  53%|▌| 7979/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  54%|▌| 7995/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  54%|▌| 7995/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -73579,8 +73580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7980/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  53%|▌| 7980/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  54%|▌| 7996/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  54%|▌| 7996/14932 [11:09<09:41, 11.94it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -73588,8 +73589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7981/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  53%|▌| 7981/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  54%|▌| 7997/14932 [11:09<09:40, 11.94it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  54%|▌| 7997/14932 [11:09<09:40, 11.94it/s, v_num=ui8w, train/loss=0.94"
      ]
     },
     {
@@ -73597,8 +73598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7982/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  53%|▌| 7982/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  54%|▌| 7998/14932 [11:09<09:40, 11.94it/s, v_num=ui8w, train/loss=0.94\r",
+      "Epoch 0:  54%|▌| 7998/14932 [11:09<09:40, 11.94it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -73606,8 +73607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7983/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  53%|▌| 7983/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  54%|▌| 7999/14932 [11:10<09:40, 11.94it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  54%|▌| 7999/14932 [11:10<09:40, 11.94it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -73615,152 +73616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  53%|▌| 7984/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  53%|▌| 7984/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.73"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  53%|▌| 7985/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  53%|▌| 7985/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=2.52"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  53%|▌| 7986/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  53%|▌| 7986/14932 [11:11<09:44, 11.89it/s, v_num=o30c, train/loss=2.91"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  53%|▌| 7987/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  53%|▌| 7987/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.58"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  53%|▌| 7988/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  53%|▌| 7988/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.17"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7989/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  54%|▌| 7989/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.00"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7990/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  54%|▌| 7990/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=2.97"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7991/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  54%|▌| 7991/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.47"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7992/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  54%|▌| 7992/14932 [11:11<09:43, 11.89it/s, v_num=o30c, train/loss=3.72"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7993/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  54%|▌| 7993/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=3.81"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7994/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  54%|▌| 7994/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.78"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7995/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  54%|▌| 7995/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.30"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7996/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  54%|▌| 7996/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.95"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7997/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  54%|▌| 7997/14932 [11:12<09:43, 11.89it/s, v_num=o30c, train/loss=3.31"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7998/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  54%|▌| 7998/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=3.16"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 7999/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  54%|▌| 7999/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=4.44"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Epoch 0:  54%|▌| 8000/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  54%|▌| 8000/14932 [11:12<09:42, 11.89it/s, v_num=o30c, train/loss=4.03/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.\r\n",
+      "Epoch 0:  54%|▌| 8000/14932 [11:10<09:40, 11.94it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  54%|▌| 8000/14932 [11:10<09:40, 11.94it/s, v_num=ui8w, train/loss=2.62/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.\r\n",
       "  warnings.warn(\r\n"
      ]
     },
@@ -73769,8 +73626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8001/14932 [11:36<10:03, 11.49it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  54%|▌| 8001/14932 [11:36<10:03, 11.49it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  54%|▌| 8001/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  54%|▌| 8001/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=1.45"
      ]
     },
     {
@@ -73778,8 +73635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8002/14932 [11:36<10:03, 11.49it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  54%|▌| 8002/14932 [11:36<10:03, 11.49it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  54%|▌| 8002/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=1.45\r",
+      "Epoch 0:  54%|▌| 8002/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -73787,8 +73644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8003/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  54%|▌| 8003/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  54%|▌| 8003/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  54%|▌| 8003/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -73796,8 +73653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8004/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  54%|▌| 8004/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  54%|▌| 8004/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  54%|▌| 8004/14932 [11:33<10:00, 11.53it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -73805,8 +73662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8005/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  54%|▌| 8005/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  54%|▌| 8005/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  54%|▌| 8005/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -73814,8 +73671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8006/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  54%|▌| 8006/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  54%|▌| 8006/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  54%|▌| 8006/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -73823,8 +73680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8007/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  54%|▌| 8007/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.74"
+      "Epoch 0:  54%|▌| 8007/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  54%|▌| 8007/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -73832,8 +73689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8008/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.74\r",
-      "Epoch 0:  54%|▌| 8008/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  54%|▌| 8008/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  54%|▌| 8008/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -73841,8 +73698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8009/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  54%|▌| 8009/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  54%|▌| 8009/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  54%|▌| 8009/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -73850,8 +73707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8010/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  54%|▌| 8010/14932 [11:36<10:02, 11.49it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  54%|▌| 8010/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  54%|▌| 8010/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -73859,8 +73716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8011/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  54%|▌| 8011/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  54%|▌| 8011/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  54%|▌| 8011/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -73868,8 +73725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8012/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  54%|▌| 8012/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  54%|▌| 8012/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  54%|▌| 8012/14932 [11:34<10:00, 11.53it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -73877,8 +73734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8013/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  54%|▌| 8013/14932 [11:37<10:02, 11.49it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  54%|▌| 8013/14932 [11:34<09:59, 11.53it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  54%|▌| 8013/14932 [11:34<09:59, 11.53it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -73886,8 +73743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8014/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  54%|▌| 8014/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  54%|▌| 8014/14932 [11:34<09:59, 11.53it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  54%|▌| 8014/14932 [11:34<09:59, 11.53it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -73895,8 +73752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8015/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  54%|▌| 8015/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  54%|▌| 8015/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  54%|▌| 8015/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -73904,8 +73761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8016/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  54%|▌| 8016/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  54%|▌| 8016/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  54%|▌| 8016/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -73913,8 +73770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8017/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  54%|▌| 8017/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=0.80"
+      "Epoch 0:  54%|▌| 8017/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  54%|▌| 8017/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -73922,8 +73779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8018/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=0.80\r",
-      "Epoch 0:  54%|▌| 8018/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  54%|▌| 8018/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  54%|▌| 8018/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -73931,8 +73788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8019/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  54%|▌| 8019/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  54%|▌| 8019/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  54%|▌| 8019/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -73940,8 +73797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8020/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  54%|▌| 8020/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  54%|▌| 8020/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:  54%|▌| 8020/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -73949,8 +73806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8021/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  54%|▌| 8021/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.33"
+      "Epoch 0:  54%|▌| 8021/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  54%|▌| 8021/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -73958,8 +73815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8022/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=1.33\r",
-      "Epoch 0:  54%|▌| 8022/14932 [11:37<10:01, 11.49it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  54%|▌| 8022/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  54%|▌| 8022/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -73967,8 +73824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8023/14932 [11:38<10:01, 11.49it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  54%|▌| 8023/14932 [11:38<10:01, 11.49it/s, v_num=o30c, train/loss=1.42"
+      "Epoch 0:  54%|▌| 8023/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  54%|▌| 8023/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -73976,8 +73833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8024/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=1.42\r",
-      "Epoch 0:  54%|▌| 8024/14932 [11:38<10:01, 11.49it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  54%|▌| 8024/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  54%|▌| 8024/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -73985,8 +73842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8025/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  54%|▌| 8025/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  54%|▌| 8025/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  54%|▌| 8025/14932 [11:35<09:59, 11.53it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -73994,8 +73851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8026/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  54%|▌| 8026/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  54%|▌| 8026/14932 [11:36<09:59, 11.53it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  54%|▌| 8026/14932 [11:36<09:59, 11.53it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -74003,8 +73860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8027/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  54%|▌| 8027/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  54%|▌| 8027/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  54%|▌| 8027/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -74012,8 +73869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8028/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  54%|▌| 8028/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  54%|▌| 8028/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  54%|▌| 8028/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -74021,8 +73878,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8029/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  54%|▌| 8029/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  54%|▌| 8029/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -74030,8 +73886,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8030/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  54%|▌| 8030/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  54%|▌| 8029/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -74039,8 +73894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8031/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  54%|▌| 8031/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  54%|▌| 8030/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  54%|▌| 8030/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -74048,8 +73903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8032/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  54%|▌| 8032/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  54%|▌| 8031/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  54%|▌| 8031/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -74057,8 +73912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8033/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  54%|▌| 8033/14932 [11:38<10:00, 11.49it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  54%|▌| 8032/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  54%|▌| 8032/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -74066,8 +73921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8034/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  54%|▌| 8034/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  54%|▌| 8033/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  54%|▌| 8033/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -74075,8 +73930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8035/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  54%|▌| 8035/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  54%|▌| 8034/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  54%|▌| 8034/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -74084,8 +73939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8036/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  54%|▌| 8036/14932 [11:39<10:00, 11.49it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  54%|▌| 8035/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  54%|▌| 8035/14932 [11:36<09:58, 11.53it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -74093,8 +73948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8037/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  54%|▌| 8037/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  54%|▌| 8036/14932 [11:37<09:58, 11.53it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  54%|▌| 8036/14932 [11:37<09:58, 11.53it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -74102,8 +73957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8038/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  54%|▌| 8038/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  54%|▌| 8037/14932 [11:37<09:58, 11.53it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  54%|▌| 8037/14932 [11:37<09:58, 11.53it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -74111,8 +73966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8039/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  54%|▌| 8039/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  54%|▌| 8038/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  54%|▌| 8038/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -74120,8 +73975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8040/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  54%|▌| 8040/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  54%|▌| 8039/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  54%|▌| 8039/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -74129,8 +73984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8041/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  54%|▌| 8041/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  54%|▌| 8040/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  54%|▌| 8040/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=1.01"
      ]
     },
     {
@@ -74138,8 +73993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8042/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  54%|▌| 8042/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  54%|▌| 8041/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=1.01\r",
+      "Epoch 0:  54%|▌| 8041/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -74147,8 +74002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8043/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  54%|▌| 8043/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  54%|▌| 8042/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  54%|▌| 8042/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -74156,8 +74011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8044/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  54%|▌| 8044/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  54%|▌| 8043/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  54%|▌| 8043/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -74165,8 +74020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8045/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  54%|▌| 8045/14932 [11:39<09:59, 11.49it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  54%|▌| 8044/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  54%|▌| 8044/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -74174,8 +74029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8046/14932 [11:40<09:59, 11.49it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  54%|▌| 8046/14932 [11:40<09:59, 11.49it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  54%|▌| 8045/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  54%|▌| 8045/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -74183,8 +74038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8047/14932 [11:40<09:59, 11.49it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  54%|▌| 8047/14932 [11:40<09:59, 11.49it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  54%|▌| 8046/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  54%|▌| 8046/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -74192,8 +74047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8048/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  54%|▌| 8048/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  54%|▌| 8047/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  54%|▌| 8047/14932 [11:37<09:57, 11.53it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -74201,8 +74056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8049/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  54%|▌| 8049/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  54%|▌| 8048/14932 [11:37<09:56, 11.53it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  54%|▌| 8048/14932 [11:37<09:56, 11.53it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -74210,8 +74065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8050/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  54%|▌| 8050/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  54%|▌| 8049/14932 [11:37<09:56, 11.53it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  54%|▌| 8049/14932 [11:37<09:56, 11.53it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -74219,8 +74074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8051/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  54%|▌| 8051/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  54%|▌| 8050/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  54%|▌| 8050/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -74228,8 +74083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8052/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  54%|▌| 8052/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  54%|▌| 8051/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  54%|▌| 8051/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -74237,8 +74092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8053/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  54%|▌| 8053/14932 [11:40<09:58, 11.49it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  54%|▌| 8052/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  54%|▌| 8052/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -74246,8 +74101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8054/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  54%|▌| 8054/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  54%|▌| 8053/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  54%|▌| 8053/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -74255,8 +74110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8055/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  54%|▌| 8055/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  54%|▌| 8054/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  54%|▌| 8054/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -74264,8 +74119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8056/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  54%|▌| 8056/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  54%|▌| 8055/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  54%|▌| 8055/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -74273,8 +74128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8057/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  54%|▌| 8057/14932 [11:40<09:58, 11.50it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  54%|▌| 8056/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  54%|▌| 8056/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -74282,8 +74137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8058/14932 [11:40<09:57, 11.50it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  54%|▌| 8058/14932 [11:40<09:57, 11.50it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  54%|▌| 8057/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  54%|▌| 8057/14932 [11:38<09:56, 11.53it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -74291,8 +74146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8059/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  54%|▌| 8059/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  54%|▌| 8058/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  54%|▌| 8058/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -74300,7 +74155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8060/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  54%|▌| 8059/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  54%|▌| 8059/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -74308,7 +74164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8060/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  54%|▌| 8060/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  54%|▌| 8060/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -74316,8 +74173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8061/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  54%|▌| 8061/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  54%|▌| 8061/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  54%|▌| 8061/14932 [11:38<09:55, 11.53it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -74325,8 +74182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8062/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  54%|▌| 8062/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  54%|▌| 8062/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  54%|▌| 8062/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -74334,8 +74191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8063/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  54%|▌| 8063/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  54%|▌| 8063/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  54%|▌| 8063/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -74343,8 +74200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8064/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=0.89\r",
-      "Epoch 0:  54%|▌| 8064/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=1.08"
+      "Epoch 0:  54%|▌| 8064/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  54%|▌| 8064/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=1.00"
      ]
     },
     {
@@ -74352,8 +74209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8065/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=1.08\r",
-      "Epoch 0:  54%|▌| 8065/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  54%|▌| 8065/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=1.00\r",
+      "Epoch 0:  54%|▌| 8065/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -74361,8 +74218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8066/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  54%|▌| 8066/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  54%|▌| 8066/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  54%|▌| 8066/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -74370,8 +74227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8067/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  54%|▌| 8067/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  54%|▌| 8067/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  54%|▌| 8067/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -74379,8 +74236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8068/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  54%|▌| 8068/14932 [11:41<09:57, 11.50it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  54%|▌| 8068/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  54%|▌| 8068/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -74388,8 +74245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8069/14932 [11:41<09:56, 11.50it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  54%|▌| 8069/14932 [11:41<09:56, 11.50it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  54%|▌| 8069/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  54%|▌| 8069/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -74397,8 +74254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8070/14932 [11:41<09:56, 11.50it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  54%|▌| 8070/14932 [11:41<09:56, 11.50it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  54%|▌| 8070/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  54%|▌| 8070/14932 [11:39<09:55, 11.53it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -74406,8 +74263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8071/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  54%|▌| 8071/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  54%|▌| 8071/14932 [11:39<09:54, 11.53it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  54%|▌| 8071/14932 [11:39<09:54, 11.53it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -74415,8 +74272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8072/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  54%|▌| 8072/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  54%|▌| 8072/14932 [11:39<09:54, 11.53it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  54%|▌| 8072/14932 [11:39<09:54, 11.53it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -74424,8 +74281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8073/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  54%|▌| 8073/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  54%|▌| 8073/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  54%|▌| 8073/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -74433,8 +74290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8074/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  54%|▌| 8074/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  54%|▌| 8074/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  54%|▌| 8074/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -74442,8 +74299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8075/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  54%|▌| 8075/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  54%|▌| 8075/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  54%|▌| 8075/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -74451,8 +74308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8076/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  54%|▌| 8076/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  54%|▌| 8076/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  54%|▌| 8076/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -74460,8 +74317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8077/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  54%|▌| 8077/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  54%|▌| 8077/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  54%|▌| 8077/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -74469,8 +74326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8078/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  54%|▌| 8078/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  54%|▌| 8078/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  54%|▌| 8078/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -74478,8 +74335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8079/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  54%|▌| 8079/14932 [11:42<09:56, 11.50it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  54%|▌| 8079/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  54%|▌| 8079/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -74487,8 +74344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8080/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  54%|▌| 8080/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  54%|▌| 8080/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  54%|▌| 8080/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=1.19"
      ]
     },
     {
@@ -74496,8 +74353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8081/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  54%|▌| 8081/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  54%|▌| 8081/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=1.19\r",
+      "Epoch 0:  54%|▌| 8081/14932 [11:40<09:54, 11.53it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -74505,8 +74362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8082/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  54%|▌| 8082/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  54%|▌| 8082/14932 [11:40<09:53, 11.53it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  54%|▌| 8082/14932 [11:40<09:53, 11.53it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -74514,8 +74371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8083/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  54%|▌| 8083/14932 [11:42<09:55, 11.50it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  54%|▌| 8083/14932 [11:41<09:54, 11.53it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  54%|▌| 8083/14932 [11:41<09:54, 11.53it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -74523,8 +74380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8084/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  54%|▌| 8084/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  54%|▌| 8084/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  54%|▌| 8084/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -74532,8 +74389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8085/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  54%|▌| 8085/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  54%|▌| 8085/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  54%|▌| 8085/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -74541,8 +74398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8086/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  54%|▌| 8086/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  54%|▌| 8086/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  54%|▌| 8086/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.22"
      ]
     },
     {
@@ -74550,8 +74407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8087/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  54%|▌| 8087/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  54%|▌| 8087/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.22\r",
+      "Epoch 0:  54%|▌| 8087/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -74559,8 +74416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8088/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  54%|▌| 8088/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  54%|▌| 8088/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  54%|▌| 8088/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -74568,8 +74425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8089/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  54%|▌| 8089/14932 [11:43<09:55, 11.50it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  54%|▌| 8089/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  54%|▌| 8089/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -74577,8 +74434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8090/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  54%|▌| 8090/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  54%|▌| 8090/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  54%|▌| 8090/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -74586,8 +74443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8091/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  54%|▌| 8091/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  54%|▌| 8091/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  54%|▌| 8091/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -74595,8 +74452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8092/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  54%|▌| 8092/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  54%|▌| 8092/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  54%|▌| 8092/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -74604,8 +74461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8093/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  54%|▌| 8093/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  54%|▌| 8093/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  54%|▌| 8093/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -74613,8 +74470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8094/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  54%|▌| 8094/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  54%|▌| 8094/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  54%|▌| 8094/14932 [11:41<09:53, 11.53it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -74622,8 +74479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8095/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  54%|▌| 8095/14932 [11:43<09:54, 11.50it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  54%|▌| 8095/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  54%|▌| 8095/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -74631,8 +74488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8096/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  54%|▌| 8096/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  54%|▌| 8096/14932 [11:42<09:53, 11.53it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  54%|▌| 8096/14932 [11:42<09:53, 11.53it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -74640,8 +74497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8097/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  54%|▌| 8097/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=5.28"
+      "Epoch 0:  54%|▌| 8097/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  54%|▌| 8097/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -74649,8 +74506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8098/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=5.28\r",
-      "Epoch 0:  54%|▌| 8098/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  54%|▌| 8098/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  54%|▌| 8098/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -74658,8 +74515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8099/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  54%|▌| 8099/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  54%|▌| 8099/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  54%|▌| 8099/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -74667,8 +74524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8100/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  54%|▌| 8100/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  54%|▌| 8100/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  54%|▌| 8100/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -74676,8 +74533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8101/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  54%|▌| 8101/14932 [11:44<09:54, 11.50it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  54%|▌| 8101/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  54%|▌| 8101/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -74685,8 +74542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8102/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  54%|▌| 8102/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  54%|▌| 8102/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  54%|▌| 8102/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -74694,8 +74551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8103/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  54%|▌| 8103/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  54%|▌| 8103/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  54%|▌| 8103/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -74703,8 +74560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8104/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  54%|▌| 8104/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  54%|▌| 8104/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  54%|▌| 8104/14932 [11:42<09:52, 11.53it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -74712,8 +74569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8105/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  54%|▌| 8105/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  54%|▌| 8105/14932 [11:43<09:52, 11.53it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  54%|▌| 8105/14932 [11:43<09:52, 11.53it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -74721,8 +74578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8106/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  54%|▌| 8106/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  54%|▌| 8106/14932 [11:43<09:52, 11.53it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  54%|▌| 8106/14932 [11:43<09:52, 11.53it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -74730,8 +74587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8107/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  54%|▌| 8107/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  54%|▌| 8107/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  54%|▌| 8107/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -74739,8 +74596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8108/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  54%|▌| 8108/14932 [11:44<09:53, 11.50it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  54%|▌| 8108/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  54%|▌| 8108/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -74748,8 +74605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8109/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  54%|▌| 8109/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  54%|▌| 8109/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  54%|▌| 8109/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -74757,8 +74614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8110/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  54%|▌| 8110/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  54%|▌| 8110/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  54%|▌| 8110/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -74766,8 +74623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8111/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  54%|▌| 8111/14932 [11:45<09:53, 11.50it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  54%|▌| 8111/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  54%|▌| 8111/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -74775,7 +74632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8112/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  54%|▌| 8112/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  54%|▌| 8112/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -74783,7 +74641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8112/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  54%|▌| 8113/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  54%|▌| 8113/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -74791,8 +74650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8113/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  54%|▌| 8113/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=1.51"
+      "Epoch 0:  54%|▌| 8114/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  54%|▌| 8114/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -74800,8 +74659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8114/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=1.51\r",
-      "Epoch 0:  54%|▌| 8114/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  54%|▌| 8115/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  54%|▌| 8115/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -74809,8 +74668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8115/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  54%|▌| 8115/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  54%|▌| 8116/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  54%|▌| 8116/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -74818,8 +74677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8116/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  54%|▌| 8116/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  54%|▌| 8117/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  54%|▌| 8117/14932 [11:43<09:51, 11.53it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -74827,8 +74686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8117/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  54%|▌| 8117/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  54%|▌| 8118/14932 [11:43<09:50, 11.53it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  54%|▌| 8118/14932 [11:43<09:50, 11.53it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -74836,8 +74695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8118/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  54%|▌| 8118/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  54%|▌| 8119/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  54%|▌| 8119/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -74845,8 +74704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8119/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  54%|▌| 8119/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  54%|▌| 8120/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  54%|▌| 8120/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -74854,8 +74713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8120/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  54%|▌| 8120/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  54%|▌| 8121/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  54%|▌| 8121/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -74863,8 +74722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8121/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  54%|▌| 8121/14932 [11:45<09:52, 11.50it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  54%|▌| 8122/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  54%|▌| 8122/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -74872,8 +74731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8122/14932 [11:45<09:51, 11.50it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  54%|▌| 8122/14932 [11:45<09:51, 11.50it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  54%|▌| 8123/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  54%|▌| 8123/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -74881,8 +74740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8123/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  54%|▌| 8123/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  54%|▌| 8124/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  54%|▌| 8124/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -74890,7 +74749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8124/14932 [11:46<09:51, 11.51it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  54%|▌| 8125/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  54%|▌| 8125/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -74898,7 +74758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8124/14932 [11:46<09:51, 11.51it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  54%|▌| 8126/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  54%|▌| 8126/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -74906,8 +74767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8125/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  54%|▌| 8125/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  54%|▌| 8127/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  54%|▌| 8127/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -74915,8 +74776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8126/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  54%|▌| 8126/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  54%|▌| 8128/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  54%|▌| 8128/14932 [11:44<09:50, 11.53it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -74924,8 +74785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8127/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  54%|▌| 8127/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  54%|▌| 8129/14932 [11:44<09:49, 11.53it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  54%|▌| 8129/14932 [11:44<09:49, 11.53it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -74933,8 +74794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8128/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  54%|▌| 8128/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  54%|▌| 8130/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  54%|▌| 8130/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -74942,8 +74803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8129/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  54%|▌| 8129/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  54%|▌| 8131/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  54%|▌| 8131/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -74951,8 +74812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8130/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  54%|▌| 8130/14932 [11:46<09:51, 11.50it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  54%|▌| 8132/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  54%|▌| 8132/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -74960,8 +74821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8131/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  54%|▌| 8131/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=1.50"
+      "Epoch 0:  54%|▌| 8133/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  54%|▌| 8133/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -74969,8 +74830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8132/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=1.50\r",
-      "Epoch 0:  54%|▌| 8132/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  54%|▌| 8134/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  54%|▌| 8134/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -74978,8 +74839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8133/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  54%|▌| 8133/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  54%|▌| 8135/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  54%|▌| 8135/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -74987,8 +74848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8134/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  54%|▌| 8134/14932 [11:47<09:51, 11.50it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  54%|▌| 8136/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  54%|▌| 8136/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -74996,8 +74857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8135/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  54%|▌| 8135/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  54%|▌| 8137/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  54%|▌| 8137/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -75005,8 +74866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8136/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  54%|▌| 8136/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  55%|▌| 8138/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  55%|▌| 8138/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -75014,8 +74875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  54%|▌| 8137/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  54%|▌| 8137/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  55%|▌| 8139/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  55%|▌| 8139/14932 [11:45<09:49, 11.53it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -75023,8 +74884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8138/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  55%|▌| 8138/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  55%|▌| 8140/14932 [11:45<09:48, 11.53it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  55%|▌| 8140/14932 [11:45<09:48, 11.53it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -75032,8 +74893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8139/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  55%|▌| 8139/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  55%|▌| 8141/14932 [11:45<09:48, 11.53it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  55%|▌| 8141/14932 [11:45<09:48, 11.53it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -75041,8 +74902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8140/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  55%|▌| 8140/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  55%|▌| 8142/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  55%|▌| 8142/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -75050,8 +74911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8141/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  55%|▌| 8141/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  55%|▌| 8143/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  55%|▌| 8143/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -75059,8 +74920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8142/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  55%|▌| 8142/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  55%|▌| 8144/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  55%|▌| 8144/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -75068,8 +74929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8143/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  55%|▌| 8143/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  55%|▌| 8145/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  55%|▌| 8145/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -75077,8 +74938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8144/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  55%|▌| 8144/14932 [11:47<09:50, 11.50it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  55%|▌| 8146/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  55%|▌| 8146/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -75086,8 +74947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8145/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  55%|▌| 8145/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  55%|▌| 8147/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  55%|▌| 8147/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -75095,8 +74956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8146/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  55%|▌| 8146/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  55%|▌| 8148/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  55%|▌| 8148/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -75104,8 +74965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8147/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  55%|▌| 8147/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  55%|▌| 8149/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  55%|▌| 8149/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -75113,8 +74974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8148/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  55%|▌| 8148/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  55%|▌| 8150/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  55%|▌| 8150/14932 [11:46<09:48, 11.53it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -75122,8 +74983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8149/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  55%|▌| 8149/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  55%|▌| 8151/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  55%|▌| 8151/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -75131,8 +74992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8150/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  55%|▌| 8150/14932 [11:48<09:49, 11.50it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  55%|▌| 8152/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  55%|▌| 8152/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -75140,8 +75001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8151/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  55%|▌| 8151/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=1.00"
+      "Epoch 0:  55%|▌| 8153/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  55%|▌| 8153/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -75149,8 +75010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8152/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=1.00\r",
-      "Epoch 0:  55%|▌| 8152/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  55%|▌| 8154/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  55%|▌| 8154/14932 [11:46<09:47, 11.53it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -75158,8 +75019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8153/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  55%|▌| 8153/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  55%|▌| 8155/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  55%|▌| 8155/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -75167,8 +75028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8154/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  55%|▌| 8154/14932 [11:48<09:49, 11.51it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  55%|▌| 8156/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  55%|▌| 8156/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -75176,8 +75037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8155/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  55%|▌| 8155/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  55%|▌| 8157/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  55%|▌| 8157/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=1.25"
      ]
     },
     {
@@ -75185,8 +75046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8156/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  55%|▌| 8156/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  55%|▌| 8158/14932 [11:47<09:47, 11.54it/s, v_num=ui8w, train/loss=1.25\r",
+      "Epoch 0:  55%|▌| 8158/14932 [11:47<09:47, 11.54it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -75194,8 +75055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8157/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  55%|▌| 8157/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  55%|▌| 8159/14932 [11:47<09:47, 11.54it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  55%|▌| 8159/14932 [11:47<09:47, 11.54it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -75203,8 +75064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8158/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  55%|▌| 8158/14932 [11:48<09:48, 11.51it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  55%|▌| 8160/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  55%|▌| 8160/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -75212,7 +75073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8159/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  55%|▌| 8161/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  55%|▌| 8161/14932 [11:47<09:47, 11.53it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -75220,7 +75082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8159/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  55%|▌| 8162/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  55%|▌| 8162/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -75228,8 +75091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8160/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  55%|▌| 8160/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  55%|▌| 8163/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  55%|▌| 8163/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -75237,8 +75100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8161/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  55%|▌| 8161/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  55%|▌| 8164/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  55%|▌| 8164/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -75246,8 +75109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8162/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  55%|▌| 8162/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  55%|▌| 8165/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  55%|▌| 8165/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -75255,8 +75118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8163/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  55%|▌| 8163/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  55%|▌| 8166/14932 [11:47<09:46, 11.53it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  55%|▌| 8166/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -75264,8 +75127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8164/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  55%|▌| 8164/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  55%|▌| 8167/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  55%|▌| 8167/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -75273,8 +75136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8165/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  55%|▌| 8165/14932 [11:49<09:48, 11.50it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  55%|▌| 8168/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  55%|▌| 8168/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -75282,7 +75145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8166/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  55%|▌| 8169/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  55%|▌| 8169/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -75290,7 +75154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8166/14932 [11:49<09:48, 11.51it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  55%|▌| 8170/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  55%|▌| 8170/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -75298,8 +75163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8167/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  55%|▌| 8167/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=0.50"
+      "Epoch 0:  55%|▌| 8171/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  55%|▌| 8171/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -75307,8 +75172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8168/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=0.50\r",
-      "Epoch 0:  55%|▌| 8168/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  55%|▌| 8172/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  55%|▌| 8172/14932 [11:48<09:46, 11.53it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -75316,8 +75181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8169/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  55%|▌| 8169/14932 [11:49<09:47, 11.51it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  55%|▌| 8173/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  55%|▌| 8173/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -75325,8 +75190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8170/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  55%|▌| 8170/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  55%|▌| 8174/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  55%|▌| 8174/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -75334,8 +75199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8171/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  55%|▌| 8171/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=1.23"
+      "Epoch 0:  55%|▌| 8175/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  55%|▌| 8175/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -75343,8 +75208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8172/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=1.23\r",
-      "Epoch 0:  55%|▌| 8172/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  55%|▌| 8176/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  55%|▌| 8176/14932 [11:48<09:45, 11.53it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -75352,8 +75217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8173/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  55%|▌| 8173/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  55%|▌| 8177/14932 [11:48<09:45, 11.54it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  55%|▌| 8177/14932 [11:48<09:45, 11.54it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -75361,8 +75226,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8174/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  55%|▌| 8174/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  55%|▌| 8178/14932 [11:48<09:45, 11.54it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -75370,8 +75234,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8175/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  55%|▌| 8175/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  55%|▌| 8178/14932 [11:48<09:45, 11.54it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -75379,8 +75242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8176/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  55%|▌| 8176/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  55%|▌| 8179/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  55%|▌| 8179/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -75388,8 +75251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8177/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  55%|▌| 8177/14932 [11:50<09:47, 11.51it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  55%|▌| 8180/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  55%|▌| 8180/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -75397,8 +75260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8178/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  55%|▌| 8178/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  55%|▌| 8181/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  55%|▌| 8181/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -75406,8 +75269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8179/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  55%|▌| 8179/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  55%|▌| 8182/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  55%|▌| 8182/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -75415,8 +75278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8180/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  55%|▌| 8180/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  55%|▌| 8183/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  55%|▌| 8183/14932 [11:49<09:45, 11.54it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -75424,8 +75287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8181/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  55%|▌| 8181/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  55%|▌| 8184/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  55%|▌| 8184/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -75433,8 +75296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8182/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  55%|▌| 8182/14932 [11:50<09:46, 11.51it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  55%|▌| 8185/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  55%|▌| 8185/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -75442,8 +75305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8183/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  55%|▌| 8183/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  55%|▌| 8186/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  55%|▌| 8186/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -75451,8 +75314,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8184/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  55%|▌| 8184/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  55%|▌| 8187/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -75460,8 +75322,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8185/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  55%|▌| 8185/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  55%|▌| 8187/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -75469,8 +75330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8186/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  55%|▌| 8186/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  55%|▌| 8188/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  55%|▌| 8188/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -75478,8 +75339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8187/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  55%|▌| 8187/14932 [11:51<09:46, 11.51it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  55%|▌| 8189/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  55%|▌| 8189/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -75487,8 +75348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8188/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  55%|▌| 8188/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  55%|▌| 8190/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  55%|▌| 8190/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -75496,8 +75357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8189/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  55%|▌| 8189/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  55%|▌| 8191/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  55%|▌| 8191/14932 [11:49<09:44, 11.54it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -75505,8 +75366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8190/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  55%|▌| 8190/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  55%|▌| 8192/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  55%|▌| 8192/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -75514,8 +75375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8191/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  55%|▌| 8191/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=5.06"
+      "Epoch 0:  55%|▌| 8193/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  55%|▌| 8193/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -75523,8 +75384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8192/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=5.06\r",
-      "Epoch 0:  55%|▌| 8192/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  55%|▌| 8194/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  55%|▌| 8194/14932 [11:50<09:44, 11.54it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -75532,8 +75393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8193/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  55%|▌| 8193/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  55%|▌| 8195/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  55%|▌| 8195/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -75541,8 +75402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8194/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  55%|▌| 8194/14932 [11:51<09:45, 11.51it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  55%|▌| 8196/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  55%|▌| 8196/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -75550,8 +75411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8195/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  55%|▌| 8195/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  55%|▌| 8197/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  55%|▌| 8197/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -75559,8 +75420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8196/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  55%|▌| 8196/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  55%|▌| 8198/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  55%|▌| 8198/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -75568,8 +75429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8197/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  55%|▌| 8197/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  55%|▌| 8199/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  55%|▌| 8199/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -75577,8 +75438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8198/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  55%|▌| 8198/14932 [11:52<09:45, 11.51it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  55%|▌| 8200/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  55%|▌| 8200/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -75586,8 +75447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8199/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  55%|▌| 8199/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  55%|▌| 8201/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  55%|▌| 8201/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -75595,8 +75456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8200/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  55%|▌| 8200/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  55%|▌| 8202/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  55%|▌| 8202/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -75604,8 +75465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8201/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  55%|▌| 8201/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  55%|▌| 8203/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  55%|▌| 8203/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -75613,8 +75474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8202/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  55%|▌| 8202/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=0.96"
+      "Epoch 0:  55%|▌| 8204/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  55%|▌| 8204/14932 [11:50<09:43, 11.54it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -75622,8 +75483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8203/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=0.96\r",
-      "Epoch 0:  55%|▌| 8203/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  55%|▌| 8205/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  55%|▌| 8205/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -75631,8 +75492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8204/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  55%|▌| 8204/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  55%|▌| 8206/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  55%|▌| 8206/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -75640,8 +75501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8205/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  55%|▌| 8205/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  55%|▌| 8207/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  55%|▌| 8207/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -75649,8 +75510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8206/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  55%|▌| 8206/14932 [11:52<09:44, 11.51it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  55%|▌| 8208/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  55%|▌| 8208/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -75658,8 +75519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8207/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  55%|▌| 8207/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  55%|▌| 8209/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  55%|▌| 8209/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -75667,8 +75528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8208/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  55%|▌| 8208/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  55%|▌| 8210/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  55%|▌| 8210/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -75676,8 +75537,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8209/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  55%|▌| 8209/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  55%|▌| 8211/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -75685,8 +75545,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8210/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  55%|▌| 8210/14932 [11:53<09:44, 11.51it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  55%|▌| 8211/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -75694,8 +75553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8211/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  55%|▌| 8211/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  55%|▌| 8212/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  55%|▌| 8212/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -75703,8 +75562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8212/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  55%|▌| 8212/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  55%|▌| 8213/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  55%|▌| 8213/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -75712,8 +75571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8213/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  55%|▌| 8213/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  55%|▌| 8214/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  55%|▌| 8214/14932 [11:51<09:42, 11.54it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -75721,8 +75580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8214/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  55%|▌| 8214/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  55%|▌| 8215/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  55%|▌| 8215/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -75730,8 +75589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8215/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  55%|▌| 8215/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  55%|▌| 8216/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  55%|▌| 8216/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -75739,8 +75598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8216/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  55%|▌| 8216/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  55%|▌| 8217/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  55%|▌| 8217/14932 [11:51<09:41, 11.54it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -75748,8 +75607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8217/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  55%|▌| 8217/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  55%|▌| 8218/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  55%|▌| 8218/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -75757,8 +75616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8218/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  55%|▌| 8218/14932 [11:53<09:43, 11.51it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  55%|▌| 8219/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  55%|▌| 8219/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -75766,8 +75625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8219/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  55%|▌| 8219/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  55%|▌| 8220/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  55%|▌| 8220/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -75775,8 +75634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8220/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  55%|▌| 8220/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  55%|▌| 8221/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  55%|▌| 8221/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -75784,8 +75643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8221/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  55%|▌| 8221/14932 [11:54<09:43, 11.51it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  55%|▌| 8222/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  55%|▌| 8222/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -75793,8 +75652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8222/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  55%|▌| 8222/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  55%|▌| 8223/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  55%|▌| 8223/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -75802,8 +75661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8223/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  55%|▌| 8223/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  55%|▌| 8224/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  55%|▌| 8224/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -75811,8 +75670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8224/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  55%|▌| 8224/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  55%|▌| 8225/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  55%|▌| 8225/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -75820,8 +75679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8225/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  55%|▌| 8225/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  55%|▌| 8226/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  55%|▌| 8226/14932 [11:52<09:41, 11.54it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -75829,8 +75688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8226/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  55%|▌| 8226/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  55%|▌| 8227/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  55%|▌| 8227/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -75838,8 +75697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8227/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  55%|▌| 8227/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  55%|▌| 8228/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  55%|▌| 8228/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -75847,8 +75706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8228/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  55%|▌| 8228/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  55%|▌| 8229/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  55%|▌| 8229/14932 [11:52<09:40, 11.54it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -75856,8 +75715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8229/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  55%|▌| 8229/14932 [11:54<09:42, 11.51it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  55%|▌| 8230/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  55%|▌| 8230/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -75865,8 +75724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8230/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  55%|▌| 8230/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  55%|▌| 8231/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  55%|▌| 8231/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -75874,8 +75733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8231/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  55%|▌| 8231/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  55%|▌| 8232/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  55%|▌| 8232/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -75883,8 +75742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8232/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  55%|▌| 8232/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  55%|▌| 8233/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  55%|▌| 8233/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -75892,8 +75751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8233/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  55%|▌| 8233/14932 [11:55<09:42, 11.51it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  55%|▌| 8234/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  55%|▌| 8234/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -75901,8 +75760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8234/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  55%|▌| 8234/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  55%|▌| 8235/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  55%|▌| 8235/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=1.32"
      ]
     },
     {
@@ -75910,8 +75769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8235/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  55%|▌| 8235/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=0.82"
+      "Epoch 0:  55%|▌| 8236/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=1.32\r",
+      "Epoch 0:  55%|▌| 8236/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -75919,8 +75778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8236/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=0.82\r",
-      "Epoch 0:  55%|▌| 8236/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  55%|▌| 8237/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  55%|▌| 8237/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -75928,8 +75787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8237/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  55%|▌| 8237/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  55%|▌| 8238/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  55%|▌| 8238/14932 [11:53<09:40, 11.54it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -75937,8 +75796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8238/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  55%|▌| 8238/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  55%|▌| 8239/14932 [11:53<09:39, 11.54it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  55%|▌| 8239/14932 [11:53<09:39, 11.54it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -75946,8 +75805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8239/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  55%|▌| 8239/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  55%|▌| 8240/14932 [11:53<09:39, 11.54it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  55%|▌| 8240/14932 [11:53<09:39, 11.54it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -75955,8 +75814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8240/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  55%|▌| 8240/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  55%|▌| 8241/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  55%|▌| 8241/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -75964,8 +75823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8241/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  55%|▌| 8241/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  55%|▌| 8242/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  55%|▌| 8242/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -75973,8 +75832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8242/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  55%|▌| 8242/14932 [11:55<09:41, 11.51it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  55%|▌| 8243/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  55%|▌| 8243/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -75982,8 +75841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8243/14932 [11:56<09:41, 11.51it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  55%|▌| 8243/14932 [11:56<09:41, 11.51it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  55%|▌| 8244/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  55%|▌| 8244/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -75991,8 +75850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8244/14932 [11:56<09:41, 11.51it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  55%|▌| 8244/14932 [11:56<09:41, 11.51it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  55%|▌| 8245/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  55%|▌| 8245/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -76000,8 +75859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8245/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  55%|▌| 8245/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  55%|▌| 8246/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  55%|▌| 8246/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -76009,8 +75868,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8246/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  55%|▌| 8246/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  55%|▌| 8247/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -76018,8 +75876,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8247/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  55%|▌| 8247/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  55%|▌| 8247/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -76027,8 +75884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8248/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  55%|▌| 8248/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  55%|▌| 8248/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  55%|▌| 8248/14932 [11:54<09:39, 11.54it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -76036,8 +75893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8249/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  55%|▌| 8249/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  55%|▌| 8249/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  55%|▌| 8249/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -76045,8 +75902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8250/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  55%|▌| 8250/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  55%|▌| 8250/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  55%|▌| 8250/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -76054,8 +75911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8251/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  55%|▌| 8251/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  55%|▌| 8251/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  55%|▌| 8251/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -76063,8 +75920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8252/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  55%|▌| 8252/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  55%|▌| 8252/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  55%|▌| 8252/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -76072,8 +75929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8253/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  55%|▌| 8253/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  55%|▌| 8253/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  55%|▌| 8253/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=1.04"
      ]
     },
     {
@@ -76081,8 +75938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8254/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  55%|▌| 8254/14932 [11:56<09:40, 11.51it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  55%|▌| 8254/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=1.04\r",
+      "Epoch 0:  55%|▌| 8254/14932 [11:54<09:38, 11.54it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -76090,8 +75947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8255/14932 [11:56<09:39, 11.51it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  55%|▌| 8255/14932 [11:56<09:39, 11.51it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  55%|▌| 8255/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  55%|▌| 8255/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -76099,8 +75956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8256/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  55%|▌| 8256/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  55%|▌| 8256/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  55%|▌| 8256/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -76108,8 +75965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8257/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  55%|▌| 8257/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  55%|▌| 8257/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  55%|▌| 8257/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -76117,8 +75974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8258/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  55%|▌| 8258/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  55%|▌| 8258/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  55%|▌| 8258/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -76126,8 +75983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8259/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  55%|▌| 8259/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  55%|▌| 8259/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  55%|▌| 8259/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -76135,7 +75992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8260/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  55%|▌| 8260/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  55%|▌| 8260/14932 [11:55<09:38, 11.54it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -76143,7 +76001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8260/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  55%|▌| 8261/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  55%|▌| 8261/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -76151,8 +76010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8261/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  55%|▌| 8261/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  55%|▌| 8262/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  55%|▌| 8262/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -76160,7 +76019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8262/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  55%|▌| 8263/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  55%|▌| 8263/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -76168,7 +76028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8262/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  55%|▌| 8264/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  55%|▌| 8264/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -76176,8 +76037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8263/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  55%|▌| 8263/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  55%|▌| 8265/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  55%|▌| 8265/14932 [11:55<09:37, 11.54it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -76185,8 +76046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8264/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  55%|▌| 8264/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  55%|▌| 8266/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  55%|▌| 8266/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -76194,8 +76055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8265/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  55%|▌| 8265/14932 [11:57<09:39, 11.51it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  55%|▌| 8267/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  55%|▌| 8267/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -76203,8 +76064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8266/14932 [11:57<09:38, 11.51it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  55%|▌| 8266/14932 [11:57<09:38, 11.51it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  55%|▌| 8268/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  55%|▌| 8268/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -76212,8 +76073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8267/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  55%|▌| 8267/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  55%|▌| 8269/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  55%|▌| 8269/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -76221,8 +76082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8268/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  55%|▌| 8268/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  55%|▌| 8270/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  55%|▌| 8270/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -76230,8 +76091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8269/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  55%|▌| 8269/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  55%|▌| 8271/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  55%|▌| 8271/14932 [11:56<09:37, 11.54it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -76239,8 +76100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8270/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  55%|▌| 8270/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  55%|▌| 8272/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  55%|▌| 8272/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -76248,8 +76109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8271/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  55%|▌| 8271/14932 [11:58<09:38, 11.51it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  55%|▌| 8273/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  55%|▌| 8273/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -76257,8 +76118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8272/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  55%|▌| 8272/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  55%|▌| 8274/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  55%|▌| 8274/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -76266,8 +76127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8273/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  55%|▌| 8273/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  55%|▌| 8275/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  55%|▌| 8275/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -76275,8 +76136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8274/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  55%|▌| 8274/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  55%|▌| 8276/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  55%|▌| 8276/14932 [11:56<09:36, 11.54it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -76284,8 +76145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8275/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  55%|▌| 8275/14932 [11:58<09:38, 11.52it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  55%|▌| 8277/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  55%|▌| 8277/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -76293,8 +76154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8276/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  55%|▌| 8276/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  55%|▌| 8278/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  55%|▌| 8278/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -76302,8 +76163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8277/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  55%|▌| 8277/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  55%|▌| 8279/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  55%|▌| 8279/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -76311,8 +76172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8278/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  55%|▌| 8278/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  55%|▌| 8280/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  55%|▌| 8280/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -76320,8 +76181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8279/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  55%|▌| 8279/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:  55%|▌| 8281/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  55%|▌| 8281/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -76329,8 +76190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8280/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:  55%|▌| 8280/14932 [11:58<09:37, 11.52it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  55%|▌| 8282/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  55%|▌| 8282/14932 [11:57<09:36, 11.54it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -76338,8 +76199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8281/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  55%|▌| 8281/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  55%|▌| 8283/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  55%|▌| 8283/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -76347,8 +76208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8282/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  55%|▌| 8282/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  55%|▌| 8284/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  55%|▌| 8284/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -76356,8 +76217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8283/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  55%|▌| 8283/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  55%|▌| 8285/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  55%|▌| 8285/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=0.93"
      ]
     },
     {
@@ -76365,8 +76226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8284/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  55%|▌| 8284/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  55%|▌| 8286/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=0.93\r",
+      "Epoch 0:  55%|▌| 8286/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -76374,8 +76235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8285/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  55%|▌| 8285/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  55%|▌| 8287/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  55%|▌| 8287/14932 [11:57<09:35, 11.54it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -76383,8 +76244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8286/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  55%|▌| 8286/14932 [11:59<09:37, 11.52it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  56%|▌| 8288/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  56%|▌| 8288/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -76392,8 +76253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  55%|▌| 8287/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  55%|▌| 8287/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  56%|▌| 8289/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  56%|▌| 8289/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -76401,8 +76262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8288/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  56%|▌| 8288/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  56%|▌| 8290/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  56%|▌| 8290/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=0.93"
      ]
     },
     {
@@ -76410,8 +76271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8289/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  56%|▌| 8289/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  56%|▌| 8291/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=0.93\r",
+      "Epoch 0:  56%|▌| 8291/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -76419,8 +76280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8290/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  56%|▌| 8290/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  56%|▌| 8292/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  56%|▌| 8292/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -76428,8 +76289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8291/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  56%|▌| 8291/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  56%|▌| 8293/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  56%|▌| 8293/14932 [11:58<09:35, 11.54it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -76437,8 +76298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8292/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  56%|▌| 8292/14932 [11:59<09:36, 11.52it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  56%|▌| 8294/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  56%|▌| 8294/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -76446,8 +76307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8293/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  56%|▌| 8293/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  56%|▌| 8295/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  56%|▌| 8295/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -76455,8 +76316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8294/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  56%|▌| 8294/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  56%|▌| 8296/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  56%|▌| 8296/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -76464,8 +76325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8295/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  56%|▌| 8295/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  56%|▌| 8297/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  56%|▌| 8297/14932 [11:58<09:34, 11.54it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -76473,8 +76334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8296/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  56%|▌| 8296/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  56%|▌| 8298/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  56%|▌| 8298/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -76482,8 +76343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8297/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  56%|▌| 8297/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  56%|▌| 8299/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  56%|▌| 8299/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -76491,8 +76352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8298/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  56%|▌| 8298/14932 [12:00<09:36, 11.52it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  56%|▌| 8300/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  56%|▌| 8300/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=1.53"
      ]
     },
     {
@@ -76500,8 +76361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8299/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  56%|▌| 8299/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  56%|▌| 8301/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=1.53\r",
+      "Epoch 0:  56%|▌| 8301/14932 [11:58<09:34, 11.55it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -76509,8 +76370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8300/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  56%|▌| 8300/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  56%|▌| 8302/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  56%|▌| 8302/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -76518,8 +76379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8301/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  56%|▌| 8301/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  56%|▌| 8303/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  56%|▌| 8303/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -76527,8 +76388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8302/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  56%|▌| 8302/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  56%|▌| 8304/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  56%|▌| 8304/14932 [11:59<09:34, 11.55it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -76536,8 +76397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8303/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  56%|▌| 8303/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  56%|▌| 8305/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  56%|▌| 8305/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -76545,8 +76406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8304/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  56%|▌| 8304/14932 [12:00<09:35, 11.52it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  56%|▌| 8306/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  56%|▌| 8306/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -76554,8 +76415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8305/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  56%|▌| 8305/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  56%|▌| 8307/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  56%|▌| 8307/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -76563,8 +76424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8306/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  56%|▌| 8306/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  56%|▌| 8308/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  56%|▌| 8308/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -76572,8 +76433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8307/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  56%|▌| 8307/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  56%|▌| 8309/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  56%|▌| 8309/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -76581,8 +76442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8308/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  56%|▌| 8308/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  56%|▌| 8310/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  56%|▌| 8310/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -76590,8 +76451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8309/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  56%|▌| 8309/14932 [12:01<09:35, 11.52it/s, v_num=o30c, train/loss=1.27"
+      "Epoch 0:  56%|▌| 8311/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  56%|▌| 8311/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -76599,8 +76460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8310/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=1.27\r",
-      "Epoch 0:  56%|▌| 8310/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  56%|▌| 8312/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  56%|▌| 8312/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -76608,8 +76469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8311/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  56%|▌| 8311/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  56%|▌| 8313/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  56%|▌| 8313/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -76617,8 +76478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8312/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  56%|▌| 8312/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  56%|▌| 8314/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  56%|▌| 8314/14932 [11:59<09:33, 11.55it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -76626,8 +76487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8313/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  56%|▌| 8313/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=0.72"
+      "Epoch 0:  56%|▌| 8315/14932 [12:00<09:33, 11.55it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  56%|▌| 8315/14932 [12:00<09:33, 11.55it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -76635,8 +76496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8314/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=0.72\r",
-      "Epoch 0:  56%|▌| 8314/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  56%|▌| 8316/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  56%|▌| 8316/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -76644,8 +76505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8315/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  56%|▌| 8315/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  56%|▌| 8317/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  56%|▌| 8317/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -76653,8 +76514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8316/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  56%|▌| 8316/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  56%|▌| 8318/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  56%|▌| 8318/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -76662,8 +76523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8317/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  56%|▌| 8317/14932 [12:01<09:34, 11.52it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  56%|▌| 8319/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  56%|▌| 8319/14932 [12:00<09:32, 11.55it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -76671,8 +76532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8318/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  56%|▌| 8318/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  56%|▌| 8320/14932 [12:00<09:32, 11.54it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  56%|▌| 8320/14932 [12:00<09:32, 11.54it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -76680,8 +76541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8319/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  56%|▌| 8319/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  56%|▌| 8321/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  56%|▌| 8321/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -76689,8 +76550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8320/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  56%|▌| 8320/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  56%|▌| 8322/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  56%|▌| 8322/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -76698,8 +76559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8321/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  56%|▌| 8321/14932 [12:02<09:34, 11.52it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  56%|▌| 8323/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  56%|▌| 8323/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -76707,8 +76568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8322/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  56%|▌| 8322/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  56%|▌| 8324/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  56%|▌| 8324/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -76716,8 +76577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8323/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  56%|▌| 8323/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  56%|▌| 8325/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  56%|▌| 8325/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -76725,8 +76586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8324/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  56%|▌| 8324/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  56%|▌| 8326/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  56%|▌| 8326/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -76734,8 +76595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8325/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  56%|▌| 8325/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  56%|▌| 8327/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  56%|▌| 8327/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -76743,8 +76604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8326/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  56%|▌| 8326/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  56%|▌| 8328/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  56%|▌| 8328/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -76752,8 +76613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8327/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  56%|▌| 8327/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  56%|▌| 8329/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  56%|▌| 8329/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -76761,8 +76622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8328/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  56%|▌| 8328/14932 [12:02<09:33, 11.52it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  56%|▌| 8330/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  56%|▌| 8330/14932 [12:01<09:32, 11.54it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -76770,8 +76631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8329/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  56%|▌| 8329/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  56%|▌| 8331/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  56%|▌| 8331/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -76779,8 +76640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8330/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  56%|▌| 8330/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  56%|▌| 8332/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  56%|▌| 8332/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -76788,8 +76649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8331/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  56%|▌| 8331/14932 [12:03<09:33, 11.52it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  56%|▌| 8333/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  56%|▌| 8333/14932 [12:01<09:31, 11.54it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -76797,8 +76658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8332/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  56%|▌| 8332/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  56%|▌| 8334/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  56%|▌| 8334/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -76806,8 +76667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8333/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  56%|▌| 8333/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  56%|▌| 8335/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  56%|▌| 8335/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -76815,8 +76676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8334/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  56%|▌| 8334/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  56%|▌| 8336/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  56%|▌| 8336/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -76824,8 +76685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8335/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  56%|▌| 8335/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  56%|▌| 8337/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  56%|▌| 8337/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -76833,8 +76694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8336/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  56%|▌| 8336/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  56%|▌| 8338/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  56%|▌| 8338/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -76842,8 +76703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8337/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  56%|▌| 8337/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  56%|▌| 8339/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  56%|▌| 8339/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -76851,8 +76712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8338/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  56%|▌| 8338/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  56%|▌| 8340/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  56%|▌| 8340/14932 [12:02<09:31, 11.54it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -76860,8 +76721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8339/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  56%|▌| 8339/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  56%|▌| 8341/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  56%|▌| 8341/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -76869,8 +76730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8340/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  56%|▌| 8340/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  56%|▌| 8342/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  56%|▌| 8342/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -76878,8 +76739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8341/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  56%|▌| 8341/14932 [12:03<09:32, 11.52it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  56%|▌| 8343/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  56%|▌| 8343/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -76887,8 +76748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8342/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  56%|▌| 8342/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  56%|▌| 8344/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  56%|▌| 8344/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -76896,8 +76757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8343/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  56%|▌| 8343/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  56%|▌| 8345/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  56%|▌| 8345/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=1.65"
      ]
     },
     {
@@ -76905,8 +76766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8344/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  56%|▌| 8344/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  56%|▌| 8346/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=1.65\r",
+      "Epoch 0:  56%|▌| 8346/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -76914,8 +76775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8345/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  56%|▌| 8345/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  56%|▌| 8347/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  56%|▌| 8347/14932 [12:02<09:30, 11.54it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -76923,8 +76784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8346/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  56%|▌| 8346/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  56%|▌| 8348/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  56%|▌| 8348/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -76932,8 +76793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8347/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  56%|▌| 8347/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  56%|▌| 8349/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  56%|▌| 8349/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -76941,8 +76802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8348/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  56%|▌| 8348/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  56%|▌| 8350/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  56%|▌| 8350/14932 [12:03<09:30, 11.55it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -76950,8 +76811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8349/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  56%|▌| 8349/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  56%|▌| 8351/14932 [12:03<09:29, 11.55it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  56%|▌| 8351/14932 [12:03<09:29, 11.55it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -76959,8 +76820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8350/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  56%|▌| 8350/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  56%|▌| 8352/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  56%|▌| 8352/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -76968,8 +76829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8351/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  56%|▌| 8351/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.75"
+      "Epoch 0:  56%|▌| 8353/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  56%|▌| 8353/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -76977,8 +76838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8352/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=4.75\r",
-      "Epoch 0:  56%|▌| 8352/14932 [12:04<09:31, 11.52it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  56%|▌| 8354/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  56%|▌| 8354/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -76986,8 +76847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8353/14932 [12:05<09:31, 11.52it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  56%|▌| 8353/14932 [12:05<09:31, 11.52it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  56%|▌| 8355/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  56%|▌| 8355/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -76995,8 +76856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8354/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  56%|▌| 8354/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  56%|▌| 8356/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  56%|▌| 8356/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -77004,8 +76865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8355/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  56%|▌| 8355/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  56%|▌| 8357/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  56%|▌| 8357/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -77013,8 +76874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8356/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  56%|▌| 8356/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  56%|▌| 8358/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  56%|▌| 8358/14932 [12:03<09:29, 11.54it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -77022,8 +76883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8357/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  56%|▌| 8357/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  56%|▌| 8359/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  56%|▌| 8359/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -77031,8 +76892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8358/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  56%|▌| 8358/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  56%|▌| 8360/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  56%|▌| 8360/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -77040,8 +76901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8359/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  56%|▌| 8359/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  56%|▌| 8361/14932 [12:04<09:29, 11.55it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  56%|▌| 8361/14932 [12:04<09:29, 11.55it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -77049,8 +76910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8360/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  56%|▌| 8360/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  56%|▌| 8362/14932 [12:04<09:29, 11.55it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  56%|▌| 8362/14932 [12:04<09:29, 11.55it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -77058,8 +76919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8361/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  56%|▌| 8361/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  56%|▌| 8363/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  56%|▌| 8363/14932 [12:04<09:29, 11.54it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -77067,8 +76928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8362/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  56%|▌| 8362/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  56%|▌| 8364/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  56%|▌| 8364/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -77076,8 +76937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8363/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  56%|▌| 8363/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  56%|▌| 8365/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  56%|▌| 8365/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -77085,8 +76946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8364/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  56%|▌| 8364/14932 [12:05<09:30, 11.52it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  56%|▌| 8366/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  56%|▌| 8366/14932 [12:04<09:28, 11.54it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -77094,8 +76955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8365/14932 [12:05<09:29, 11.52it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  56%|▌| 8365/14932 [12:05<09:29, 11.52it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  56%|▌| 8367/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  56%|▌| 8367/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -77103,8 +76964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8366/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  56%|▌| 8366/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  56%|▌| 8368/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  56%|▌| 8368/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -77112,8 +76973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8367/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  56%|▌| 8367/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  56%|▌| 8369/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  56%|▌| 8369/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -77121,8 +76982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8368/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  56%|▌| 8368/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  56%|▌| 8370/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  56%|▌| 8370/14932 [12:04<09:28, 11.55it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -77130,8 +76991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8369/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  56%|▌| 8369/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  56%|▌| 8371/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  56%|▌| 8371/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -77139,8 +77000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8370/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  56%|▌| 8370/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  56%|▌| 8372/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  56%|▌| 8372/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -77148,8 +77009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8371/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  56%|▌| 8371/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  56%|▌| 8373/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  56%|▌| 8373/14932 [12:05<09:28, 11.55it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -77157,8 +77018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8372/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  56%|▌| 8372/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  56%|▌| 8374/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  56%|▌| 8374/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -77166,8 +77027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8373/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  56%|▌| 8373/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  56%|▌| 8375/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  56%|▌| 8375/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=0.95"
      ]
     },
     {
@@ -77175,8 +77036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8374/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  56%|▌| 8374/14932 [12:06<09:29, 11.52it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  56%|▌| 8376/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=0.95\r",
+      "Epoch 0:  56%|▌| 8376/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -77184,8 +77045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8375/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  56%|▌| 8375/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  56%|▌| 8377/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  56%|▌| 8377/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -77193,8 +77054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8376/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  56%|▌| 8376/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  56%|▌| 8378/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  56%|▌| 8378/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -77202,8 +77063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8377/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  56%|▌| 8377/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  56%|▌| 8379/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  56%|▌| 8379/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -77211,8 +77072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8378/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  56%|▌| 8378/14932 [12:06<09:28, 11.52it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  56%|▌| 8380/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  56%|▌| 8380/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -77220,7 +77081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8379/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  56%|▌| 8381/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  56%|▌| 8381/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -77228,7 +77090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8379/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  56%|▌| 8382/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  56%|▌| 8382/14932 [12:05<09:27, 11.55it/s, v_num=ui8w, train/loss=1.02"
      ]
     },
     {
@@ -77236,8 +77099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8380/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  56%|▌| 8380/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  56%|▌| 8383/14932 [12:06<09:27, 11.55it/s, v_num=ui8w, train/loss=1.02\r",
+      "Epoch 0:  56%|▌| 8383/14932 [12:06<09:27, 11.55it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -77245,8 +77108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8381/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  56%|▌| 8381/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  56%|▌| 8384/14932 [12:06<09:27, 11.54it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  56%|▌| 8384/14932 [12:06<09:27, 11.54it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -77254,8 +77117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8382/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  56%|▌| 8382/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  56%|▌| 8385/14932 [12:06<09:27, 11.55it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  56%|▌| 8385/14932 [12:06<09:27, 11.55it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -77263,8 +77126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8383/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  56%|▌| 8383/14932 [12:07<09:28, 11.53it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  56%|▌| 8386/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  56%|▌| 8386/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -77272,8 +77135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8384/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  56%|▌| 8384/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  56%|▌| 8387/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  56%|▌| 8387/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -77281,8 +77144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8385/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  56%|▌| 8385/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=1.88"
+      "Epoch 0:  56%|▌| 8388/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  56%|▌| 8388/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -77290,8 +77153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8386/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=1.88\r",
-      "Epoch 0:  56%|▌| 8386/14932 [12:07<09:28, 11.52it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  56%|▌| 8389/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  56%|▌| 8389/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -77299,8 +77162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8387/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  56%|▌| 8387/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  56%|▌| 8390/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  56%|▌| 8390/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -77308,8 +77171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8388/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  56%|▌| 8388/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  56%|▌| 8391/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  56%|▌| 8391/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -77317,8 +77180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8389/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  56%|▌| 8389/14932 [12:07<09:27, 11.52it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  56%|▌| 8392/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  56%|▌| 8392/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -77326,8 +77189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8390/14932 [12:08<09:27, 11.52it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  56%|▌| 8390/14932 [12:08<09:27, 11.52it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  56%|▌| 8393/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  56%|▌| 8393/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -77335,8 +77198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8391/14932 [12:08<09:27, 11.52it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  56%|▌| 8391/14932 [12:08<09:27, 11.52it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  56%|▌| 8394/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  56%|▌| 8394/14932 [12:06<09:26, 11.55it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -77344,8 +77207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8392/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  56%|▌| 8392/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  56%|▌| 8395/14932 [12:07<09:26, 11.55it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  56%|▌| 8395/14932 [12:07<09:26, 11.55it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -77353,8 +77216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8393/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  56%|▌| 8393/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  56%|▌| 8396/14932 [12:07<09:26, 11.55it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  56%|▌| 8396/14932 [12:07<09:26, 11.55it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -77362,8 +77225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8394/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  56%|▌| 8394/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  56%|▌| 8397/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  56%|▌| 8397/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -77371,8 +77234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8395/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  56%|▌| 8395/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  56%|▌| 8398/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  56%|▌| 8398/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=0.80"
      ]
     },
     {
@@ -77380,8 +77243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8396/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  56%|▌| 8396/14932 [12:08<09:27, 11.53it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  56%|▌| 8399/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=0.80\r",
+      "Epoch 0:  56%|▌| 8399/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -77389,8 +77252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8397/14932 [12:08<09:26, 11.53it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  56%|▌| 8397/14932 [12:08<09:26, 11.53it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  56%|▌| 8400/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  56%|▌| 8400/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -77398,8 +77261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8398/14932 [12:08<09:26, 11.53it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  56%|▌| 8398/14932 [12:08<09:26, 11.53it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  56%|▌| 8401/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  56%|▌| 8401/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -77407,8 +77270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8399/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  56%|▌| 8399/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  56%|▌| 8402/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  56%|▌| 8402/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -77416,8 +77279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8400/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  56%|▌| 8400/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  56%|▌| 8403/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  56%|▌| 8403/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -77425,8 +77288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8401/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  56%|▌| 8401/14932 [12:08<09:26, 11.52it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  56%|▌| 8404/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  56%|▌| 8404/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -77434,8 +77297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8402/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  56%|▌| 8402/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  56%|▌| 8405/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  56%|▌| 8405/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -77443,8 +77306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8403/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  56%|▌| 8403/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  56%|▌| 8406/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  56%|▌| 8406/14932 [12:07<09:25, 11.55it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -77452,8 +77315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8404/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  56%|▌| 8404/14932 [12:09<09:26, 11.52it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  56%|▌| 8407/14932 [12:07<09:24, 11.55it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  56%|▌| 8407/14932 [12:07<09:24, 11.55it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -77461,8 +77324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8405/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  56%|▌| 8405/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  56%|▌| 8408/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  56%|▌| 8408/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -77470,8 +77333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8406/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  56%|▌| 8406/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  56%|▌| 8409/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  56%|▌| 8409/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -77479,8 +77342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8407/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  56%|▌| 8407/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  56%|▌| 8410/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  56%|▌| 8410/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -77488,8 +77351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8408/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  56%|▌| 8408/14932 [12:09<09:26, 11.53it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  56%|▌| 8411/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  56%|▌| 8411/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -77497,8 +77360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8409/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  56%|▌| 8409/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  56%|▌| 8412/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  56%|▌| 8412/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -77506,8 +77369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8410/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  56%|▌| 8410/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  56%|▌| 8413/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  56%|▌| 8413/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -77515,8 +77378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8411/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  56%|▌| 8411/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  56%|▌| 8414/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  56%|▌| 8414/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -77524,8 +77387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8412/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  56%|▌| 8412/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  56%|▌| 8415/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  56%|▌| 8415/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -77533,8 +77396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8413/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  56%|▌| 8413/14932 [12:09<09:25, 11.53it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  56%|▌| 8416/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  56%|▌| 8416/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -77542,8 +77405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8414/14932 [12:10<09:25, 11.53it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  56%|▌| 8414/14932 [12:10<09:25, 11.53it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  56%|▌| 8417/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  56%|▌| 8417/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -77551,8 +77414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8415/14932 [12:10<09:25, 11.53it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  56%|▌| 8415/14932 [12:10<09:25, 11.53it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  56%|▌| 8418/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  56%|▌| 8418/14932 [12:08<09:24, 11.55it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -77560,8 +77423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8416/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  56%|▌| 8416/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  56%|▌| 8419/14932 [12:08<09:23, 11.55it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  56%|▌| 8419/14932 [12:08<09:23, 11.55it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -77569,8 +77432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8417/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  56%|▌| 8417/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  56%|▌| 8420/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  56%|▌| 8420/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -77578,8 +77441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8418/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  56%|▌| 8418/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  56%|▌| 8421/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  56%|▌| 8421/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -77587,8 +77450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8419/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  56%|▌| 8419/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  56%|▌| 8422/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  56%|▌| 8422/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -77596,8 +77459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8420/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  56%|▌| 8420/14932 [12:10<09:25, 11.52it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  56%|▌| 8423/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  56%|▌| 8423/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -77605,8 +77468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8421/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  56%|▌| 8421/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  56%|▌| 8424/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  56%|▌| 8424/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -77614,8 +77477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8422/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  56%|▌| 8422/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  56%|▌| 8425/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  56%|▌| 8425/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -77623,8 +77486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8423/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  56%|▌| 8423/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  56%|▌| 8426/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  56%|▌| 8426/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -77632,8 +77495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8424/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  56%|▌| 8424/14932 [12:10<09:24, 11.53it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  56%|▌| 8427/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  56%|▌| 8427/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -77641,8 +77504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8425/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  56%|▌| 8425/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  56%|▌| 8428/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  56%|▌| 8428/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -77650,8 +77513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8426/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  56%|▌| 8426/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  56%|▌| 8429/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  56%|▌| 8429/14932 [12:09<09:23, 11.55it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -77659,8 +77522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8427/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  56%|▌| 8427/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  56%|▌| 8430/14932 [12:09<09:22, 11.55it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  56%|▌| 8430/14932 [12:09<09:22, 11.55it/s, v_num=ui8w, train/loss=1.03"
      ]
     },
     {
@@ -77668,8 +77531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8428/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  56%|▌| 8428/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  56%|▌| 8431/14932 [12:09<09:22, 11.55it/s, v_num=ui8w, train/loss=1.03\r",
+      "Epoch 0:  56%|▌| 8431/14932 [12:09<09:22, 11.55it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -77677,8 +77540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8429/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  56%|▌| 8429/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  56%|▌| 8432/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  56%|▌| 8432/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -77686,8 +77549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8430/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  56%|▌| 8430/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  56%|▌| 8433/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  56%|▌| 8433/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -77695,8 +77558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8431/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  56%|▌| 8431/14932 [12:11<09:24, 11.53it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  56%|▌| 8434/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  56%|▌| 8434/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -77704,8 +77567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8432/14932 [12:11<09:24, 11.52it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  56%|▌| 8432/14932 [12:11<09:24, 11.52it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  56%|▌| 8435/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  56%|▌| 8435/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -77713,8 +77576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8433/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  56%|▌| 8433/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  56%|▌| 8436/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  56%|▌| 8436/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=1.79"
      ]
     },
     {
@@ -77722,8 +77585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8434/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  56%|▌| 8434/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  57%|▌| 8437/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=1.79\r",
+      "Epoch 0:  57%|▌| 8437/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -77731,8 +77594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8435/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  56%|▌| 8435/14932 [12:11<09:23, 11.52it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  57%|▌| 8438/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  57%|▌| 8438/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -77740,8 +77603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  56%|▌| 8436/14932 [12:11<09:23, 11.53it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  56%|▌| 8436/14932 [12:11<09:23, 11.53it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  57%|▌| 8439/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  57%|▌| 8439/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -77749,8 +77612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8437/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  57%|▌| 8437/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  57%|▌| 8440/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  57%|▌| 8440/14932 [12:10<09:22, 11.55it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -77758,8 +77621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8438/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  57%|▌| 8438/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  57%|▌| 8441/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  57%|▌| 8441/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -77767,8 +77630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8439/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  57%|▌| 8439/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  57%|▌| 8442/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  57%|▌| 8442/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -77776,8 +77639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8440/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  57%|▌| 8440/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  57%|▌| 8443/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  57%|▌| 8443/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -77785,8 +77648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8441/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  57%|▌| 8441/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  57%|▌| 8444/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  57%|▌| 8444/14932 [12:10<09:21, 11.55it/s, v_num=ui8w, train/loss=0.86"
      ]
     },
     {
@@ -77794,8 +77657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8442/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  57%|▌| 8442/14932 [12:12<09:23, 11.53it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  57%|▌| 8445/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=0.86\r",
+      "Epoch 0:  57%|▌| 8445/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -77803,8 +77666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8443/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  57%|▌| 8443/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  57%|▌| 8446/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  57%|▌| 8446/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -77812,8 +77675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8444/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  57%|▌| 8444/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=4.81"
+      "Epoch 0:  57%|▌| 8447/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  57%|▌| 8447/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -77821,8 +77684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8445/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=4.81\r",
-      "Epoch 0:  57%|▌| 8445/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  57%|▌| 8448/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  57%|▌| 8448/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -77830,8 +77693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8446/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  57%|▌| 8446/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  57%|▌| 8449/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  57%|▌| 8449/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -77839,8 +77702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8447/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  57%|▌| 8447/14932 [12:12<09:22, 11.53it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  57%|▌| 8450/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  57%|▌| 8450/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -77848,8 +77711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8448/14932 [12:13<09:22, 11.52it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  57%|▌| 8448/14932 [12:13<09:22, 11.52it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  57%|▌| 8451/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  57%|▌| 8451/14932 [12:11<09:21, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -77857,8 +77720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8449/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  57%|▌| 8449/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  57%|▌| 8452/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  57%|▌| 8452/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -77866,8 +77729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8450/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  57%|▌| 8450/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  57%|▌| 8453/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  57%|▌| 8453/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -77875,8 +77738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8451/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  57%|▌| 8451/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  57%|▌| 8454/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  57%|▌| 8454/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -77884,8 +77747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8452/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  57%|▌| 8452/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  57%|▌| 8455/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  57%|▌| 8455/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -77893,8 +77756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8453/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  57%|▌| 8453/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=1.15"
+      "Epoch 0:  57%|▌| 8456/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  57%|▌| 8456/14932 [12:11<09:20, 11.55it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -77902,8 +77765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8454/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=1.15\r",
-      "Epoch 0:  57%|▌| 8454/14932 [12:13<09:22, 11.53it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  57%|▌| 8457/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  57%|▌| 8457/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -77911,8 +77774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8455/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  57%|▌| 8455/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=1.32"
+      "Epoch 0:  57%|▌| 8458/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  57%|▌| 8458/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -77920,8 +77783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8456/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=1.32\r",
-      "Epoch 0:  57%|▌| 8456/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  57%|▌| 8459/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  57%|▌| 8459/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -77929,8 +77792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8457/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  57%|▌| 8457/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  57%|▌| 8460/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  57%|▌| 8460/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -77938,8 +77801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8458/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  57%|▌| 8458/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=0.78"
+      "Epoch 0:  57%|▌| 8461/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  57%|▌| 8461/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -77947,8 +77810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8459/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=0.78\r",
-      "Epoch 0:  57%|▌| 8459/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  57%|▌| 8462/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  57%|▌| 8462/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -77956,8 +77819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8460/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  57%|▌| 8460/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  57%|▌| 8463/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  57%|▌| 8463/14932 [12:12<09:20, 11.55it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -77965,8 +77828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8461/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  57%|▌| 8461/14932 [12:13<09:21, 11.53it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  57%|▌| 8464/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  57%|▌| 8464/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -77974,8 +77837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8462/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  57%|▌| 8462/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  57%|▌| 8465/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  57%|▌| 8465/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -77983,8 +77846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8463/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  57%|▌| 8463/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  57%|▌| 8466/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  57%|▌| 8466/14932 [12:12<09:19, 11.55it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -77992,8 +77855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8464/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  57%|▌| 8464/14932 [12:14<09:21, 11.53it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  57%|▌| 8467/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  57%|▌| 8467/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -78001,8 +77864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8465/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  57%|▌| 8465/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  57%|▌| 8468/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  57%|▌| 8468/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -78010,8 +77873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8466/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  57%|▌| 8466/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  57%|▌| 8469/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  57%|▌| 8469/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -78019,8 +77882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8467/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  57%|▌| 8467/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  57%|▌| 8470/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  57%|▌| 8470/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -78028,8 +77891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8468/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  57%|▌| 8468/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  57%|▌| 8471/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  57%|▌| 8471/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -78037,8 +77900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8469/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  57%|▌| 8469/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  57%|▌| 8472/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  57%|▌| 8472/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -78046,8 +77909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8470/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  57%|▌| 8470/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  57%|▌| 8473/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  57%|▌| 8473/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -78055,8 +77918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8471/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  57%|▌| 8471/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  57%|▌| 8474/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  57%|▌| 8474/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -78064,8 +77927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8472/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  57%|▌| 8472/14932 [12:14<09:20, 11.53it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  57%|▌| 8475/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  57%|▌| 8475/14932 [12:13<09:19, 11.55it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -78073,8 +77936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8473/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  57%|▌| 8473/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  57%|▌| 8476/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  57%|▌| 8476/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -78082,8 +77945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8474/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  57%|▌| 8474/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  57%|▌| 8477/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  57%|▌| 8477/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -78091,8 +77954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8475/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  57%|▌| 8475/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  57%|▌| 8478/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  57%|▌| 8478/14932 [12:13<09:18, 11.55it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -78100,8 +77963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8476/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  57%|▌| 8476/14932 [12:15<09:20, 11.53it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  57%|▌| 8479/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  57%|▌| 8479/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -78109,8 +77972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8477/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  57%|▌| 8477/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  57%|▌| 8480/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  57%|▌| 8480/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -78118,8 +77981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8478/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  57%|▌| 8478/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  57%|▌| 8481/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  57%|▌| 8481/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -78127,8 +77990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8479/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  57%|▌| 8479/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  57%|▌| 8482/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  57%|▌| 8482/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -78136,8 +77999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8480/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  57%|▌| 8480/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  57%|▌| 8483/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  57%|▌| 8483/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -78145,8 +78008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8481/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  57%|▌| 8481/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  57%|▌| 8484/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  57%|▌| 8484/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -78154,8 +78017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8482/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  57%|▌| 8482/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  57%|▌| 8485/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  57%|▌| 8485/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -78163,8 +78026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8483/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  57%|▌| 8483/14932 [12:15<09:19, 11.53it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  57%|▌| 8486/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  57%|▌| 8486/14932 [12:14<09:18, 11.55it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -78172,8 +78035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8484/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  57%|▌| 8484/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  57%|▌| 8487/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  57%|▌| 8487/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -78181,8 +78044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8485/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  57%|▌| 8485/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  57%|▌| 8488/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  57%|▌| 8488/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -78190,8 +78053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8486/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  57%|▌| 8486/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  57%|▌| 8489/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  57%|▌| 8489/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -78199,8 +78062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8487/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  57%|▌| 8487/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  57%|▌| 8490/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:  57%|▌| 8490/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -78208,8 +78071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8488/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  57%|▌| 8488/14932 [12:16<09:19, 11.53it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  57%|▌| 8491/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  57%|▌| 8491/14932 [12:14<09:17, 11.55it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -78217,8 +78080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8489/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  57%|▌| 8489/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  57%|▌| 8492/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  57%|▌| 8492/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -78226,8 +78089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8490/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  57%|▌| 8490/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  57%|▌| 8493/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  57%|▌| 8493/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -78235,8 +78098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8491/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  57%|▌| 8491/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  57%|▌| 8494/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  57%|▌| 8494/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -78244,8 +78107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8492/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  57%|▌| 8492/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  57%|▌| 8495/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  57%|▌| 8495/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -78253,8 +78116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8493/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  57%|▌| 8493/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  57%|▌| 8496/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  57%|▌| 8496/14932 [12:15<09:17, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -78262,8 +78125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8494/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  57%|▌| 8494/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=1.08"
+      "Epoch 0:  57%|▌| 8497/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  57%|▌| 8497/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -78271,8 +78134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8495/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=1.08\r",
-      "Epoch 0:  57%|▌| 8495/14932 [12:16<09:18, 11.53it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  57%|▌| 8498/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  57%|▌| 8498/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -78280,8 +78143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8496/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  57%|▌| 8496/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  57%|▌| 8499/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  57%|▌| 8499/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -78289,8 +78152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8497/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  57%|▌| 8497/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  57%|▌| 8500/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  57%|▌| 8500/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -78298,8 +78161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8498/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  57%|▌| 8498/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  57%|▌| 8501/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  57%|▌| 8501/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -78307,8 +78170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8499/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  57%|▌| 8499/14932 [12:17<09:18, 11.53it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  57%|▌| 8502/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  57%|▌| 8502/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -78316,8 +78179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8500/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  57%|▌| 8500/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  57%|▌| 8503/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  57%|▌| 8503/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -78325,8 +78188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8501/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  57%|▌| 8501/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  57%|▌| 8504/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  57%|▌| 8504/14932 [12:15<09:16, 11.55it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -78334,8 +78197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8502/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  57%|▌| 8502/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  57%|▌| 8505/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  57%|▌| 8505/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -78343,8 +78206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8503/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  57%|▌| 8503/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  57%|▌| 8506/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  57%|▌| 8506/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -78352,8 +78215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8504/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  57%|▌| 8504/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.77"
+      "Epoch 0:  57%|▌| 8507/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  57%|▌| 8507/14932 [12:16<09:16, 11.55it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -78361,8 +78224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8505/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=1.77\r",
-      "Epoch 0:  57%|▌| 8505/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  57%|▌| 8508/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  57%|▌| 8508/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -78370,8 +78233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8506/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  57%|▌| 8506/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  57%|▌| 8509/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  57%|▌| 8509/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -78379,8 +78242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8507/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  57%|▌| 8507/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  57%|▌| 8510/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  57%|▌| 8510/14932 [12:16<09:15, 11.56it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -78388,8 +78251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8508/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  57%|▌| 8508/14932 [12:17<09:17, 11.53it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  57%|▌| 8511/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  57%|▌| 8511/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -78397,8 +78260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8509/14932 [12:18<09:17, 11.53it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  57%|▌| 8509/14932 [12:18<09:17, 11.53it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  57%|▌| 8512/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  57%|▌| 8512/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -78406,8 +78269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8510/14932 [12:18<09:17, 11.53it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  57%|▌| 8510/14932 [12:18<09:17, 11.53it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  57%|▌| 8513/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  57%|▌| 8513/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -78415,8 +78278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8511/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  57%|▌| 8511/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  57%|▌| 8514/14932 [12:16<09:15, 11.55it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  57%|▌| 8514/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -78424,8 +78287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8512/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  57%|▌| 8512/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  57%|▌| 8515/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  57%|▌| 8515/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -78433,8 +78296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8513/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  57%|▌| 8513/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  57%|▌| 8516/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  57%|▌| 8516/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -78442,8 +78305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8514/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  57%|▌| 8514/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  57%|▌| 8517/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  57%|▌| 8517/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -78451,8 +78314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8515/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  57%|▌| 8515/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  57%|▌| 8518/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  57%|▌| 8518/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -78460,7 +78323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8516/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  57%|▌| 8519/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  57%|▌| 8519/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -78468,7 +78332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8516/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  57%|▌| 8520/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  57%|▌| 8520/14932 [12:17<09:15, 11.55it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -78476,8 +78341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8517/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  57%|▌| 8517/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  57%|▌| 8521/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  57%|▌| 8521/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -78485,8 +78350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8518/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  57%|▌| 8518/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  57%|▌| 8522/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  57%|▌| 8522/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -78494,8 +78359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8519/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  57%|▌| 8519/14932 [12:18<09:16, 11.53it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  57%|▌| 8523/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  57%|▌| 8523/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -78503,8 +78368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8520/14932 [12:19<09:16, 11.53it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  57%|▌| 8520/14932 [12:19<09:16, 11.53it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  57%|▌| 8524/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  57%|▌| 8524/14932 [12:17<09:14, 11.55it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -78512,8 +78377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8521/14932 [12:19<09:16, 11.53it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  57%|▌| 8521/14932 [12:19<09:16, 11.53it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  57%|▌| 8525/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  57%|▌| 8525/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=1.11"
      ]
     },
     {
@@ -78521,8 +78386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8522/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  57%|▌| 8522/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  57%|▌| 8526/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=1.11\r",
+      "Epoch 0:  57%|▌| 8526/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -78530,8 +78395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8523/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  57%|▌| 8523/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.14"
+      "Epoch 0:  57%|▌| 8527/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  57%|▌| 8527/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -78539,8 +78404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8524/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.14\r",
-      "Epoch 0:  57%|▌| 8524/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  57%|▌| 8528/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  57%|▌| 8528/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -78548,8 +78413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8525/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  57%|▌| 8525/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  57%|▌| 8529/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  57%|▌| 8529/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -78557,8 +78422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8526/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  57%|▌| 8526/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  57%|▌| 8530/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  57%|▌| 8530/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -78566,8 +78431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8527/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  57%|▌| 8527/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  57%|▌| 8531/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  57%|▌| 8531/14932 [12:18<09:14, 11.55it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -78575,8 +78440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8528/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  57%|▌| 8528/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  57%|▌| 8532/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  57%|▌| 8532/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -78584,8 +78449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8529/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  57%|▌| 8529/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  57%|▌| 8533/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  57%|▌| 8533/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=5.03"
      ]
     },
     {
@@ -78593,8 +78458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8530/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  57%|▌| 8530/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  57%|▌| 8534/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=5.03\r",
+      "Epoch 0:  57%|▌| 8534/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -78602,8 +78467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8531/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  57%|▌| 8531/14932 [12:19<09:15, 11.53it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  57%|▌| 8535/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  57%|▌| 8535/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -78611,8 +78476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8532/14932 [12:19<09:14, 11.53it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  57%|▌| 8532/14932 [12:19<09:14, 11.53it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  57%|▌| 8536/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  57%|▌| 8536/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -78620,8 +78485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8533/14932 [12:19<09:14, 11.53it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  57%|▌| 8533/14932 [12:19<09:14, 11.53it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  57%|▌| 8537/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  57%|▌| 8537/14932 [12:18<09:13, 11.55it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -78629,8 +78494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8534/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  57%|▌| 8534/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  57%|▌| 8538/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  57%|▌| 8538/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -78638,8 +78503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8535/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  57%|▌| 8535/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  57%|▌| 8539/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  57%|▌| 8539/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -78647,8 +78512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8536/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  57%|▌| 8536/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  57%|▌| 8540/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  57%|▌| 8540/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -78656,8 +78521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8537/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  57%|▌| 8537/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  57%|▌| 8541/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  57%|▌| 8541/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -78665,8 +78530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8538/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  57%|▌| 8538/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  57%|▌| 8542/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  57%|▌| 8542/14932 [12:19<09:13, 11.55it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -78674,8 +78539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8539/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  57%|▌| 8539/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  57%|▌| 8543/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  57%|▌| 8543/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -78683,8 +78548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8540/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  57%|▌| 8540/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=1.55"
+      "Epoch 0:  57%|▌| 8544/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  57%|▌| 8544/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -78692,8 +78557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8541/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=1.55\r",
-      "Epoch 0:  57%|▌| 8541/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  57%|▌| 8545/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  57%|▌| 8545/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -78701,8 +78566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8542/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  57%|▌| 8542/14932 [12:20<09:14, 11.53it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  57%|▌| 8546/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  57%|▌| 8546/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -78710,8 +78575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8543/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  57%|▌| 8543/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  57%|▌| 8547/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  57%|▌| 8547/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -78719,8 +78584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8544/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  57%|▌| 8544/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  57%|▌| 8548/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  57%|▌| 8548/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -78728,8 +78593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8545/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  57%|▌| 8545/14932 [12:20<09:13, 11.53it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  57%|▌| 8549/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  57%|▌| 8549/14932 [12:19<09:12, 11.55it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -78737,8 +78602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8546/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  57%|▌| 8546/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  57%|▌| 8550/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  57%|▌| 8550/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -78746,8 +78611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8547/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  57%|▌| 8547/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  57%|▌| 8551/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  57%|▌| 8551/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -78755,8 +78620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8548/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  57%|▌| 8548/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  57%|▌| 8552/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  57%|▌| 8552/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -78764,8 +78629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8549/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  57%|▌| 8549/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  57%|▌| 8553/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  57%|▌| 8553/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -78773,8 +78638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8550/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  57%|▌| 8550/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=1.96"
+      "Epoch 0:  57%|▌| 8554/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  57%|▌| 8554/14932 [12:20<09:12, 11.55it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -78782,8 +78647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8551/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=1.96\r",
-      "Epoch 0:  57%|▌| 8551/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  57%|▌| 8555/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  57%|▌| 8555/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -78791,8 +78656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8552/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  57%|▌| 8552/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  57%|▌| 8556/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  57%|▌| 8556/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -78800,8 +78665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8553/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  57%|▌| 8553/14932 [12:21<09:13, 11.53it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  57%|▌| 8557/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  57%|▌| 8557/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -78809,8 +78674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8554/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  57%|▌| 8554/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  57%|▌| 8558/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  57%|▌| 8558/14932 [12:20<09:11, 11.55it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -78818,8 +78683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8555/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  57%|▌| 8555/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  57%|▌| 8559/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  57%|▌| 8559/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -78827,8 +78692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8556/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  57%|▌| 8556/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  57%|▌| 8560/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  57%|▌| 8560/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -78836,8 +78701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8557/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  57%|▌| 8557/14932 [12:21<09:12, 11.53it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  57%|▌| 8561/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  57%|▌| 8561/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -78845,8 +78710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8558/14932 [12:21<09:12, 11.54it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  57%|▌| 8558/14932 [12:21<09:12, 11.54it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  57%|▌| 8562/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  57%|▌| 8562/14932 [12:20<09:11, 11.56it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -78854,8 +78719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8559/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  57%|▌| 8559/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  57%|▌| 8563/14932 [12:21<09:11, 11.56it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  57%|▌| 8563/14932 [12:21<09:11, 11.56it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -78863,8 +78728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8560/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  57%|▌| 8560/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  57%|▌| 8564/14932 [12:21<09:11, 11.56it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  57%|▌| 8564/14932 [12:21<09:11, 11.56it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -78872,8 +78737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8561/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  57%|▌| 8561/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  57%|▌| 8565/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  57%|▌| 8565/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -78881,8 +78746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8562/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  57%|▌| 8562/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  57%|▌| 8566/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  57%|▌| 8566/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -78890,8 +78755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8563/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  57%|▌| 8563/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  57%|▌| 8567/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  57%|▌| 8567/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -78899,8 +78764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8564/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  57%|▌| 8564/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  57%|▌| 8568/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  57%|▌| 8568/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -78908,8 +78773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8565/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  57%|▌| 8565/14932 [12:22<09:12, 11.53it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  57%|▌| 8569/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  57%|▌| 8569/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -78917,8 +78782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8566/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  57%|▌| 8566/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  57%|▌| 8570/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  57%|▌| 8570/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -78926,8 +78791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8567/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  57%|▌| 8567/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  57%|▌| 8571/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  57%|▌| 8571/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -78935,8 +78800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8568/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  57%|▌| 8568/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  57%|▌| 8572/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  57%|▌| 8572/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -78944,8 +78809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8569/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  57%|▌| 8569/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  57%|▌| 8573/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  57%|▌| 8573/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -78953,8 +78818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8570/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  57%|▌| 8570/14932 [12:22<09:11, 11.53it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  57%|▌| 8574/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  57%|▌| 8574/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -78962,8 +78827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8571/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  57%|▌| 8571/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  57%|▌| 8575/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  57%|▌| 8575/14932 [12:21<09:10, 11.56it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -78971,8 +78836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8572/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  57%|▌| 8572/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  57%|▌| 8576/14932 [12:22<09:10, 11.56it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  57%|▌| 8576/14932 [12:22<09:10, 11.56it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -78980,8 +78845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8573/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  57%|▌| 8573/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  57%|▌| 8577/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  57%|▌| 8577/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -78989,8 +78854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8574/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  57%|▌| 8574/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  57%|▌| 8578/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  57%|▌| 8578/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -78998,8 +78863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8575/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  57%|▌| 8575/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  57%|▌| 8579/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  57%|▌| 8579/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -79007,8 +78872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8576/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  57%|▌| 8576/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  57%|▌| 8580/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  57%|▌| 8580/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -79016,8 +78881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8577/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  57%|▌| 8577/14932 [12:23<09:11, 11.53it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  57%|▌| 8581/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  57%|▌| 8581/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=5.12"
      ]
     },
     {
@@ -79025,8 +78890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8578/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  57%|▌| 8578/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  57%|▌| 8582/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=5.12\r",
+      "Epoch 0:  57%|▌| 8582/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -79034,8 +78899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8579/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  57%|▌| 8579/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  57%|▌| 8583/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  57%|▌| 8583/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -79043,8 +78908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8580/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  57%|▌| 8580/14932 [12:23<09:10, 11.53it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  57%|▌| 8584/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  57%|▌| 8584/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -79052,8 +78917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8581/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  57%|▌| 8581/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  57%|▌| 8585/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  57%|▌| 8585/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -79061,8 +78926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8582/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  57%|▌| 8582/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  58%|▌| 8586/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  58%|▌| 8586/14932 [12:22<09:09, 11.56it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -79070,8 +78935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8583/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  57%|▌| 8583/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  58%|▌| 8587/14932 [12:23<09:09, 11.56it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  58%|▌| 8587/14932 [12:23<09:09, 11.56it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -79079,8 +78944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8584/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  57%|▌| 8584/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  58%|▌| 8588/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  58%|▌| 8588/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -79088,8 +78953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  57%|▌| 8585/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  57%|▌| 8585/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  58%|▌| 8589/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  58%|▌| 8589/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -79097,8 +78962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8586/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  58%|▌| 8586/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  58%|▌| 8590/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  58%|▌| 8590/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -79106,8 +78971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8587/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  58%|▌| 8587/14932 [12:24<09:10, 11.53it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  58%|▌| 8591/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  58%|▌| 8591/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -79115,8 +78980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8588/14932 [12:24<09:09, 11.53it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  58%|▌| 8588/14932 [12:24<09:09, 11.53it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  58%|▌| 8592/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  58%|▌| 8592/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -79124,8 +78989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8589/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  58%|▌| 8589/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  58%|▌| 8593/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  58%|▌| 8593/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -79133,8 +78998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8590/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  58%|▌| 8590/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  58%|▌| 8594/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  58%|▌| 8594/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -79142,8 +79007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8591/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  58%|▌| 8591/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  58%|▌| 8595/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  58%|▌| 8595/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -79151,8 +79016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8592/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  58%|▌| 8592/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  58%|▌| 8596/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  58%|▌| 8596/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -79160,8 +79025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8593/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  58%|▌| 8593/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  58%|▌| 8597/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  58%|▌| 8597/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -79169,8 +79034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8594/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  58%|▌| 8594/14932 [12:24<09:09, 11.54it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  58%|▌| 8598/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  58%|▌| 8598/14932 [12:23<09:08, 11.56it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -79178,8 +79043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8595/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  58%|▌| 8595/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  58%|▌| 8599/14932 [12:23<09:07, 11.56it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  58%|▌| 8599/14932 [12:23<09:07, 11.56it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -79187,8 +79052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8596/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  58%|▌| 8596/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  58%|▌| 8600/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  58%|▌| 8600/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -79196,8 +79061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8597/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  58%|▌| 8597/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  58%|▌| 8601/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  58%|▌| 8601/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -79205,8 +79070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8598/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  58%|▌| 8598/14932 [12:25<09:09, 11.54it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  58%|▌| 8602/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  58%|▌| 8602/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -79214,8 +79079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8599/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  58%|▌| 8599/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  58%|▌| 8603/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  58%|▌| 8603/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -79223,8 +79088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8600/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  58%|▌| 8600/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  58%|▌| 8604/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  58%|▌| 8604/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=1.18"
      ]
     },
     {
@@ -79232,8 +79097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8601/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  58%|▌| 8601/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  58%|▌| 8605/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=1.18\r",
+      "Epoch 0:  58%|▌| 8605/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=1.76"
      ]
     },
     {
@@ -79241,8 +79106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8602/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  58%|▌| 8602/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  58%|▌| 8606/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=1.76\r",
+      "Epoch 0:  58%|▌| 8606/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -79250,8 +79115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8603/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  58%|▌| 8603/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  58%|▌| 8607/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  58%|▌| 8607/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -79259,8 +79124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8604/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  58%|▌| 8604/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  58%|▌| 8608/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  58%|▌| 8608/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -79268,8 +79133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8605/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  58%|▌| 8605/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  58%|▌| 8609/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  58%|▌| 8609/14932 [12:24<09:07, 11.56it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -79277,8 +79142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8606/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  58%|▌| 8606/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  58%|▌| 8610/14932 [12:25<09:07, 11.56it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  58%|▌| 8610/14932 [12:25<09:07, 11.56it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -79286,8 +79151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8607/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  58%|▌| 8607/14932 [12:25<09:08, 11.54it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  58%|▌| 8611/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  58%|▌| 8611/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -79295,8 +79160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8608/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  58%|▌| 8608/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  58%|▌| 8612/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  58%|▌| 8612/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -79304,8 +79169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8609/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  58%|▌| 8609/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  58%|▌| 8613/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  58%|▌| 8613/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -79313,8 +79178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8610/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  58%|▌| 8610/14932 [12:26<09:08, 11.54it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  58%|▌| 8614/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  58%|▌| 8614/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -79322,8 +79187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8611/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  58%|▌| 8611/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  58%|▌| 8615/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  58%|▌| 8615/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -79331,8 +79196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8612/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  58%|▌| 8612/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  58%|▌| 8616/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  58%|▌| 8616/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -79340,8 +79205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8613/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  58%|▌| 8613/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  58%|▌| 8617/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  58%|▌| 8617/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -79349,8 +79214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8614/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  58%|▌| 8614/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  58%|▌| 8618/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  58%|▌| 8618/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -79358,8 +79223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8615/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  58%|▌| 8615/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  58%|▌| 8619/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  58%|▌| 8619/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -79367,8 +79232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8616/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  58%|▌| 8616/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  58%|▌| 8620/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  58%|▌| 8620/14932 [12:25<09:06, 11.56it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -79376,8 +79241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8617/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  58%|▌| 8617/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  58%|▌| 8621/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  58%|▌| 8621/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -79385,8 +79250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8618/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  58%|▌| 8618/14932 [12:26<09:07, 11.54it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  58%|▌| 8622/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  58%|▌| 8622/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -79394,8 +79259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8619/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  58%|▌| 8619/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  58%|▌| 8623/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  58%|▌| 8623/14932 [12:25<09:05, 11.56it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -79403,8 +79268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8620/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  58%|▌| 8620/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  58%|▌| 8624/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  58%|▌| 8624/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -79412,8 +79277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8621/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  58%|▌| 8621/14932 [12:27<09:07, 11.54it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  58%|▌| 8625/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  58%|▌| 8625/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -79421,8 +79286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8622/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  58%|▌| 8622/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  58%|▌| 8626/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  58%|▌| 8626/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -79430,7 +79295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8623/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  58%|▌| 8627/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  58%|▌| 8627/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -79438,7 +79304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8623/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  58%|▌| 8628/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  58%|▌| 8628/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -79446,8 +79313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8624/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  58%|▌| 8624/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  58%|▌| 8629/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  58%|▌| 8629/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -79455,8 +79322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8625/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  58%|▌| 8625/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  58%|▌| 8630/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  58%|▌| 8630/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -79464,8 +79331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8626/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  58%|▌| 8626/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  58%|▌| 8631/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  58%|▌| 8631/14932 [12:26<09:05, 11.56it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -79473,8 +79340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8627/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  58%|▌| 8627/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  58%|▌| 8632/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  58%|▌| 8632/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -79482,8 +79349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8628/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  58%|▌| 8628/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  58%|▌| 8633/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  58%|▌| 8633/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -79491,8 +79358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8629/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  58%|▌| 8629/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  58%|▌| 8634/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  58%|▌| 8634/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -79500,8 +79367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8630/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  58%|▌| 8630/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  58%|▌| 8635/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  58%|▌| 8635/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -79509,8 +79376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8631/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  58%|▌| 8631/14932 [12:27<09:06, 11.54it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  58%|▌| 8636/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  58%|▌| 8636/14932 [12:26<09:04, 11.56it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -79518,8 +79385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8632/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  58%|▌| 8632/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  58%|▌| 8637/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  58%|▌| 8637/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -79527,8 +79394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8633/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  58%|▌| 8633/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  58%|▌| 8638/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  58%|▌| 8638/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -79536,8 +79403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8634/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  58%|▌| 8634/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  58%|▌| 8639/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  58%|▌| 8639/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -79545,8 +79412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8635/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  58%|▌| 8635/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  58%|▌| 8640/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  58%|▌| 8640/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -79554,8 +79421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8636/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  58%|▌| 8636/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  58%|▌| 8641/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  58%|▌| 8641/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -79563,8 +79430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8637/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  58%|▌| 8637/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  58%|▌| 8642/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  58%|▌| 8642/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -79572,8 +79439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8638/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  58%|▌| 8638/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  58%|▌| 8643/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  58%|▌| 8643/14932 [12:27<09:04, 11.56it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -79581,8 +79448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8639/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  58%|▌| 8639/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  58%|▌| 8644/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  58%|▌| 8644/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -79590,8 +79457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8640/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  58%|▌| 8640/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  58%|▌| 8645/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  58%|▌| 8645/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -79599,8 +79466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8641/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  58%|▌| 8641/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  58%|▌| 8646/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  58%|▌| 8646/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -79608,8 +79475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8642/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  58%|▌| 8642/14932 [12:28<09:05, 11.54it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  58%|▌| 8647/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  58%|▌| 8647/14932 [12:27<09:03, 11.56it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -79617,8 +79484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8643/14932 [12:29<09:05, 11.54it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  58%|▌| 8643/14932 [12:29<09:05, 11.54it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  58%|▌| 8648/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  58%|▌| 8648/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -79626,8 +79493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8644/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  58%|▌| 8644/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  58%|▌| 8649/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  58%|▌| 8649/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -79635,8 +79502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8645/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  58%|▌| 8645/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  58%|▌| 8650/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  58%|▌| 8650/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -79644,8 +79511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8646/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  58%|▌| 8646/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  58%|▌| 8651/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  58%|▌| 8651/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -79653,8 +79520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8647/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  58%|▌| 8647/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  58%|▌| 8652/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  58%|▌| 8652/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -79662,8 +79529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8648/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  58%|▌| 8648/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  58%|▌| 8653/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  58%|▌| 8653/14932 [12:28<09:03, 11.56it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -79671,8 +79538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8649/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  58%|▌| 8649/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  58%|▌| 8654/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  58%|▌| 8654/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -79680,8 +79547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8650/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  58%|▌| 8650/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  58%|▌| 8655/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  58%|▌| 8655/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -79689,8 +79556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8651/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  58%|▌| 8651/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  58%|▌| 8656/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  58%|▌| 8656/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -79698,8 +79565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8652/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  58%|▌| 8652/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  58%|▌| 8657/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  58%|▌| 8657/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -79707,8 +79574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8653/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  58%|▌| 8653/14932 [12:29<09:04, 11.54it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  58%|▌| 8658/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  58%|▌| 8658/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -79716,8 +79583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8654/14932 [12:29<09:03, 11.54it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  58%|▌| 8654/14932 [12:29<09:03, 11.54it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  58%|▌| 8659/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  58%|▌| 8659/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -79725,8 +79592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8655/14932 [12:29<09:03, 11.54it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  58%|▌| 8655/14932 [12:29<09:03, 11.54it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  58%|▌| 8660/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  58%|▌| 8660/14932 [12:28<09:02, 11.56it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -79734,8 +79601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8656/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  58%|▌| 8656/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  58%|▌| 8661/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  58%|▌| 8661/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -79743,8 +79610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8657/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  58%|▌| 8657/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  58%|▌| 8662/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  58%|▌| 8662/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -79752,8 +79619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8658/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  58%|▌| 8658/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  58%|▌| 8663/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  58%|▌| 8663/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -79761,8 +79628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8659/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  58%|▌| 8659/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  58%|▌| 8664/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  58%|▌| 8664/14932 [12:29<09:02, 11.56it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -79770,8 +79637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8660/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  58%|▌| 8660/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  58%|▌| 8665/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  58%|▌| 8665/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -79779,8 +79646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8661/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  58%|▌| 8661/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  58%|▌| 8666/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  58%|▌| 8666/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -79788,8 +79655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8662/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  58%|▌| 8662/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  58%|▌| 8667/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  58%|▌| 8667/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -79797,8 +79664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8663/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  58%|▌| 8663/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  58%|▌| 8668/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  58%|▌| 8668/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -79806,8 +79673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8664/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  58%|▌| 8664/14932 [12:30<09:03, 11.54it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  58%|▌| 8669/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  58%|▌| 8669/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -79815,8 +79682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8665/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  58%|▌| 8665/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  58%|▌| 8670/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  58%|▌| 8670/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -79824,8 +79691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8666/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  58%|▌| 8666/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  58%|▌| 8671/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  58%|▌| 8671/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -79833,8 +79700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8667/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  58%|▌| 8667/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  58%|▌| 8672/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  58%|▌| 8672/14932 [12:29<09:01, 11.56it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -79842,8 +79709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8668/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  58%|▌| 8668/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  58%|▌| 8673/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  58%|▌| 8673/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -79851,8 +79718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8669/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  58%|▌| 8669/14932 [12:30<09:02, 11.54it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  58%|▌| 8674/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  58%|▌| 8674/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -79860,8 +79727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8670/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  58%|▌| 8670/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  58%|▌| 8675/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  58%|▌| 8675/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -79869,8 +79736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8671/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  58%|▌| 8671/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  58%|▌| 8676/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  58%|▌| 8676/14932 [12:30<09:01, 11.56it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -79878,8 +79745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8672/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  58%|▌| 8672/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  58%|▌| 8677/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  58%|▌| 8677/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=0.84"
      ]
     },
     {
@@ -79887,8 +79754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8673/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  58%|▌| 8673/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=0.78"
+      "Epoch 0:  58%|▌| 8678/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=0.84\r",
+      "Epoch 0:  58%|▌| 8678/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -79896,8 +79763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8674/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=0.78\r",
-      "Epoch 0:  58%|▌| 8674/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  58%|▌| 8679/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  58%|▌| 8679/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -79905,8 +79772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8675/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  58%|▌| 8675/14932 [12:31<09:02, 11.54it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  58%|▌| 8680/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  58%|▌| 8680/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -79914,8 +79781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8676/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  58%|▌| 8676/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  58%|▌| 8681/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  58%|▌| 8681/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -79923,8 +79790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8677/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  58%|▌| 8677/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  58%|▌| 8682/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  58%|▌| 8682/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -79932,8 +79799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8678/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  58%|▌| 8678/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  58%|▌| 8683/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  58%|▌| 8683/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -79941,8 +79808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8679/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  58%|▌| 8679/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  58%|▌| 8684/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  58%|▌| 8684/14932 [12:30<09:00, 11.56it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -79950,8 +79817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8680/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  58%|▌| 8680/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  58%|▌| 8685/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  58%|▌| 8685/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -79959,8 +79826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8681/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  58%|▌| 8681/14932 [12:31<09:01, 11.54it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  58%|▌| 8686/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  58%|▌| 8686/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -79968,8 +79835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8682/14932 [12:32<09:01, 11.54it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  58%|▌| 8682/14932 [12:32<09:01, 11.54it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  58%|▌| 8687/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  58%|▌| 8687/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -79977,8 +79844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8683/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  58%|▌| 8683/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  58%|▌| 8688/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  58%|▌| 8688/14932 [12:31<09:00, 11.56it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -79986,8 +79853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8684/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  58%|▌| 8684/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  58%|▌| 8689/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  58%|▌| 8689/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -79995,8 +79862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8685/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  58%|▌| 8685/14932 [12:32<09:01, 11.55it/s, v_num=o30c, train/loss=0.90"
+      "Epoch 0:  58%|▌| 8690/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  58%|▌| 8690/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -80004,8 +79871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8686/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=0.90\r",
-      "Epoch 0:  58%|▌| 8686/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  58%|▌| 8691/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  58%|▌| 8691/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -80013,8 +79880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8687/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  58%|▌| 8687/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  58%|▌| 8692/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  58%|▌| 8692/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -80022,8 +79889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8688/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  58%|▌| 8688/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  58%|▌| 8693/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  58%|▌| 8693/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -80031,8 +79898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8689/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  58%|▌| 8689/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  58%|▌| 8694/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  58%|▌| 8694/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -80040,8 +79907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8690/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  58%|▌| 8690/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  58%|▌| 8695/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  58%|▌| 8695/14932 [12:31<08:59, 11.56it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -80049,8 +79916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8691/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  58%|▌| 8691/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  58%|▌| 8696/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  58%|▌| 8696/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -80058,8 +79925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8692/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  58%|▌| 8692/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  58%|▌| 8697/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  58%|▌| 8697/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -80067,8 +79934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8693/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  58%|▌| 8693/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  58%|▌| 8698/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  58%|▌| 8698/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -80076,8 +79943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8694/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  58%|▌| 8694/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  58%|▌| 8699/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  58%|▌| 8699/14932 [12:32<08:59, 11.56it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -80085,8 +79952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8695/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  58%|▌| 8695/14932 [12:32<09:00, 11.55it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  58%|▌| 8700/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  58%|▌| 8700/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -80094,8 +79961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8696/14932 [12:33<09:00, 11.55it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  58%|▌| 8696/14932 [12:33<09:00, 11.55it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  58%|▌| 8701/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  58%|▌| 8701/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -80103,8 +79970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8697/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  58%|▌| 8697/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  58%|▌| 8702/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  58%|▌| 8702/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -80112,8 +79979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8698/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  58%|▌| 8698/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  58%|▌| 8703/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  58%|▌| 8703/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -80121,8 +79988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8699/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  58%|▌| 8699/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  58%|▌| 8704/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  58%|▌| 8704/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -80130,8 +79997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8700/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  58%|▌| 8700/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  58%|▌| 8705/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  58%|▌| 8705/14932 [12:32<08:58, 11.56it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -80139,8 +80006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8701/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  58%|▌| 8701/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  58%|▌| 8706/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  58%|▌| 8706/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -80148,8 +80015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8702/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  58%|▌| 8702/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  58%|▌| 8707/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  58%|▌| 8707/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -80157,8 +80024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8703/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  58%|▌| 8703/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=1.05"
+      "Epoch 0:  58%|▌| 8708/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  58%|▌| 8708/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -80166,8 +80033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8704/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=1.05\r",
-      "Epoch 0:  58%|▌| 8704/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  58%|▌| 8709/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  58%|▌| 8709/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -80175,8 +80042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8705/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  58%|▌| 8705/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  58%|▌| 8710/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  58%|▌| 8710/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -80184,8 +80051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8706/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  58%|▌| 8706/14932 [12:33<08:59, 11.55it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  58%|▌| 8711/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  58%|▌| 8711/14932 [12:33<08:58, 11.56it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -80193,8 +80060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8707/14932 [12:34<08:59, 11.55it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  58%|▌| 8707/14932 [12:34<08:59, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  58%|▌| 8712/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  58%|▌| 8712/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -80202,8 +80069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8708/14932 [12:34<08:59, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  58%|▌| 8708/14932 [12:34<08:59, 11.55it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  58%|▌| 8713/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  58%|▌| 8713/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -80211,8 +80078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8709/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  58%|▌| 8709/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  58%|▌| 8714/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  58%|▌| 8714/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -80220,8 +80087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8710/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  58%|▌| 8710/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  58%|▌| 8715/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  58%|▌| 8715/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -80229,8 +80096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8711/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  58%|▌| 8711/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  58%|▌| 8716/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  58%|▌| 8716/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -80238,8 +80105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8712/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  58%|▌| 8712/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  58%|▌| 8717/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  58%|▌| 8717/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -80247,8 +80114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8713/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  58%|▌| 8713/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  58%|▌| 8718/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  58%|▌| 8718/14932 [12:33<08:57, 11.56it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -80256,8 +80123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8714/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  58%|▌| 8714/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  58%|▌| 8719/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  58%|▌| 8719/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -80265,8 +80132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8715/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  58%|▌| 8715/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  58%|▌| 8720/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  58%|▌| 8720/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -80274,8 +80141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8716/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  58%|▌| 8716/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  58%|▌| 8721/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  58%|▌| 8721/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -80283,8 +80150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8717/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  58%|▌| 8717/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  58%|▌| 8722/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  58%|▌| 8722/14932 [12:34<08:57, 11.56it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -80292,8 +80159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8718/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  58%|▌| 8718/14932 [12:34<08:58, 11.55it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  58%|▌| 8723/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  58%|▌| 8723/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=0.78"
      ]
     },
     {
@@ -80301,8 +80168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8719/14932 [12:34<08:57, 11.55it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  58%|▌| 8719/14932 [12:34<08:57, 11.55it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  58%|▌| 8724/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=0.78\r",
+      "Epoch 0:  58%|▌| 8724/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -80310,8 +80177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8720/14932 [12:34<08:57, 11.55it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  58%|▌| 8720/14932 [12:34<08:57, 11.55it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  58%|▌| 8725/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  58%|▌| 8725/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -80319,8 +80186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8721/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  58%|▌| 8721/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  58%|▌| 8726/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  58%|▌| 8726/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -80328,8 +80195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8722/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  58%|▌| 8722/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  58%|▌| 8727/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  58%|▌| 8727/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -80337,8 +80204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8723/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  58%|▌| 8723/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  58%|▌| 8728/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  58%|▌| 8728/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -80346,8 +80213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8724/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  58%|▌| 8724/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  58%|▌| 8729/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  58%|▌| 8729/14932 [12:34<08:56, 11.56it/s, v_num=ui8w, train/loss=1.46"
      ]
     },
     {
@@ -80355,8 +80222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8725/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  58%|▌| 8725/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  58%|▌| 8730/14932 [12:34<08:56, 11.57it/s, v_num=ui8w, train/loss=1.46\r",
+      "Epoch 0:  58%|▌| 8730/14932 [12:34<08:56, 11.57it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -80364,8 +80231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8726/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  58%|▌| 8726/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  58%|▌| 8731/14932 [12:34<08:56, 11.57it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  58%|▌| 8731/14932 [12:34<08:56, 11.57it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -80373,8 +80240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8727/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  58%|▌| 8727/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=1.86"
+      "Epoch 0:  58%|▌| 8732/14932 [12:35<08:56, 11.56it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  58%|▌| 8732/14932 [12:35<08:56, 11.56it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -80382,8 +80249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8728/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=1.86\r",
-      "Epoch 0:  58%|▌| 8728/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  58%|▌| 8733/14932 [12:35<08:56, 11.56it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  58%|▌| 8733/14932 [12:35<08:56, 11.56it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -80391,8 +80258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8729/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  58%|▌| 8729/14932 [12:35<08:57, 11.55it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  58%|▌| 8734/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  58%|▌| 8734/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -80400,8 +80267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8730/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  58%|▌| 8730/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  58%|▌| 8735/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  58%|▌| 8735/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -80409,8 +80276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8731/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  58%|▌| 8731/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  59%|▌| 8736/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  59%|▌| 8736/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -80418,8 +80285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8732/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  58%|▌| 8732/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  59%|▌| 8737/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  59%|▌| 8737/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -80427,8 +80294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8733/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  58%|▌| 8733/14932 [12:35<08:56, 11.55it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  59%|▌| 8738/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  59%|▌| 8738/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=1.85"
      ]
     },
     {
@@ -80436,8 +80303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8734/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  58%|▌| 8734/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  59%|▌| 8739/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=1.85\r",
+      "Epoch 0:  59%|▌| 8739/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -80445,8 +80312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  58%|▌| 8735/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  58%|▌| 8735/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  59%|▌| 8740/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  59%|▌| 8740/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -80454,8 +80321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8736/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  59%|▌| 8736/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  59%|▌| 8741/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  59%|▌| 8741/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -80463,8 +80330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8737/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  59%|▌| 8737/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  59%|▌| 8742/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  59%|▌| 8742/14932 [12:35<08:55, 11.56it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -80472,8 +80339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8738/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  59%|▌| 8738/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  59%|▌| 8743/14932 [12:36<08:55, 11.56it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  59%|▌| 8743/14932 [12:36<08:55, 11.56it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -80481,8 +80348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8739/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  59%|▌| 8739/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  59%|▌| 8744/14932 [12:36<08:55, 11.56it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:  59%|▌| 8744/14932 [12:36<08:55, 11.56it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -80490,8 +80357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8740/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  59%|▌| 8740/14932 [12:36<08:56, 11.55it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  59%|▌| 8745/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  59%|▌| 8745/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -80499,8 +80366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8741/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  59%|▌| 8741/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  59%|▌| 8746/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  59%|▌| 8746/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -80508,8 +80375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8742/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  59%|▌| 8742/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  59%|▌| 8747/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  59%|▌| 8747/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -80517,8 +80384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8743/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  59%|▌| 8743/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  59%|▌| 8748/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  59%|▌| 8748/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -80526,8 +80393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8744/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  59%|▌| 8744/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  59%|▌| 8749/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  59%|▌| 8749/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -80535,8 +80402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8745/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  59%|▌| 8745/14932 [12:36<08:55, 11.55it/s, v_num=o30c, train/loss=1.48"
+      "Epoch 0:  59%|▌| 8750/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  59%|▌| 8750/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -80544,8 +80411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8746/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=1.48\r",
-      "Epoch 0:  59%|▌| 8746/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  59%|▌| 8751/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  59%|▌| 8751/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -80553,8 +80420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8747/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  59%|▌| 8747/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  59%|▌| 8752/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  59%|▌| 8752/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -80562,8 +80429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8748/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  59%|▌| 8748/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  59%|▌| 8753/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  59%|▌| 8753/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -80571,8 +80438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8749/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  59%|▌| 8749/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  59%|▌| 8754/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  59%|▌| 8754/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -80580,8 +80447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8750/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  59%|▌| 8750/14932 [12:37<08:55, 11.55it/s, v_num=o30c, train/loss=1.39"
+      "Epoch 0:  59%|▌| 8755/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  59%|▌| 8755/14932 [12:36<08:54, 11.57it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -80589,8 +80456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8751/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=1.39\r",
-      "Epoch 0:  59%|▌| 8751/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  59%|▌| 8756/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  59%|▌| 8756/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -80598,8 +80465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8752/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  59%|▌| 8752/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  59%|▌| 8757/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  59%|▌| 8757/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -80607,8 +80474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8753/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  59%|▌| 8753/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=1.73"
+      "Epoch 0:  59%|▌| 8758/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  59%|▌| 8758/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -80616,8 +80483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8754/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=1.73\r",
-      "Epoch 0:  59%|▌| 8754/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  59%|▌| 8759/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  59%|▌| 8759/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -80625,8 +80492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8755/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  59%|▌| 8755/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  59%|▌| 8760/14932 [12:37<08:53, 11.56it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  59%|▌| 8760/14932 [12:37<08:53, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -80634,8 +80501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8756/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  59%|▌| 8756/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  59%|▌| 8761/14932 [12:37<08:53, 11.56it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  59%|▌| 8761/14932 [12:37<08:53, 11.56it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -80643,8 +80510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8757/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  59%|▌| 8757/14932 [12:37<08:54, 11.55it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  59%|▌| 8762/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  59%|▌| 8762/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -80652,8 +80519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8758/14932 [12:37<08:54, 11.56it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  59%|▌| 8758/14932 [12:37<08:54, 11.56it/s, v_num=o30c, train/loss=1.68"
+      "Epoch 0:  59%|▌| 8763/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  59%|▌| 8763/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -80661,8 +80528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8759/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=1.68\r",
-      "Epoch 0:  59%|▌| 8759/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  59%|▌| 8764/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  59%|▌| 8764/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -80670,8 +80537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8760/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  59%|▌| 8760/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  59%|▌| 8765/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  59%|▌| 8765/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -80679,8 +80546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8761/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  59%|▌| 8761/14932 [12:38<08:54, 11.56it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  59%|▌| 8766/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  59%|▌| 8766/14932 [12:37<08:53, 11.57it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -80688,8 +80555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8762/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  59%|▌| 8762/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=0.98"
+      "Epoch 0:  59%|▌| 8767/14932 [12:38<08:53, 11.57it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  59%|▌| 8767/14932 [12:38<08:53, 11.57it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -80697,8 +80564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8763/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=0.98\r",
-      "Epoch 0:  59%|▌| 8763/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  59%|▌| 8768/14932 [12:38<08:53, 11.56it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  59%|▌| 8768/14932 [12:38<08:53, 11.56it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -80706,8 +80573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8764/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  59%|▌| 8764/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  59%|▌| 8769/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  59%|▌| 8769/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -80715,8 +80582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8765/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  59%|▌| 8765/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  59%|▌| 8770/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  59%|▌| 8770/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -80724,8 +80591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8766/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  59%|▌| 8766/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  59%|▌| 8771/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  59%|▌| 8771/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -80733,8 +80600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8767/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  59%|▌| 8767/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  59%|▌| 8772/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  59%|▌| 8772/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -80742,8 +80609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8768/14932 [12:38<08:53, 11.55it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  59%|▌| 8768/14932 [12:38<08:53, 11.55it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  59%|▌| 8773/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  59%|▌| 8773/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -80751,8 +80618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8769/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  59%|▌| 8769/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  59%|▌| 8774/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  59%|▌| 8774/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -80760,8 +80627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8770/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  59%|▌| 8770/14932 [12:38<08:53, 11.56it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  59%|▌| 8775/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  59%|▌| 8775/14932 [12:38<08:52, 11.56it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -80769,8 +80636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8771/14932 [12:39<08:53, 11.56it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  59%|▌| 8771/14932 [12:39<08:53, 11.56it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  59%|▌| 8776/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  59%|▌| 8776/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -80778,8 +80645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8772/14932 [12:39<08:53, 11.56it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  59%|▌| 8772/14932 [12:39<08:53, 11.56it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  59%|▌| 8777/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  59%|▌| 8777/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -80787,8 +80654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8773/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  59%|▌| 8773/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  59%|▌| 8778/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  59%|▌| 8778/14932 [12:38<08:52, 11.57it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -80796,8 +80663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8774/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  59%|▌| 8774/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  59%|▌| 8779/14932 [12:39<08:52, 11.57it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  59%|▌| 8779/14932 [12:39<08:52, 11.57it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -80805,8 +80672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8775/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  59%|▌| 8775/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  59%|▌| 8780/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  59%|▌| 8780/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -80814,8 +80681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8776/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  59%|▌| 8776/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  59%|▌| 8781/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  59%|▌| 8781/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -80823,8 +80690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8777/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  59%|▌| 8777/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  59%|▌| 8782/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  59%|▌| 8782/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -80832,8 +80699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8778/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  59%|▌| 8778/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  59%|▌| 8783/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  59%|▌| 8783/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -80841,8 +80708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8779/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  59%|▌| 8779/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  59%|▌| 8784/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  59%|▌| 8784/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -80850,8 +80717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8780/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  59%|▌| 8780/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  59%|▌| 8785/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  59%|▌| 8785/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -80859,8 +80726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8781/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  59%|▌| 8781/14932 [12:39<08:52, 11.56it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  59%|▌| 8786/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  59%|▌| 8786/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -80868,8 +80735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8782/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  59%|▌| 8782/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  59%|▌| 8787/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  59%|▌| 8787/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -80877,8 +80744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8783/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  59%|▌| 8783/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=4.66"
+      "Epoch 0:  59%|▌| 8788/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  59%|▌| 8788/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -80886,8 +80753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8784/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=4.66\r",
-      "Epoch 0:  59%|▌| 8784/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  59%|▌| 8789/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  59%|▌| 8789/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=1.36"
      ]
     },
     {
@@ -80895,8 +80762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8785/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  59%|▌| 8785/14932 [12:40<08:52, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  59%|▌| 8790/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=1.36\r",
+      "Epoch 0:  59%|▌| 8790/14932 [12:39<08:51, 11.57it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -80904,8 +80771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8786/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  59%|▌| 8786/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  59%|▌| 8791/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  59%|▌| 8791/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -80913,8 +80780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8787/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  59%|▌| 8787/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  59%|▌| 8792/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  59%|▌| 8792/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -80922,8 +80789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8788/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  59%|▌| 8788/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  59%|▌| 8793/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  59%|▌| 8793/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -80931,8 +80798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8789/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  59%|▌| 8789/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  59%|▌| 8794/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  59%|▌| 8794/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -80940,8 +80807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8790/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  59%|▌| 8790/14932 [12:40<08:51, 11.55it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  59%|▌| 8795/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  59%|▌| 8795/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -80949,8 +80816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8791/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  59%|▌| 8791/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  59%|▌| 8796/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  59%|▌| 8796/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -80958,8 +80825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8792/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  59%|▌| 8792/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  59%|▌| 8797/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  59%|▌| 8797/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -80967,8 +80834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8793/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  59%|▌| 8793/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  59%|▌| 8798/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  59%|▌| 8798/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -80976,8 +80843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8794/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  59%|▌| 8794/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=0.77"
+      "Epoch 0:  59%|▌| 8799/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  59%|▌| 8799/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -80985,8 +80852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8795/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=0.77\r",
-      "Epoch 0:  59%|▌| 8795/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  59%|▌| 8800/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  59%|▌| 8800/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -80994,8 +80861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8796/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  59%|▌| 8796/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  59%|▌| 8801/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  59%|▌| 8801/14932 [12:40<08:50, 11.57it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -81003,8 +80870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8797/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  59%|▌| 8797/14932 [12:41<08:51, 11.55it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  59%|▌| 8802/14932 [12:40<08:49, 11.57it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  59%|▌| 8802/14932 [12:40<08:49, 11.57it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -81012,8 +80879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8798/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  59%|▌| 8798/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  59%|▌| 8803/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  59%|▌| 8803/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -81021,8 +80888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8799/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  59%|▌| 8799/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  59%|▌| 8804/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  59%|▌| 8804/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -81030,8 +80897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8800/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  59%|▌| 8800/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  59%|▌| 8805/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  59%|▌| 8805/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -81039,8 +80906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8801/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  59%|▌| 8801/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  59%|▌| 8806/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  59%|▌| 8806/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -81048,8 +80915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8802/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  59%|▌| 8802/14932 [12:41<08:50, 11.55it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  59%|▌| 8807/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  59%|▌| 8807/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -81057,8 +80924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8803/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  59%|▌| 8803/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  59%|▌| 8808/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  59%|▌| 8808/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -81066,8 +80933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8804/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  59%|▌| 8804/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  59%|▌| 8809/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  59%|▌| 8809/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -81075,8 +80942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8805/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  59%|▌| 8805/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  59%|▌| 8810/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  59%|▌| 8810/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -81084,8 +80951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8806/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  59%|▌| 8806/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  59%|▌| 8811/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  59%|▌| 8811/14932 [12:41<08:49, 11.57it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -81093,8 +80960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8807/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  59%|▌| 8807/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=0.76"
+      "Epoch 0:  59%|▌| 8812/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  59%|▌| 8812/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -81102,8 +80969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8808/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=0.76\r",
-      "Epoch 0:  59%|▌| 8808/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  59%|▌| 8813/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  59%|▌| 8813/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=5.38"
      ]
     },
     {
@@ -81111,8 +80978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8809/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  59%|▌| 8809/14932 [12:42<08:50, 11.55it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  59%|▌| 8814/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=5.38\r",
+      "Epoch 0:  59%|▌| 8814/14932 [12:42<08:49, 11.56it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -81120,8 +80987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8810/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  59%|▌| 8810/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  59%|▌| 8815/14932 [12:42<08:48, 11.56it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  59%|▌| 8815/14932 [12:42<08:48, 11.56it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -81129,8 +80996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8811/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  59%|▌| 8811/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  59%|▌| 8816/14932 [12:42<08:48, 11.56it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  59%|▌| 8816/14932 [12:42<08:48, 11.56it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -81138,8 +81005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8812/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  59%|▌| 8812/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  59%|▌| 8817/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  59%|▌| 8817/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -81147,8 +81014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8813/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  59%|▌| 8813/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  59%|▌| 8818/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  59%|▌| 8818/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -81156,8 +81023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8814/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  59%|▌| 8814/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  59%|▌| 8819/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  59%|▌| 8819/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.68"
      ]
     },
     {
@@ -81165,8 +81032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8815/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  59%|▌| 8815/14932 [12:42<08:49, 11.55it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  59%|▌| 8820/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.68\r",
+      "Epoch 0:  59%|▌| 8820/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.02"
      ]
     },
     {
@@ -81174,8 +81041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8816/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  59%|▌| 8816/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  59%|▌| 8821/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.02\r",
+      "Epoch 0:  59%|▌| 8821/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -81183,8 +81050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8817/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  59%|▌| 8817/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  59%|▌| 8822/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  59%|▌| 8822/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -81192,8 +81059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8818/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  59%|▌| 8818/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  59%|▌| 8823/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  59%|▌| 8823/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -81201,8 +81068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8819/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  59%|▌| 8819/14932 [12:43<08:49, 11.55it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  59%|▌| 8824/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  59%|▌| 8824/14932 [12:42<08:48, 11.57it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -81210,8 +81077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8820/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  59%|▌| 8820/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  59%|▌| 8825/14932 [12:43<08:48, 11.57it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  59%|▌| 8825/14932 [12:43<08:48, 11.57it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -81219,8 +81086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8821/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  59%|▌| 8821/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  59%|▌| 8826/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  59%|▌| 8826/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -81228,8 +81095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8822/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  59%|▌| 8822/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  59%|▌| 8827/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  59%|▌| 8827/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -81237,8 +81104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8823/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  59%|▌| 8823/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  59%|▌| 8828/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  59%|▌| 8828/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -81246,8 +81113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8824/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  59%|▌| 8824/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=1.61"
+      "Epoch 0:  59%|▌| 8829/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  59%|▌| 8829/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -81255,8 +81122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8825/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=1.61\r",
-      "Epoch 0:  59%|▌| 8825/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  59%|▌| 8830/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  59%|▌| 8830/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -81264,8 +81131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8826/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=4.84\r",
-      "Epoch 0:  59%|▌| 8826/14932 [12:43<08:48, 11.55it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  59%|▌| 8831/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  59%|▌| 8831/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=1.38"
      ]
     },
     {
@@ -81273,8 +81140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8827/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  59%|▌| 8827/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  59%|▌| 8832/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=1.38\r",
+      "Epoch 0:  59%|▌| 8832/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -81282,8 +81149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8828/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  59%|▌| 8828/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  59%|▌| 8833/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  59%|▌| 8833/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -81291,8 +81158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8829/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  59%|▌| 8829/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  59%|▌| 8834/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  59%|▌| 8834/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=4.75"
      ]
     },
     {
@@ -81300,8 +81167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8830/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  59%|▌| 8830/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  59%|▌| 8835/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=4.75\r",
+      "Epoch 0:  59%|▌| 8835/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -81309,8 +81176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8831/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  59%|▌| 8831/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  59%|▌| 8836/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  59%|▌| 8836/14932 [12:43<08:47, 11.57it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -81318,8 +81185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8832/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  59%|▌| 8832/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  59%|▌| 8837/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  59%|▌| 8837/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -81327,8 +81194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8833/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  59%|▌| 8833/14932 [12:44<08:48, 11.55it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  59%|▌| 8838/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  59%|▌| 8838/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -81336,8 +81203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8834/14932 [12:44<08:47, 11.55it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  59%|▌| 8834/14932 [12:44<08:47, 11.55it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  59%|▌| 8839/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  59%|▌| 8839/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -81345,8 +81212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8835/14932 [12:44<08:47, 11.55it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  59%|▌| 8835/14932 [12:44<08:47, 11.55it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  59%|▌| 8840/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  59%|▌| 8840/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -81354,8 +81221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8836/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  59%|▌| 8836/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  59%|▌| 8841/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  59%|▌| 8841/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -81363,8 +81230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8837/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  59%|▌| 8837/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  59%|▌| 8842/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  59%|▌| 8842/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -81372,8 +81239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8838/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  59%|▌| 8838/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  59%|▌| 8843/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  59%|▌| 8843/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -81381,8 +81248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8839/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  59%|▌| 8839/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  59%|▌| 8844/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  59%|▌| 8844/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -81390,8 +81257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8840/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  59%|▌| 8840/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  59%|▌| 8845/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  59%|▌| 8845/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -81399,8 +81266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8841/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  59%|▌| 8841/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  59%|▌| 8846/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  59%|▌| 8846/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -81408,8 +81275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8842/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  59%|▌| 8842/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  59%|▌| 8847/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  59%|▌| 8847/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -81417,8 +81284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8843/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  59%|▌| 8843/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  59%|▌| 8848/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  59%|▌| 8848/14932 [12:44<08:46, 11.57it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -81426,8 +81293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8844/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  59%|▌| 8844/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  59%|▌| 8849/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  59%|▌| 8849/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -81435,8 +81302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8845/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  59%|▌| 8845/14932 [12:45<08:47, 11.55it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  59%|▌| 8850/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  59%|▌| 8850/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -81444,8 +81311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8846/14932 [12:45<08:46, 11.55it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  59%|▌| 8846/14932 [12:45<08:46, 11.55it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  59%|▌| 8851/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  59%|▌| 8851/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -81453,8 +81320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8847/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  59%|▌| 8847/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  59%|▌| 8852/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  59%|▌| 8852/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -81462,8 +81329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8848/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  59%|▌| 8848/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=0.93"
+      "Epoch 0:  59%|▌| 8853/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  59%|▌| 8853/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -81471,8 +81338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8849/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=0.93\r",
-      "Epoch 0:  59%|▌| 8849/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  59%|▌| 8854/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  59%|▌| 8854/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -81480,8 +81347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8850/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  59%|▌| 8850/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  59%|▌| 8855/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  59%|▌| 8855/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -81489,7 +81356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8851/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  59%|▌| 8856/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  59%|▌| 8856/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -81497,7 +81365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8851/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  59%|▌| 8857/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  59%|▌| 8857/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -81505,8 +81374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8852/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  59%|▌| 8852/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  59%|▌| 8858/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  59%|▌| 8858/14932 [12:45<08:45, 11.57it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -81514,8 +81383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8853/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  59%|▌| 8853/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  59%|▌| 8859/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  59%|▌| 8859/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -81523,8 +81392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8854/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  59%|▌| 8854/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  59%|▌| 8860/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  59%|▌| 8860/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -81532,8 +81401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8855/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  59%|▌| 8855/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  59%|▌| 8861/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  59%|▌| 8861/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -81541,8 +81410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8856/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  59%|▌| 8856/14932 [12:46<08:46, 11.55it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  59%|▌| 8862/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  59%|▌| 8862/14932 [12:45<08:44, 11.57it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -81550,8 +81419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8857/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  59%|▌| 8857/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  59%|▌| 8863/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  59%|▌| 8863/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -81559,8 +81428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8858/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  59%|▌| 8858/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  59%|▌| 8864/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  59%|▌| 8864/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -81568,8 +81437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8859/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  59%|▌| 8859/14932 [12:46<08:45, 11.55it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  59%|▌| 8865/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  59%|▌| 8865/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -81577,8 +81446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8860/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  59%|▌| 8860/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  59%|▌| 8866/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  59%|▌| 8866/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -81586,8 +81455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8861/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  59%|▌| 8861/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=1.79"
+      "Epoch 0:  59%|▌| 8867/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  59%|▌| 8867/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -81595,8 +81464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8862/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=1.79\r",
-      "Epoch 0:  59%|▌| 8862/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  59%|▌| 8868/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  59%|▌| 8868/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -81604,8 +81473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8863/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  59%|▌| 8863/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  59%|▌| 8869/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  59%|▌| 8869/14932 [12:46<08:44, 11.57it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -81613,8 +81482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8864/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  59%|▌| 8864/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  59%|▌| 8870/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  59%|▌| 8870/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -81622,8 +81491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8865/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  59%|▌| 8865/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  59%|▌| 8871/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  59%|▌| 8871/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -81631,8 +81500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8866/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  59%|▌| 8866/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  59%|▌| 8872/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  59%|▌| 8872/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=1.97"
      ]
     },
     {
@@ -81640,8 +81509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8867/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  59%|▌| 8867/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  59%|▌| 8873/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=1.97\r",
+      "Epoch 0:  59%|▌| 8873/14932 [12:46<08:43, 11.57it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -81649,8 +81518,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8868/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  59%|▌| 8868/14932 [12:47<08:45, 11.55it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  59%|▌| 8874/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -81658,8 +81526,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8869/14932 [12:47<08:44, 11.55it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  59%|▌| 8869/14932 [12:47<08:44, 11.55it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  59%|▌| 8874/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -81667,8 +81534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8870/14932 [12:47<08:44, 11.55it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  59%|▌| 8870/14932 [12:47<08:44, 11.55it/s, v_num=o30c, train/loss=1.98"
+      "Epoch 0:  59%|▌| 8875/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  59%|▌| 8875/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -81676,8 +81543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8871/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=1.98\r",
-      "Epoch 0:  59%|▌| 8871/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  59%|▌| 8876/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  59%|▌| 8876/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -81685,8 +81552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8872/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  59%|▌| 8872/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  59%|▌| 8877/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  59%|▌| 8877/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -81694,8 +81561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8873/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  59%|▌| 8873/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  59%|▌| 8878/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  59%|▌| 8878/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -81703,8 +81570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8874/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  59%|▌| 8874/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  59%|▌| 8879/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  59%|▌| 8879/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -81712,8 +81579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8875/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  59%|▌| 8875/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  59%|▌| 8880/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  59%|▌| 8880/14932 [12:47<08:43, 11.57it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -81721,8 +81588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8876/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  59%|▌| 8876/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  59%|▌| 8881/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  59%|▌| 8881/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -81730,8 +81597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8877/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  59%|▌| 8877/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  59%|▌| 8882/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  59%|▌| 8882/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -81739,8 +81606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8878/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  59%|▌| 8878/14932 [12:48<08:44, 11.55it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  59%|▌| 8883/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  59%|▌| 8883/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -81748,8 +81615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8879/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  59%|▌| 8879/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  59%|▌| 8884/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  59%|▌| 8884/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -81757,8 +81624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8880/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  59%|▌| 8880/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  60%|▌| 8885/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  60%|▌| 8885/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -81766,8 +81633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8881/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  59%|▌| 8881/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  60%|▌| 8886/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  60%|▌| 8886/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -81775,8 +81642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8882/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  59%|▌| 8882/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  60%|▌| 8887/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  60%|▌| 8887/14932 [12:47<08:42, 11.57it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -81784,8 +81651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8883/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  59%|▌| 8883/14932 [12:48<08:43, 11.55it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  60%|▌| 8888/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  60%|▌| 8888/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -81793,8 +81660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  59%|▌| 8884/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  59%|▌| 8884/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  60%|▌| 8889/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  60%|▌| 8889/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -81802,8 +81669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8885/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  60%|▌| 8885/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  60%|▌| 8890/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  60%|▌| 8890/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -81811,8 +81678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8886/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  60%|▌| 8886/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  60%|▌| 8891/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  60%|▌| 8891/14932 [12:48<08:42, 11.57it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -81820,8 +81687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8887/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  60%|▌| 8887/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  60%|▌| 8892/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  60%|▌| 8892/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -81829,8 +81696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8888/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  60%|▌| 8888/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  60%|▌| 8893/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  60%|▌| 8893/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -81838,8 +81705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8889/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  60%|▌| 8889/14932 [12:49<08:43, 11.55it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  60%|▌| 8894/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  60%|▌| 8894/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -81847,8 +81714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8890/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  60%|▌| 8890/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  60%|▌| 8895/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  60%|▌| 8895/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -81856,8 +81723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8891/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  60%|▌| 8891/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  60%|▌| 8896/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  60%|▌| 8896/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -81865,8 +81732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8892/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  60%|▌| 8892/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  60%|▌| 8897/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  60%|▌| 8897/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -81874,8 +81741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8893/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  60%|▌| 8893/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  60%|▌| 8898/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  60%|▌| 8898/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -81883,8 +81750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8894/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  60%|▌| 8894/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  60%|▌| 8899/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  60%|▌| 8899/14932 [12:48<08:41, 11.57it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -81892,8 +81759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8895/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  60%|▌| 8895/14932 [12:49<08:42, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  60%|▌| 8900/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  60%|▌| 8900/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -81901,8 +81768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8896/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  60%|▌| 8896/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  60%|▌| 8901/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  60%|▌| 8901/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -81910,8 +81777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8897/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  60%|▌| 8897/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  60%|▌| 8902/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  60%|▌| 8902/14932 [12:49<08:41, 11.57it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -81919,8 +81786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8898/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  60%|▌| 8898/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  60%|▌| 8903/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  60%|▌| 8903/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -81928,8 +81795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8899/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  60%|▌| 8899/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  60%|▌| 8904/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  60%|▌| 8904/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -81937,8 +81804,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8900/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  60%|▌| 8900/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  60%|▌| 8905/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -81946,8 +81812,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8901/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  60%|▌| 8901/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  60%|▌| 8905/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -81955,8 +81820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8902/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  60%|▌| 8902/14932 [12:50<08:42, 11.55it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  60%|▌| 8906/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  60%|▌| 8906/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -81964,8 +81829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8903/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  60%|▌| 8903/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  60%|▌| 8907/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  60%|▌| 8907/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -81973,8 +81838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8904/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  60%|▌| 8904/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  60%|▌| 8908/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  60%|▌| 8908/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -81982,8 +81847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8905/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  60%|▌| 8905/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  60%|▌| 8909/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  60%|▌| 8909/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -81991,8 +81856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8906/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  60%|▌| 8906/14932 [12:50<08:41, 11.55it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  60%|▌| 8910/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  60%|▌| 8910/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -82000,8 +81865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8907/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  60%|▌| 8907/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  60%|▌| 8911/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  60%|▌| 8911/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -82009,8 +81874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8908/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  60%|▌| 8908/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  60%|▌| 8912/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  60%|▌| 8912/14932 [12:49<08:40, 11.57it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -82018,8 +81883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8909/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  60%|▌| 8909/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  60%|▌| 8913/14932 [12:50<08:40, 11.57it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  60%|▌| 8913/14932 [12:50<08:40, 11.57it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -82027,8 +81892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8910/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  60%|▌| 8910/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  60%|▌| 8914/14932 [12:50<08:39, 11.57it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  60%|▌| 8914/14932 [12:50<08:39, 11.57it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -82036,8 +81901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8911/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  60%|▌| 8911/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  60%|▌| 8915/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  60%|▌| 8915/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -82045,8 +81910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8912/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  60%|▌| 8912/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  60%|▌| 8916/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  60%|▌| 8916/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -82054,8 +81919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8913/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  60%|▌| 8913/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  60%|▌| 8917/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  60%|▌| 8917/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -82063,8 +81928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8914/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  60%|▌| 8914/14932 [12:51<08:41, 11.55it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  60%|▌| 8918/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  60%|▌| 8918/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -82072,8 +81937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8915/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  60%|▌| 8915/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  60%|▌| 8919/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  60%|▌| 8919/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -82081,8 +81946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8916/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  60%|▌| 8916/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  60%|▌| 8920/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  60%|▌| 8920/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -82090,8 +81955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8917/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  60%|▌| 8917/14932 [12:51<08:40, 11.55it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  60%|▌| 8921/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  60%|▌| 8921/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -82099,8 +81964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8918/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  60%|▌| 8918/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  60%|▌| 8922/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  60%|▌| 8922/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -82108,8 +81973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8919/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  60%|▌| 8919/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  60%|▌| 8923/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  60%|▌| 8923/14932 [12:50<08:39, 11.58it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -82117,8 +81982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8920/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  60%|▌| 8920/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  60%|▌| 8924/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  60%|▌| 8924/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -82126,8 +81991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8921/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  60%|▌| 8921/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  60%|▌| 8925/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  60%|▌| 8925/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -82135,8 +82000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8922/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  60%|▌| 8922/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  60%|▌| 8926/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  60%|▌| 8926/14932 [12:50<08:38, 11.58it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -82144,8 +82009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8923/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  60%|▌| 8923/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  60%|▌| 8927/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  60%|▌| 8927/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -82153,8 +82018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8924/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  60%|▌| 8924/14932 [12:52<08:40, 11.55it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  60%|▌| 8928/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  60%|▌| 8928/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -82162,8 +82027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8925/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  60%|▌| 8925/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  60%|▌| 8929/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  60%|▌| 8929/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -82171,8 +82036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8926/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  60%|▌| 8926/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  60%|▌| 8930/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  60%|▌| 8930/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -82180,8 +82045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8927/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  60%|▌| 8927/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  60%|▌| 8931/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  60%|▌| 8931/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -82189,8 +82054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8928/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  60%|▌| 8928/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  60%|▌| 8932/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  60%|▌| 8932/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -82198,8 +82063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8929/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  60%|▌| 8929/14932 [12:52<08:39, 11.55it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  60%|▌| 8933/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  60%|▌| 8933/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -82207,8 +82072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8930/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  60%|▌| 8930/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  60%|▌| 8934/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  60%|▌| 8934/14932 [12:51<08:38, 11.58it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -82216,8 +82081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8931/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  60%|▌| 8931/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  60%|▌| 8935/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  60%|▌| 8935/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -82225,8 +82090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8932/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  60%|▌| 8932/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  60%|▌| 8936/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  60%|▌| 8936/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -82234,8 +82099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8933/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  60%|▌| 8933/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  60%|▌| 8937/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  60%|▌| 8937/14932 [12:51<08:37, 11.58it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -82243,8 +82108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8934/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  60%|▌| 8934/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  60%|▌| 8938/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  60%|▌| 8938/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -82252,8 +82117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8935/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  60%|▌| 8935/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=1.45"
+      "Epoch 0:  60%|▌| 8939/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  60%|▌| 8939/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -82261,8 +82126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8936/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=1.45\r",
-      "Epoch 0:  60%|▌| 8936/14932 [12:53<08:39, 11.55it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  60%|▌| 8940/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  60%|▌| 8940/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -82270,8 +82135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8937/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  60%|▌| 8937/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  60%|▌| 8941/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  60%|▌| 8941/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -82279,8 +82144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8938/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  60%|▌| 8938/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  60%|▌| 8942/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  60%|▌| 8942/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=1.02"
      ]
     },
     {
@@ -82288,8 +82153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8939/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  60%|▌| 8939/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  60%|▌| 8943/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=1.02\r",
+      "Epoch 0:  60%|▌| 8943/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -82297,8 +82162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8940/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  60%|▌| 8940/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  60%|▌| 8944/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  60%|▌| 8944/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -82306,8 +82171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8941/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  60%|▌| 8941/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  60%|▌| 8945/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  60%|▌| 8945/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -82315,8 +82180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8942/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  60%|▌| 8942/14932 [12:53<08:38, 11.55it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  60%|▌| 8946/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  60%|▌| 8946/14932 [12:52<08:37, 11.58it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -82324,8 +82189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8943/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  60%|▌| 8943/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  60%|▌| 8947/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  60%|▌| 8947/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -82333,8 +82198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8944/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  60%|▌| 8944/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  60%|▌| 8948/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  60%|▌| 8948/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -82342,8 +82207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8945/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  60%|▌| 8945/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  60%|▌| 8949/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  60%|▌| 8949/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -82351,8 +82216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8946/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  60%|▌| 8946/14932 [12:54<08:38, 11.55it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  60%|▌| 8950/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  60%|▌| 8950/14932 [12:52<08:36, 11.58it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -82360,8 +82225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8947/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  60%|▌| 8947/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  60%|▌| 8951/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  60%|▌| 8951/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -82369,8 +82234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8948/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  60%|▌| 8948/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  60%|▌| 8952/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  60%|▌| 8952/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -82378,8 +82243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8949/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  60%|▌| 8949/14932 [12:54<08:37, 11.55it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  60%|▌| 8953/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  60%|▌| 8953/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -82387,8 +82252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8950/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  60%|▌| 8950/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  60%|▌| 8954/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  60%|▌| 8954/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -82396,8 +82261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8951/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  60%|▌| 8951/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  60%|▌| 8955/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  60%|▌| 8955/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -82405,8 +82270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8952/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  60%|▌| 8952/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  60%|▌| 8956/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  60%|▌| 8956/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -82414,8 +82279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8953/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  60%|▌| 8953/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  60%|▌| 8957/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  60%|▌| 8957/14932 [12:53<08:36, 11.58it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -82423,8 +82288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8954/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  60%|▌| 8954/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  60%|▌| 8958/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  60%|▌| 8958/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -82432,8 +82297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8955/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  60%|▌| 8955/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  60%|▌| 8959/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  60%|▌| 8959/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -82441,8 +82306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8956/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  60%|▌| 8956/14932 [12:54<08:37, 11.56it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  60%|▌| 8960/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  60%|▌| 8960/14932 [12:53<08:35, 11.58it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -82450,8 +82315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8957/14932 [12:55<08:37, 11.56it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  60%|▌| 8957/14932 [12:55<08:37, 11.56it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  60%|▌| 8961/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  60%|▌| 8961/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -82459,8 +82324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8958/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  60%|▌| 8958/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  60%|▌| 8962/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  60%|▌| 8962/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -82468,8 +82333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8959/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  60%|▌| 8959/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  60%|▌| 8963/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  60%|▌| 8963/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -82477,8 +82342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8960/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  60%|▌| 8960/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  60%|▌| 8964/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  60%|▌| 8964/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=0.73"
      ]
     },
     {
@@ -82486,8 +82351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8961/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  60%|▌| 8961/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  60%|▌| 8965/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=0.73\r",
+      "Epoch 0:  60%|▌| 8965/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -82495,8 +82360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8962/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  60%|▌| 8962/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  60%|▌| 8966/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  60%|▌| 8966/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -82504,8 +82369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8963/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  60%|▌| 8963/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  60%|▌| 8967/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  60%|▌| 8967/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -82513,8 +82378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8964/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  60%|▌| 8964/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  60%|▌| 8968/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  60%|▌| 8968/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -82522,8 +82387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8965/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  60%|▌| 8965/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  60%|▌| 8969/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  60%|▌| 8969/14932 [12:54<08:35, 11.58it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -82531,8 +82396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8966/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  60%|▌| 8966/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  60%|▌| 8970/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  60%|▌| 8970/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -82540,8 +82405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8967/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  60%|▌| 8967/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  60%|▌| 8971/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  60%|▌| 8971/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -82549,8 +82414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8968/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  60%|▌| 8968/14932 [12:55<08:36, 11.56it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  60%|▌| 8972/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  60%|▌| 8972/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -82558,8 +82423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8969/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  60%|▌| 8969/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  60%|▌| 8973/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  60%|▌| 8973/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -82567,8 +82432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8970/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  60%|▌| 8970/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=1.97"
+      "Epoch 0:  60%|▌| 8974/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  60%|▌| 8974/14932 [12:54<08:34, 11.58it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -82576,8 +82441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8971/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=1.97\r",
-      "Epoch 0:  60%|▌| 8971/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  60%|▌| 8975/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  60%|▌| 8975/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=1.88"
      ]
     },
     {
@@ -82585,8 +82450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8972/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  60%|▌| 8972/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  60%|▌| 8976/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=1.88\r",
+      "Epoch 0:  60%|▌| 8976/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -82594,8 +82459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8973/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  60%|▌| 8973/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  60%|▌| 8977/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  60%|▌| 8977/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -82603,8 +82468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8974/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  60%|▌| 8974/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  60%|▌| 8978/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  60%|▌| 8978/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -82612,8 +82477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8975/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  60%|▌| 8975/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  60%|▌| 8979/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  60%|▌| 8979/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -82621,8 +82486,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8976/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  60%|▌| 8976/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  60%|▌| 8980/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -82630,8 +82494,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8977/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  60%|▌| 8977/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  60%|▌| 8980/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -82639,8 +82502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8978/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  60%|▌| 8978/14932 [12:56<08:35, 11.56it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  60%|▌| 8981/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  60%|▌| 8981/14932 [12:55<08:34, 11.58it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -82648,8 +82511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8979/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  60%|▌| 8979/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  60%|▌| 8982/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  60%|▌| 8982/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -82657,8 +82520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8980/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  60%|▌| 8980/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=1.85"
+      "Epoch 0:  60%|▌| 8983/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  60%|▌| 8983/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -82666,8 +82529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8981/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=1.85\r",
-      "Epoch 0:  60%|▌| 8981/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  60%|▌| 8984/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  60%|▌| 8984/14932 [12:55<08:33, 11.58it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -82675,8 +82538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8982/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  60%|▌| 8982/14932 [12:56<08:34, 11.56it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  60%|▌| 8985/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  60%|▌| 8985/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -82684,8 +82547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8983/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  60%|▌| 8983/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  60%|▌| 8986/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  60%|▌| 8986/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -82693,8 +82556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8984/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  60%|▌| 8984/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  60%|▌| 8987/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  60%|▌| 8987/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -82702,8 +82565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8985/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  60%|▌| 8985/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  60%|▌| 8988/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  60%|▌| 8988/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -82711,8 +82574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8986/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  60%|▌| 8986/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  60%|▌| 8989/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  60%|▌| 8989/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -82720,8 +82583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8987/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  60%|▌| 8987/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  60%|▌| 8990/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  60%|▌| 8990/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -82729,8 +82592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8988/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  60%|▌| 8988/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  60%|▌| 8991/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  60%|▌| 8991/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -82738,8 +82601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8989/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  60%|▌| 8989/14932 [12:57<08:34, 11.56it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  60%|▌| 8992/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  60%|▌| 8992/14932 [12:56<08:33, 11.58it/s, v_num=ui8w, train/loss=1.86"
      ]
     },
     {
@@ -82747,8 +82610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8990/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  60%|▌| 8990/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=1.35"
+      "Epoch 0:  60%|▌| 8993/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=1.86\r",
+      "Epoch 0:  60%|▌| 8993/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -82756,8 +82619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8991/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=1.35\r",
-      "Epoch 0:  60%|▌| 8991/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  60%|▌| 8994/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  60%|▌| 8994/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -82765,8 +82628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8992/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  60%|▌| 8992/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  60%|▌| 8995/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  60%|▌| 8995/14932 [12:56<08:32, 11.58it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -82774,8 +82637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8993/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  60%|▌| 8993/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  60%|▌| 8996/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  60%|▌| 8996/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -82783,8 +82646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8994/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  60%|▌| 8994/14932 [12:57<08:33, 11.56it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  60%|▌| 8997/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  60%|▌| 8997/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -82792,8 +82655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8995/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  60%|▌| 8995/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  60%|▌| 8998/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  60%|▌| 8998/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -82801,8 +82664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8996/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  60%|▌| 8996/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  60%|▌| 8999/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  60%|▌| 8999/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -82810,8 +82673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8997/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  60%|▌| 8997/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  60%|▌| 9000/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  60%|▌| 9000/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -82819,8 +82682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8998/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  60%|▌| 8998/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  60%|▌| 9001/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  60%|▌| 9001/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -82828,8 +82691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 8999/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  60%|▌| 8999/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  60%|▌| 9002/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  60%|▌| 9002/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -82837,8 +82700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9000/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  60%|▌| 9000/14932 [12:58<08:33, 11.56it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  60%|▌| 9003/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  60%|▌| 9003/14932 [12:57<08:32, 11.58it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -82846,8 +82709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9001/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  60%|▌| 9001/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=4.56"
+      "Epoch 0:  60%|▌| 9004/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  60%|▌| 9004/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -82855,8 +82718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9002/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=4.56\r",
-      "Epoch 0:  60%|▌| 9002/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  60%|▌| 9005/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  60%|▌| 9005/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -82864,8 +82727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9003/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  60%|▌| 9003/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  60%|▌| 9006/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  60%|▌| 9006/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -82873,8 +82736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9004/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  60%|▌| 9004/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  60%|▌| 9007/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  60%|▌| 9007/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -82882,8 +82745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9005/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  60%|▌| 9005/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  60%|▌| 9008/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  60%|▌| 9008/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -82891,8 +82754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9006/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  60%|▌| 9006/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  60%|▌| 9009/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  60%|▌| 9009/14932 [12:57<08:31, 11.58it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -82900,8 +82763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9007/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  60%|▌| 9007/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  60%|▌| 9010/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  60%|▌| 9010/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -82909,8 +82772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9008/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  60%|▌| 9008/14932 [12:58<08:32, 11.56it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  60%|▌| 9011/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  60%|▌| 9011/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -82918,8 +82781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9009/14932 [12:59<08:32, 11.56it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  60%|▌| 9009/14932 [12:59<08:32, 11.56it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  60%|▌| 9012/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  60%|▌| 9012/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -82927,8 +82790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9010/14932 [12:59<08:32, 11.56it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  60%|▌| 9010/14932 [12:59<08:32, 11.56it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  60%|▌| 9013/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  60%|▌| 9013/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -82936,8 +82799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9011/14932 [12:59<08:31, 11.56it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  60%|▌| 9011/14932 [12:59<08:31, 11.56it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  60%|▌| 9014/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  60%|▌| 9014/14932 [12:58<08:31, 11.58it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -82945,8 +82808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9012/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  60%|▌| 9012/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=1.21"
+      "Epoch 0:  60%|▌| 9015/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  60%|▌| 9015/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -82954,8 +82817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9013/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=1.21\r",
-      "Epoch 0:  60%|▌| 9013/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  60%|▌| 9016/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  60%|▌| 9016/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -82963,8 +82826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9014/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  60%|▌| 9014/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  60%|▌| 9017/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  60%|▌| 9017/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -82972,8 +82835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9015/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  60%|▌| 9015/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  60%|▌| 9018/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  60%|▌| 9018/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -82981,8 +82844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9016/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  60%|▌| 9016/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  60%|▌| 9019/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  60%|▌| 9019/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -82990,8 +82853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9017/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  60%|▌| 9017/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  60%|▌| 9020/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  60%|▌| 9020/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -82999,8 +82862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9018/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  60%|▌| 9018/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  60%|▌| 9021/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  60%|▌| 9021/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -83008,8 +82871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9019/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  60%|▌| 9019/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  60%|▌| 9022/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  60%|▌| 9022/14932 [12:58<08:30, 11.58it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -83017,8 +82880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9020/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  60%|▌| 9020/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  60%|▌| 9023/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  60%|▌| 9023/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -83026,8 +82889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9021/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  60%|▌| 9021/14932 [12:59<08:31, 11.57it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  60%|▌| 9024/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  60%|▌| 9024/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -83035,8 +82898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9022/14932 [13:00<08:31, 11.57it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  60%|▌| 9022/14932 [13:00<08:31, 11.57it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  60%|▌| 9025/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  60%|▌| 9025/14932 [12:59<08:30, 11.58it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -83044,8 +82907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9023/14932 [13:00<08:30, 11.57it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  60%|▌| 9023/14932 [13:00<08:30, 11.57it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  60%|▌| 9026/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  60%|▌| 9026/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -83053,8 +82916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9024/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  60%|▌| 9024/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  60%|▌| 9027/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  60%|▌| 9027/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=1.20"
      ]
     },
     {
@@ -83062,8 +82925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9025/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  60%|▌| 9025/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  60%|▌| 9028/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=1.20\r",
+      "Epoch 0:  60%|▌| 9028/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -83071,8 +82934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9026/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  60%|▌| 9026/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  60%|▌| 9029/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  60%|▌| 9029/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -83080,8 +82943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9027/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  60%|▌| 9027/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  60%|▌| 9030/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  60%|▌| 9030/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -83089,8 +82952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9028/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  60%|▌| 9028/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  60%|▌| 9031/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  60%|▌| 9031/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -83098,8 +82961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9029/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  60%|▌| 9029/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  60%|▌| 9032/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  60%|▌| 9032/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -83107,8 +82970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9030/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  60%|▌| 9030/14932 [13:00<08:30, 11.56it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  60%|▌| 9033/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  60%|▌| 9033/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -83116,8 +82979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9031/14932 [13:00<08:30, 11.57it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  60%|▌| 9031/14932 [13:00<08:30, 11.57it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  61%|▌| 9034/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  61%|▌| 9034/14932 [12:59<08:29, 11.58it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -83125,8 +82988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9032/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  60%|▌| 9032/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  61%|▌| 9035/14932 [13:00<08:29, 11.58it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  61%|▌| 9035/14932 [13:00<08:29, 11.58it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -83134,8 +82997,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  60%|▌| 9033/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  60%|▌| 9033/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  61%|▌| 9036/14932 [13:00<08:29, 11.58it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -83143,8 +83005,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9034/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  61%|▌| 9034/14932 [13:01<08:30, 11.56it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  61%|▌| 9036/14932 [13:00<08:29, 11.58it/s, v_num=ui8w, train/loss=5.41"
      ]
     },
     {
@@ -83152,8 +83013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9035/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  61%|▌| 9035/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  61%|▌| 9037/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=5.41\r",
+      "Epoch 0:  61%|▌| 9037/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -83161,8 +83022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9036/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  61%|▌| 9036/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  61%|▌| 9038/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  61%|▌| 9038/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -83170,8 +83031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9037/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  61%|▌| 9037/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  61%|▌| 9039/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  61%|▌| 9039/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -83179,8 +83040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9038/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  61%|▌| 9038/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  61%|▌| 9040/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  61%|▌| 9040/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -83188,8 +83049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9039/14932 [13:01<08:29, 11.57it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  61%|▌| 9039/14932 [13:01<08:29, 11.57it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  61%|▌| 9041/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  61%|▌| 9041/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -83197,8 +83058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9040/14932 [13:01<08:29, 11.57it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  61%|▌| 9040/14932 [13:01<08:29, 11.57it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  61%|▌| 9042/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  61%|▌| 9042/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -83206,8 +83067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9041/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  61%|▌| 9041/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  61%|▌| 9043/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  61%|▌| 9043/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -83215,8 +83076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9042/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  61%|▌| 9042/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  61%|▌| 9044/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  61%|▌| 9044/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -83224,8 +83085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9043/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  61%|▌| 9043/14932 [13:01<08:29, 11.56it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  61%|▌| 9045/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  61%|▌| 9045/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -83233,8 +83094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9044/14932 [13:02<08:29, 11.56it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  61%|▌| 9044/14932 [13:02<08:29, 11.56it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  61%|▌| 9046/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  61%|▌| 9046/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -83242,8 +83103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9045/14932 [13:02<08:29, 11.57it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  61%|▌| 9045/14932 [13:02<08:29, 11.57it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  61%|▌| 9047/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  61%|▌| 9047/14932 [13:00<08:28, 11.58it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -83251,8 +83112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9046/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  61%|▌| 9046/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  61%|▌| 9048/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  61%|▌| 9048/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -83260,8 +83121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9047/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  61%|▌| 9047/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  61%|▌| 9049/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  61%|▌| 9049/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -83269,8 +83130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9048/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  61%|▌| 9048/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  61%|▌| 9050/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  61%|▌| 9050/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=1.27"
      ]
     },
     {
@@ -83278,8 +83139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9049/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  61%|▌| 9049/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  61%|▌| 9051/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=1.27\r",
+      "Epoch 0:  61%|▌| 9051/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -83287,8 +83148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9050/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  61%|▌| 9050/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  61%|▌| 9052/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  61%|▌| 9052/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -83296,8 +83157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9051/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  61%|▌| 9051/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  61%|▌| 9053/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  61%|▌| 9053/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=0.74"
      ]
     },
     {
@@ -83305,8 +83166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9052/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  61%|▌| 9052/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  61%|▌| 9054/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=0.74\r",
+      "Epoch 0:  61%|▌| 9054/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -83314,8 +83175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9053/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  61%|▌| 9053/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  61%|▌| 9055/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  61%|▌| 9055/14932 [13:01<08:27, 11.59it/s, v_num=ui8w, train/loss=2.12"
      ]
     },
     {
@@ -83323,8 +83184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9054/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  61%|▌| 9054/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  61%|▌| 9056/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.12\r",
+      "Epoch 0:  61%|▌| 9056/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -83332,8 +83193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9055/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  61%|▌| 9055/14932 [13:02<08:28, 11.57it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  61%|▌| 9057/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  61%|▌| 9057/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -83341,8 +83202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9056/14932 [13:03<08:28, 11.57it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  61%|▌| 9056/14932 [13:03<08:28, 11.57it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  61%|▌| 9058/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  61%|▌| 9058/14932 [13:01<08:27, 11.58it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -83350,8 +83211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9057/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  61%|▌| 9057/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  61%|▌| 9059/14932 [13:01<08:26, 11.58it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  61%|▌| 9059/14932 [13:01<08:26, 11.58it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -83359,8 +83220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9058/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  61%|▌| 9058/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  61%|▌| 9060/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  61%|▌| 9060/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -83368,8 +83229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9059/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  61%|▌| 9059/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  61%|▌| 9061/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  61%|▌| 9061/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -83377,8 +83238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9060/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  61%|▌| 9060/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  61%|▌| 9062/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  61%|▌| 9062/14932 [13:02<08:26, 11.59it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -83386,8 +83247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9061/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  61%|▌| 9061/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  61%|▌| 9063/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  61%|▌| 9063/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -83395,8 +83256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9062/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  61%|▌| 9062/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  61%|▌| 9064/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  61%|▌| 9064/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -83404,8 +83265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9063/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  61%|▌| 9063/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  61%|▌| 9065/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  61%|▌| 9065/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -83413,8 +83274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9064/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  61%|▌| 9064/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  61%|▌| 9066/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  61%|▌| 9066/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=1.64"
      ]
     },
     {
@@ -83422,8 +83283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9065/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  61%|▌| 9065/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  61%|▌| 9067/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=1.64\r",
+      "Epoch 0:  61%|▌| 9067/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -83431,8 +83292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9066/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  61%|▌| 9066/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  61%|▌| 9068/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  61%|▌| 9068/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -83440,8 +83301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9067/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  61%|▌| 9067/14932 [13:03<08:27, 11.57it/s, v_num=o30c, train/loss=5.38"
+      "Epoch 0:  61%|▌| 9069/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  61%|▌| 9069/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -83449,8 +83310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9068/14932 [13:03<08:26, 11.57it/s, v_num=o30c, train/loss=5.38\r",
-      "Epoch 0:  61%|▌| 9068/14932 [13:03<08:26, 11.57it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  61%|▌| 9070/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  61%|▌| 9070/14932 [13:02<08:26, 11.58it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -83458,8 +83319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9069/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  61%|▌| 9069/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  61%|▌| 9071/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  61%|▌| 9071/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.15"
      ]
     },
     {
@@ -83467,8 +83328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9070/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  61%|▌| 9070/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  61%|▌| 9072/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.15\r",
+      "Epoch 0:  61%|▌| 9072/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -83476,8 +83337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9071/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  61%|▌| 9071/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  61%|▌| 9073/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  61%|▌| 9073/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -83485,8 +83346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9072/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  61%|▌| 9072/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  61%|▌| 9074/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  61%|▌| 9074/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -83494,8 +83355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9073/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  61%|▌| 9073/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  61%|▌| 9075/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  61%|▌| 9075/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -83503,8 +83364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9074/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  61%|▌| 9074/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  61%|▌| 9076/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  61%|▌| 9076/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -83512,8 +83373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9075/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  61%|▌| 9075/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  61%|▌| 9077/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  61%|▌| 9077/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -83521,8 +83382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9076/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  61%|▌| 9076/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  61%|▌| 9078/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  61%|▌| 9078/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.29"
      ]
     },
     {
@@ -83530,8 +83391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9077/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  61%|▌| 9077/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  61%|▌| 9079/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=1.29\r",
+      "Epoch 0:  61%|▌| 9079/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -83539,8 +83400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9078/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  61%|▌| 9078/14932 [13:04<08:26, 11.57it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  61%|▌| 9080/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  61%|▌| 9080/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -83548,8 +83409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9079/14932 [13:04<08:25, 11.57it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  61%|▌| 9079/14932 [13:04<08:25, 11.57it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  61%|▌| 9081/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  61%|▌| 9081/14932 [13:03<08:25, 11.58it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -83557,8 +83418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9080/14932 [13:04<08:25, 11.57it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  61%|▌| 9080/14932 [13:04<08:25, 11.57it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  61%|▌| 9082/14932 [13:04<08:25, 11.58it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  61%|▌| 9082/14932 [13:04<08:25, 11.58it/s, v_num=ui8w, train/loss=1.37"
      ]
     },
     {
@@ -83566,8 +83427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9081/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  61%|▌| 9081/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  61%|▌| 9083/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=1.37\r",
+      "Epoch 0:  61%|▌| 9083/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=1.35"
      ]
     },
     {
@@ -83575,8 +83436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9082/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  61%|▌| 9082/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  61%|▌| 9084/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=1.35\r",
+      "Epoch 0:  61%|▌| 9084/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -83584,8 +83445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9083/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  61%|▌| 9083/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  61%|▌| 9085/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  61%|▌| 9085/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -83593,8 +83454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9084/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  61%|▌| 9084/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  61%|▌| 9086/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  61%|▌| 9086/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -83602,8 +83463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9085/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  61%|▌| 9085/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  61%|▌| 9087/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  61%|▌| 9087/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -83611,8 +83472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9086/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  61%|▌| 9086/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.64"
+      "Epoch 0:  61%|▌| 9088/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  61%|▌| 9088/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -83620,8 +83481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9087/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.64\r",
-      "Epoch 0:  61%|▌| 9087/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  61%|▌| 9089/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  61%|▌| 9089/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -83629,8 +83490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9088/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  61%|▌| 9088/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  61%|▌| 9090/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  61%|▌| 9090/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -83638,8 +83499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9089/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  61%|▌| 9089/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  61%|▌| 9091/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  61%|▌| 9091/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -83647,8 +83508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9090/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  61%|▌| 9090/14932 [13:05<08:25, 11.57it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  61%|▌| 9092/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  61%|▌| 9092/14932 [13:04<08:24, 11.58it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -83656,8 +83517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9091/14932 [13:05<08:24, 11.57it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  61%|▌| 9091/14932 [13:05<08:24, 11.57it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  61%|▌| 9093/14932 [13:05<08:24, 11.58it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  61%|▌| 9093/14932 [13:05<08:24, 11.58it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -83665,8 +83526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9092/14932 [13:05<08:24, 11.57it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  61%|▌| 9092/14932 [13:05<08:24, 11.57it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  61%|▌| 9094/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  61%|▌| 9094/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -83674,8 +83535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9093/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  61%|▌| 9093/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  61%|▌| 9095/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  61%|▌| 9095/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -83683,8 +83544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9094/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  61%|▌| 9094/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  61%|▌| 9096/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  61%|▌| 9096/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -83692,8 +83553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9095/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  61%|▌| 9095/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  61%|▌| 9097/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  61%|▌| 9097/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -83701,8 +83562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9096/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  61%|▌| 9096/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=1.24"
+      "Epoch 0:  61%|▌| 9098/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  61%|▌| 9098/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -83710,8 +83571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9097/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=1.24\r",
-      "Epoch 0:  61%|▌| 9097/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=0.90"
+      "Epoch 0:  61%|▌| 9099/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  61%|▌| 9099/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -83719,8 +83580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9098/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=0.90\r",
-      "Epoch 0:  61%|▌| 9098/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  61%|▌| 9100/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  61%|▌| 9100/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -83728,8 +83589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9099/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  61%|▌| 9099/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  61%|▌| 9101/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  61%|▌| 9101/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -83737,8 +83598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9100/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  61%|▌| 9100/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  61%|▌| 9102/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  61%|▌| 9102/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -83746,8 +83607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9101/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  61%|▌| 9101/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  61%|▌| 9103/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  61%|▌| 9103/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -83755,8 +83616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9102/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  61%|▌| 9102/14932 [13:06<08:24, 11.57it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  61%|▌| 9104/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  61%|▌| 9104/14932 [13:05<08:23, 11.58it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -83764,8 +83625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9103/14932 [13:06<08:23, 11.57it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  61%|▌| 9103/14932 [13:06<08:23, 11.57it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  61%|▌| 9105/14932 [13:05<08:22, 11.58it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  61%|▌| 9105/14932 [13:05<08:22, 11.58it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -83773,8 +83634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9104/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  61%|▌| 9104/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.19"
+      "Epoch 0:  61%|▌| 9106/14932 [13:06<08:22, 11.58it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  61%|▌| 9106/14932 [13:06<08:22, 11.58it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -83782,8 +83643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9105/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.19\r",
-      "Epoch 0:  61%|▌| 9105/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  61%|▌| 9107/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  61%|▌| 9107/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -83791,8 +83652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9106/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  61%|▌| 9106/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  61%|▌| 9108/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  61%|▌| 9108/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -83800,8 +83661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9107/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  61%|▌| 9107/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  61%|▌| 9109/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  61%|▌| 9109/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -83809,8 +83670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9108/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  61%|▌| 9108/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  61%|▌| 9110/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  61%|▌| 9110/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -83818,7 +83679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9109/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  61%|▌| 9111/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  61%|▌| 9111/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -83826,7 +83688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9109/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  61%|▌| 9112/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  61%|▌| 9112/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -83834,8 +83697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9110/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  61%|▌| 9110/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  61%|▌| 9113/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  61%|▌| 9113/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -83843,8 +83706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9111/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  61%|▌| 9111/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  61%|▌| 9114/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  61%|▌| 9114/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -83852,8 +83715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9112/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  61%|▌| 9112/14932 [13:07<08:23, 11.57it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  61%|▌| 9115/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  61%|▌| 9115/14932 [13:06<08:22, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -83861,8 +83724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9113/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  61%|▌| 9113/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  61%|▌| 9116/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  61%|▌| 9116/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -83870,8 +83733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9114/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  61%|▌| 9114/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  61%|▌| 9117/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  61%|▌| 9117/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -83879,8 +83742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9115/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  61%|▌| 9115/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  61%|▌| 9118/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  61%|▌| 9118/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -83888,8 +83751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9116/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  61%|▌| 9116/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  61%|▌| 9119/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  61%|▌| 9119/14932 [13:06<08:21, 11.59it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -83897,8 +83760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9117/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  61%|▌| 9117/14932 [13:07<08:22, 11.57it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  61%|▌| 9120/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  61%|▌| 9120/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -83906,8 +83769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9118/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  61%|▌| 9118/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  61%|▌| 9121/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  61%|▌| 9121/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -83915,8 +83778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9119/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  61%|▌| 9119/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  61%|▌| 9122/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  61%|▌| 9122/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -83924,8 +83787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9120/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  61%|▌| 9120/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  61%|▌| 9123/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  61%|▌| 9123/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -83933,8 +83796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9121/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  61%|▌| 9121/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  61%|▌| 9124/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  61%|▌| 9124/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -83942,8 +83805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9122/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  61%|▌| 9122/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  61%|▌| 9125/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  61%|▌| 9125/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -83951,8 +83814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9123/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  61%|▌| 9123/14932 [13:08<08:22, 11.57it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  61%|▌| 9126/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  61%|▌| 9126/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -83960,8 +83823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9124/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  61%|▌| 9124/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  61%|▌| 9127/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  61%|▌| 9127/14932 [13:07<08:21, 11.59it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -83969,8 +83832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9125/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  61%|▌| 9125/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  61%|▌| 9128/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  61%|▌| 9128/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -83978,8 +83841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9126/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  61%|▌| 9126/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  61%|▌| 9129/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  61%|▌| 9129/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=1.87"
      ]
     },
     {
@@ -83987,8 +83850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9127/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  61%|▌| 9127/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  61%|▌| 9130/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=1.87\r",
+      "Epoch 0:  61%|▌| 9130/14932 [13:07<08:20, 11.59it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -83996,8 +83859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9128/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  61%|▌| 9128/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  61%|▌| 9131/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  61%|▌| 9131/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -84005,8 +83868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9129/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  61%|▌| 9129/14932 [13:08<08:21, 11.57it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  61%|▌| 9132/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  61%|▌| 9132/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -84014,8 +83877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9130/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  61%|▌| 9130/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  61%|▌| 9133/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  61%|▌| 9133/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -84023,8 +83886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9131/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  61%|▌| 9131/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  61%|▌| 9134/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  61%|▌| 9134/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -84032,8 +83895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9132/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  61%|▌| 9132/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  61%|▌| 9135/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  61%|▌| 9135/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -84041,8 +83904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9133/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  61%|▌| 9133/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  61%|▌| 9136/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  61%|▌| 9136/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -84050,8 +83913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9134/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  61%|▌| 9134/14932 [13:09<08:21, 11.57it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  61%|▌| 9137/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  61%|▌| 9137/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=1.49"
      ]
     },
     {
@@ -84059,8 +83922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9135/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  61%|▌| 9135/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  61%|▌| 9138/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=1.49\r",
+      "Epoch 0:  61%|▌| 9138/14932 [13:08<08:20, 11.59it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -84068,8 +83931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9136/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  61%|▌| 9136/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  61%|▌| 9139/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  61%|▌| 9139/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -84077,8 +83940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9137/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  61%|▌| 9137/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  61%|▌| 9140/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  61%|▌| 9140/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -84086,8 +83949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9138/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  61%|▌| 9138/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  61%|▌| 9141/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  61%|▌| 9141/14932 [13:08<08:19, 11.59it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -84095,8 +83958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9139/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  61%|▌| 9139/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  61%|▌| 9142/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  61%|▌| 9142/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -84104,8 +83967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9140/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  61%|▌| 9140/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  61%|▌| 9143/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  61%|▌| 9143/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -84113,8 +83976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9141/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  61%|▌| 9141/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  61%|▌| 9144/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  61%|▌| 9144/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -84122,8 +83985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9142/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  61%|▌| 9142/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  61%|▌| 9145/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  61%|▌| 9145/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -84131,8 +83994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9143/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  61%|▌| 9143/14932 [13:09<08:20, 11.57it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  61%|▌| 9146/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  61%|▌| 9146/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -84140,8 +84003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9144/14932 [13:10<08:20, 11.57it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  61%|▌| 9144/14932 [13:10<08:20, 11.57it/s, v_num=o30c, train/loss=1.07"
+      "Epoch 0:  61%|▌| 9147/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  61%|▌| 9147/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -84149,8 +84012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9145/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=1.07\r",
-      "Epoch 0:  61%|▌| 9145/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  61%|▌| 9148/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  61%|▌| 9148/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -84158,8 +84021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9146/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  61%|▌| 9146/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  61%|▌| 9149/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  61%|▌| 9149/14932 [13:09<08:19, 11.59it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -84167,8 +84030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9147/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  61%|▌| 9147/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  61%|▌| 9150/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  61%|▌| 9150/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -84176,8 +84039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9148/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  61%|▌| 9148/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  61%|▌| 9151/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  61%|▌| 9151/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=1.82"
      ]
     },
     {
@@ -84185,8 +84048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9149/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  61%|▌| 9149/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  61%|▌| 9152/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=1.82\r",
+      "Epoch 0:  61%|▌| 9152/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -84194,8 +84057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9150/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  61%|▌| 9150/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  61%|▌| 9153/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  61%|▌| 9153/14932 [13:09<08:18, 11.59it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -84203,8 +84066,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9151/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  61%|▌| 9151/14932 [13:10<08:19, 11.58it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  61%|▌| 9154/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -84212,8 +84074,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9152/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  61%|▌| 9152/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=1.94"
+      "Epoch 0:  61%|▌| 9154/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -84221,8 +84082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9153/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=1.94\r",
-      "Epoch 0:  61%|▌| 9153/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  61%|▌| 9155/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  61%|▌| 9155/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -84230,8 +84091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9154/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  61%|▌| 9154/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=0.45"
+      "Epoch 0:  61%|▌| 9156/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  61%|▌| 9156/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -84239,8 +84100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9155/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=0.45\r",
-      "Epoch 0:  61%|▌| 9155/14932 [13:10<08:19, 11.57it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  61%|▌| 9157/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  61%|▌| 9157/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -84248,8 +84109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9156/14932 [13:11<08:19, 11.57it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  61%|▌| 9156/14932 [13:11<08:19, 11.57it/s, v_num=o30c, train/loss=0.88"
+      "Epoch 0:  61%|▌| 9158/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  61%|▌| 9158/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -84257,8 +84118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9157/14932 [13:11<08:18, 11.57it/s, v_num=o30c, train/loss=0.88\r",
-      "Epoch 0:  61%|▌| 9157/14932 [13:11<08:18, 11.57it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  61%|▌| 9159/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  61%|▌| 9159/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -84266,8 +84127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9158/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  61%|▌| 9158/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  61%|▌| 9160/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  61%|▌| 9160/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -84275,8 +84136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9159/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  61%|▌| 9159/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  61%|▌| 9161/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  61%|▌| 9161/14932 [13:10<08:18, 11.59it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -84284,8 +84145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9160/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  61%|▌| 9160/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=1.75"
+      "Epoch 0:  61%|▌| 9162/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  61%|▌| 9162/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -84293,8 +84154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9161/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=1.75\r",
-      "Epoch 0:  61%|▌| 9161/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=1.03"
+      "Epoch 0:  61%|▌| 9163/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  61%|▌| 9163/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -84302,8 +84163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9162/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=1.03\r",
-      "Epoch 0:  61%|▌| 9162/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  61%|▌| 9164/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  61%|▌| 9164/14932 [13:10<08:17, 11.59it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -84311,8 +84172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9163/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  61%|▌| 9163/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  61%|▌| 9165/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  61%|▌| 9165/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -84320,8 +84181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9164/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  61%|▌| 9164/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  61%|▌| 9166/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  61%|▌| 9166/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -84329,8 +84190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9165/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  61%|▌| 9165/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  61%|▌| 9167/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  61%|▌| 9167/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -84338,8 +84199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9166/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  61%|▌| 9166/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  61%|▌| 9168/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  61%|▌| 9168/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -84347,8 +84208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9167/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  61%|▌| 9167/14932 [13:11<08:18, 11.58it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  61%|▌| 9169/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  61%|▌| 9169/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -84356,8 +84217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9168/14932 [13:11<08:17, 11.58it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  61%|▌| 9168/14932 [13:11<08:17, 11.58it/s, v_num=o30c, train/loss=1.21"
+      "Epoch 0:  61%|▌| 9170/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  61%|▌| 9170/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -84365,8 +84226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9169/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=1.21\r",
-      "Epoch 0:  61%|▌| 9169/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  61%|▌| 9171/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  61%|▌| 9171/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -84374,8 +84235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9170/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  61%|▌| 9170/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  61%|▌| 9172/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  61%|▌| 9172/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -84383,8 +84244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9171/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  61%|▌| 9171/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  61%|▌| 9173/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  61%|▌| 9173/14932 [13:11<08:17, 11.59it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -84392,8 +84253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9172/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  61%|▌| 9172/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  61%|▌| 9174/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  61%|▌| 9174/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -84401,8 +84262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9173/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  61%|▌| 9173/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  61%|▌| 9175/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  61%|▌| 9175/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -84410,8 +84271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9174/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  61%|▌| 9174/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  61%|▌| 9176/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  61%|▌| 9176/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -84419,8 +84280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9175/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  61%|▌| 9175/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  61%|▌| 9177/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  61%|▌| 9177/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -84428,8 +84289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9176/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  61%|▌| 9176/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  61%|▌| 9178/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  61%|▌| 9178/14932 [13:11<08:16, 11.59it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -84437,8 +84298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9177/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  61%|▌| 9177/14932 [13:12<08:17, 11.58it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  61%|▌| 9179/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  61%|▌| 9179/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -84446,8 +84307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9178/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  61%|▌| 9178/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  61%|▌| 9180/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  61%|▌| 9180/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -84455,8 +84316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9179/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  61%|▌| 9179/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  61%|▌| 9181/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  61%|▌| 9181/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=4.84"
      ]
     },
     {
@@ -84464,8 +84325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9180/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  61%|▌| 9180/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  61%|▌| 9182/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=4.84\r",
+      "Epoch 0:  61%|▌| 9182/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -84473,8 +84334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9181/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  61%|▌| 9181/14932 [13:12<08:16, 11.58it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  61%|▌| 9183/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  61%|▌| 9183/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -84482,8 +84343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9182/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  61%|▌| 9182/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  62%|▌| 9184/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  62%|▌| 9184/14932 [13:12<08:16, 11.59it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -84491,8 +84352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  61%|▌| 9183/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  61%|▌| 9183/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  62%|▌| 9185/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  62%|▌| 9185/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -84500,8 +84361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9184/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  62%|▌| 9184/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  62%|▌| 9186/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  62%|▌| 9186/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -84509,8 +84370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9185/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  62%|▌| 9185/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  62%|▌| 9187/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  62%|▌| 9187/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -84518,8 +84379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9186/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  62%|▌| 9186/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  62%|▌| 9188/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  62%|▌| 9188/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -84527,8 +84388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9187/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  62%|▌| 9187/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  62%|▌| 9189/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  62%|▌| 9189/14932 [13:12<08:15, 11.59it/s, v_num=ui8w, train/loss=1.55"
      ]
     },
     {
@@ -84536,8 +84397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9188/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  62%|▌| 9188/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  62%|▌| 9190/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=1.55\r",
+      "Epoch 0:  62%|▌| 9190/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -84545,8 +84406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9189/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  62%|▌| 9189/14932 [13:13<08:16, 11.58it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  62%|▌| 9191/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  62%|▌| 9191/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -84554,8 +84415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9190/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  62%|▌| 9190/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  62%|▌| 9192/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  62%|▌| 9192/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -84563,8 +84424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9191/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  62%|▌| 9191/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  62%|▌| 9193/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  62%|▌| 9193/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -84572,8 +84433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9192/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  62%|▌| 9192/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  62%|▌| 9194/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  62%|▌| 9194/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -84581,8 +84442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9193/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  62%|▌| 9193/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  62%|▌| 9195/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  62%|▌| 9195/14932 [13:13<08:15, 11.59it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -84590,8 +84451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9194/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  62%|▌| 9194/14932 [13:13<08:15, 11.58it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  62%|▌| 9196/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  62%|▌| 9196/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -84599,8 +84460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9195/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  62%|▌| 9195/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  62%|▌| 9197/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  62%|▌| 9197/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -84608,8 +84469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9196/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  62%|▌| 9196/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  62%|▌| 9198/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  62%|▌| 9198/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -84617,8 +84478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9197/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  62%|▌| 9197/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  62%|▌| 9199/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  62%|▌| 9199/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -84626,8 +84487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9198/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  62%|▌| 9198/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  62%|▌| 9200/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  62%|▌| 9200/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -84635,8 +84496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9199/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  62%|▌| 9199/14932 [13:14<08:15, 11.58it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  62%|▌| 9201/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  62%|▌| 9201/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -84644,8 +84505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9200/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  62%|▌| 9200/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  62%|▌| 9202/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  62%|▌| 9202/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -84653,8 +84514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9201/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  62%|▌| 9201/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  62%|▌| 9203/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  62%|▌| 9203/14932 [13:13<08:14, 11.59it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -84662,8 +84523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9202/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  62%|▌| 9202/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  62%|▌| 9204/14932 [13:14<08:14, 11.59it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  62%|▌| 9204/14932 [13:14<08:14, 11.59it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -84671,8 +84532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9203/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  62%|▌| 9203/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  62%|▌| 9205/14932 [13:14<08:14, 11.59it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  62%|▌| 9205/14932 [13:14<08:14, 11.59it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -84680,8 +84541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9204/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  62%|▌| 9204/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  62%|▌| 9206/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  62%|▌| 9206/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.25"
      ]
     },
     {
@@ -84689,8 +84550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9205/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  62%|▌| 9205/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  62%|▌| 9207/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.25\r",
+      "Epoch 0:  62%|▌| 9207/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -84698,8 +84559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9206/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  62%|▌| 9206/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  62%|▌| 9208/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  62%|▌| 9208/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -84707,8 +84568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9207/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  62%|▌| 9207/14932 [13:14<08:14, 11.58it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  62%|▌| 9209/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  62%|▌| 9209/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -84716,8 +84577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9208/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  62%|▌| 9208/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  62%|▌| 9210/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  62%|▌| 9210/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -84725,8 +84586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9209/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  62%|▌| 9209/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  62%|▌| 9211/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  62%|▌| 9211/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -84734,8 +84595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9210/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  62%|▌| 9210/14932 [13:15<08:14, 11.58it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  62%|▌| 9212/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  62%|▌| 9212/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -84743,8 +84604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9211/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  62%|▌| 9211/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  62%|▌| 9213/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  62%|▌| 9213/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -84752,8 +84613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9212/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  62%|▌| 9212/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  62%|▌| 9214/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  62%|▌| 9214/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -84761,8 +84622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9213/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  62%|▌| 9213/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  62%|▌| 9215/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  62%|▌| 9215/14932 [13:14<08:13, 11.59it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -84770,8 +84631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9214/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  62%|▌| 9214/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  62%|▌| 9216/14932 [13:15<08:13, 11.59it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  62%|▌| 9216/14932 [13:15<08:13, 11.59it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -84779,8 +84640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9215/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  62%|▌| 9215/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  62%|▌| 9217/14932 [13:15<08:13, 11.59it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  62%|▌| 9217/14932 [13:15<08:13, 11.59it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -84788,8 +84649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9216/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  62%|▌| 9216/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  62%|▌| 9218/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  62%|▌| 9218/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -84797,8 +84658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9217/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  62%|▌| 9217/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  62%|▌| 9219/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  62%|▌| 9219/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -84806,8 +84667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9218/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  62%|▌| 9218/14932 [13:15<08:13, 11.58it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  62%|▌| 9220/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  62%|▌| 9220/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -84815,8 +84676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9219/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  62%|▌| 9219/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  62%|▌| 9221/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  62%|▌| 9221/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -84824,8 +84685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9220/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  62%|▌| 9220/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  62%|▌| 9222/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  62%|▌| 9222/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=0.92"
      ]
     },
     {
@@ -84833,8 +84694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9221/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  62%|▌| 9221/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  62%|▌| 9223/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=0.92\r",
+      "Epoch 0:  62%|▌| 9223/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -84842,8 +84703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9222/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  62%|▌| 9222/14932 [13:16<08:13, 11.58it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  62%|▌| 9224/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  62%|▌| 9224/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -84851,8 +84712,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9223/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  62%|▌| 9223/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  62%|▌| 9225/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -84860,8 +84720,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9224/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  62%|▌| 9224/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  62%|▌| 9225/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -84869,8 +84728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9225/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  62%|▌| 9225/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  62%|▌| 9226/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  62%|▌| 9226/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -84878,8 +84737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9226/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  62%|▌| 9226/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  62%|▌| 9227/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  62%|▌| 9227/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -84887,8 +84746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9227/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  62%|▌| 9227/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  62%|▌| 9228/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  62%|▌| 9228/14932 [13:15<08:12, 11.59it/s, v_num=ui8w, train/loss=0.94"
      ]
     },
     {
@@ -84896,8 +84755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9228/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  62%|▌| 9228/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  62%|▌| 9229/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=0.94\r",
+      "Epoch 0:  62%|▌| 9229/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -84905,8 +84764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9229/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  62%|▌| 9229/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  62%|▌| 9230/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  62%|▌| 9230/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -84914,8 +84773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9230/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  62%|▌| 9230/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  62%|▌| 9231/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  62%|▌| 9231/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -84923,8 +84782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9231/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  62%|▌| 9231/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  62%|▌| 9232/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  62%|▌| 9232/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -84932,8 +84791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9232/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  62%|▌| 9232/14932 [13:16<08:12, 11.58it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  62%|▌| 9233/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  62%|▌| 9233/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -84941,8 +84800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9233/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  62%|▌| 9233/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  62%|▌| 9234/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  62%|▌| 9234/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -84950,8 +84809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9234/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  62%|▌| 9234/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=1.00"
+      "Epoch 0:  62%|▌| 9235/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  62%|▌| 9235/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -84959,8 +84818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9235/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=1.00\r",
-      "Epoch 0:  62%|▌| 9235/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  62%|▌| 9236/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  62%|▌| 9236/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -84968,8 +84827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9236/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  62%|▌| 9236/14932 [13:17<08:11, 11.58it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  62%|▌| 9237/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  62%|▌| 9237/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -84977,8 +84836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9237/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  62%|▌| 9237/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  62%|▌| 9238/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  62%|▌| 9238/14932 [13:16<08:11, 11.59it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -84986,8 +84845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9238/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  62%|▌| 9238/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  62%|▌| 9239/14932 [13:17<08:11, 11.59it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  62%|▌| 9239/14932 [13:17<08:11, 11.59it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -84995,8 +84854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9239/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  62%|▌| 9239/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  62%|▌| 9240/14932 [13:17<08:11, 11.59it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  62%|▌| 9240/14932 [13:17<08:11, 11.59it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -85004,8 +84863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9240/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  62%|▌| 9240/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  62%|▌| 9241/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  62%|▌| 9241/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -85013,8 +84872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9241/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  62%|▌| 9241/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  62%|▌| 9242/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  62%|▌| 9242/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -85022,8 +84881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9242/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  62%|▌| 9242/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  62%|▌| 9243/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  62%|▌| 9243/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -85031,8 +84890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9243/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  62%|▌| 9243/14932 [13:17<08:11, 11.59it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  62%|▌| 9244/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  62%|▌| 9244/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -85040,8 +84899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9244/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  62%|▌| 9244/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=1.58"
+      "Epoch 0:  62%|▌| 9245/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  62%|▌| 9245/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -85049,8 +84908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9245/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=1.58\r",
-      "Epoch 0:  62%|▌| 9245/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  62%|▌| 9246/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  62%|▌| 9246/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -85058,8 +84917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9246/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  62%|▌| 9246/14932 [13:17<08:10, 11.59it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  62%|▌| 9247/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  62%|▌| 9247/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -85067,8 +84926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9247/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  62%|▌| 9247/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  62%|▌| 9248/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  62%|▌| 9248/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.22"
      ]
     },
     {
@@ -85076,8 +84935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9248/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  62%|▌| 9248/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  62%|▌| 9249/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.22\r",
+      "Epoch 0:  62%|▌| 9249/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -85085,8 +84944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9249/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  62%|▌| 9249/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  62%|▌| 9250/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  62%|▌| 9250/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -85094,8 +84953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9250/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  62%|▌| 9250/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  62%|▌| 9251/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  62%|▌| 9251/14932 [13:17<08:10, 11.59it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -85103,8 +84962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9251/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  62%|▌| 9251/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  62%|▌| 9252/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  62%|▌| 9252/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -85112,8 +84971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9252/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  62%|▌| 9252/14932 [13:18<08:10, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  62%|▌| 9253/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  62%|▌| 9253/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -85121,8 +84980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9253/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  62%|▌| 9253/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  62%|▌| 9254/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  62%|▌| 9254/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -85130,8 +84989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9254/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  62%|▌| 9254/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=1.54"
+      "Epoch 0:  62%|▌| 9255/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  62%|▌| 9255/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -85139,8 +84998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9255/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=1.54\r",
-      "Epoch 0:  62%|▌| 9255/14932 [13:18<08:10, 11.58it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  62%|▌| 9256/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  62%|▌| 9256/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -85148,8 +85007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9256/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  62%|▌| 9256/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  62%|▌| 9257/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  62%|▌| 9257/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -85157,8 +85016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9257/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  62%|▌| 9257/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  62%|▌| 9258/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  62%|▌| 9258/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -85166,8 +85025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9258/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  62%|▌| 9258/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  62%|▌| 9259/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  62%|▌| 9259/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -85175,8 +85034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9259/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  62%|▌| 9259/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  62%|▌| 9260/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  62%|▌| 9260/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -85184,8 +85043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9260/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  62%|▌| 9260/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  62%|▌| 9261/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  62%|▌| 9261/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -85193,8 +85052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9261/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  62%|▌| 9261/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  62%|▌| 9262/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  62%|▌| 9262/14932 [13:18<08:09, 11.59it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -85202,8 +85061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9262/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  62%|▌| 9262/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  62%|▌| 9263/14932 [13:18<08:08, 11.59it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  62%|▌| 9263/14932 [13:18<08:08, 11.59it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -85211,7 +85070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9263/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  62%|▌| 9264/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  62%|▌| 9264/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -85219,7 +85079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9263/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  62%|▌| 9265/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  62%|▌| 9265/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -85227,8 +85088,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9264/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  62%|▌| 9264/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=1.80"
+      "Epoch 0:  62%|▌| 9266/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -85236,8 +85096,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9265/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=1.80\r",
-      "Epoch 0:  62%|▌| 9265/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  62%|▌| 9266/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -85245,8 +85104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9266/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  62%|▌| 9266/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  62%|▌| 9267/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  62%|▌| 9267/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -85254,8 +85113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9267/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  62%|▌| 9267/14932 [13:19<08:09, 11.58it/s, v_num=o30c, train/loss=4.59"
+      "Epoch 0:  62%|▌| 9268/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  62%|▌| 9268/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -85263,8 +85122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9268/14932 [13:20<08:08, 11.58it/s, v_num=o30c, train/loss=4.59\r",
-      "Epoch 0:  62%|▌| 9268/14932 [13:20<08:08, 11.58it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  62%|▌| 9269/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  62%|▌| 9269/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -85272,8 +85131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9269/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  62%|▌| 9269/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  62%|▌| 9270/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  62%|▌| 9270/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -85281,8 +85140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9270/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  62%|▌| 9270/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  62%|▌| 9271/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  62%|▌| 9271/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -85290,8 +85149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9271/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  62%|▌| 9271/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  62%|▌| 9272/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  62%|▌| 9272/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -85299,8 +85158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9272/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  62%|▌| 9272/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  62%|▌| 9273/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  62%|▌| 9273/14932 [13:19<08:08, 11.59it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -85308,8 +85167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9273/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  62%|▌| 9273/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  62%|▌| 9274/14932 [13:19<08:07, 11.59it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  62%|▌| 9274/14932 [13:19<08:07, 11.59it/s, v_num=ui8w, train/loss=1.81"
      ]
     },
     {
@@ -85317,8 +85176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9274/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  62%|▌| 9274/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.36"
+      "Epoch 0:  62%|▌| 9275/14932 [13:19<08:07, 11.59it/s, v_num=ui8w, train/loss=1.81\r",
+      "Epoch 0:  62%|▌| 9275/14932 [13:19<08:07, 11.59it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -85326,8 +85185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9275/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.36\r",
-      "Epoch 0:  62%|▌| 9275/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  62%|▌| 9276/14932 [13:19<08:07, 11.60it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  62%|▌| 9276/14932 [13:19<08:07, 11.60it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -85335,8 +85194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9276/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  62%|▌| 9276/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  62%|▌| 9277/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  62%|▌| 9277/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -85344,8 +85203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9277/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  62%|▌| 9277/14932 [13:20<08:08, 11.59it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  62%|▌| 9278/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  62%|▌| 9278/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -85353,8 +85212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9278/14932 [13:20<08:07, 11.59it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  62%|▌| 9278/14932 [13:20<08:07, 11.59it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  62%|▌| 9279/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  62%|▌| 9279/14932 [13:20<08:07, 11.60it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -85362,8 +85221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9279/14932 [13:20<08:07, 11.59it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  62%|▌| 9279/14932 [13:20<08:07, 11.59it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  62%|▌| 9280/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  62%|▌| 9280/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -85371,8 +85230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9280/14932 [13:21<08:07, 11.58it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  62%|▌| 9280/14932 [13:21<08:07, 11.58it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  62%|▌| 9281/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  62%|▌| 9281/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -85380,8 +85239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9281/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  62%|▌| 9281/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  62%|▌| 9282/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  62%|▌| 9282/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -85389,8 +85248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9282/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  62%|▌| 9282/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  62%|▌| 9283/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  62%|▌| 9283/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -85398,8 +85257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9283/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  62%|▌| 9283/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  62%|▌| 9284/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  62%|▌| 9284/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -85407,8 +85266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9284/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  62%|▌| 9284/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  62%|▌| 9285/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  62%|▌| 9285/14932 [13:20<08:07, 11.59it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -85416,8 +85275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9285/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  62%|▌| 9285/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  62%|▌| 9286/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  62%|▌| 9286/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=1.06"
      ]
     },
     {
@@ -85425,8 +85284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9286/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  62%|▌| 9286/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=1.53"
+      "Epoch 0:  62%|▌| 9287/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=1.06\r",
+      "Epoch 0:  62%|▌| 9287/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -85434,8 +85293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9287/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=1.53\r",
-      "Epoch 0:  62%|▌| 9287/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  62%|▌| 9288/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  62%|▌| 9288/14932 [13:20<08:06, 11.60it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -85443,8 +85302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9288/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  62%|▌| 9288/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  62%|▌| 9289/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  62%|▌| 9289/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -85452,8 +85311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9289/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  62%|▌| 9289/14932 [13:21<08:07, 11.59it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  62%|▌| 9290/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  62%|▌| 9290/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -85461,8 +85320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9290/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  62%|▌| 9290/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  62%|▌| 9291/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  62%|▌| 9291/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -85470,8 +85329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9291/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  62%|▌| 9291/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  62%|▌| 9292/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  62%|▌| 9292/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -85479,8 +85338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9292/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  62%|▌| 9292/14932 [13:21<08:06, 11.59it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  62%|▌| 9293/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  62%|▌| 9293/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -85488,8 +85347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9293/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  62%|▌| 9293/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  62%|▌| 9294/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  62%|▌| 9294/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -85497,8 +85356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9294/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  62%|▌| 9294/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  62%|▌| 9295/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  62%|▌| 9295/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -85506,8 +85365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9295/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  62%|▌| 9295/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  62%|▌| 9296/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  62%|▌| 9296/14932 [13:21<08:06, 11.60it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -85515,8 +85374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9296/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  62%|▌| 9296/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.10"
+      "Epoch 0:  62%|▌| 9297/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  62%|▌| 9297/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -85524,8 +85383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9297/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.10\r",
-      "Epoch 0:  62%|▌| 9297/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  62%|▌| 9298/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  62%|▌| 9298/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -85533,8 +85392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9298/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  62%|▌| 9298/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  62%|▌| 9299/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  62%|▌| 9299/14932 [13:21<08:05, 11.60it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -85542,8 +85401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9299/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  62%|▌| 9299/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  62%|▌| 9300/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  62%|▌| 9300/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -85551,8 +85410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9300/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  62%|▌| 9300/14932 [13:22<08:06, 11.59it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  62%|▌| 9301/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  62%|▌| 9301/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -85560,8 +85419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9301/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  62%|▌| 9301/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  62%|▌| 9302/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  62%|▌| 9302/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -85569,8 +85428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9302/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  62%|▌| 9302/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  62%|▌| 9303/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  62%|▌| 9303/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -85578,8 +85437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9303/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  62%|▌| 9303/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=1.18"
+      "Epoch 0:  62%|▌| 9304/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  62%|▌| 9304/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -85587,8 +85446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9304/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=1.18\r",
-      "Epoch 0:  62%|▌| 9304/14932 [13:22<08:05, 11.59it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  62%|▌| 9305/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  62%|▌| 9305/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -85596,8 +85455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9305/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  62%|▌| 9305/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  62%|▌| 9306/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  62%|▌| 9306/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -85605,8 +85464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9306/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  62%|▌| 9306/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  62%|▌| 9307/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  62%|▌| 9307/14932 [13:22<08:05, 11.60it/s, v_num=ui8w, train/loss=4.53"
      ]
     },
     {
@@ -85614,8 +85473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9307/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  62%|▌| 9307/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  62%|▌| 9308/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=4.53\r",
+      "Epoch 0:  62%|▌| 9308/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -85623,8 +85482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9308/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  62%|▌| 9308/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  62%|▌| 9309/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  62%|▌| 9309/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -85632,8 +85491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9309/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  62%|▌| 9309/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=1.28"
+      "Epoch 0:  62%|▌| 9310/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  62%|▌| 9310/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -85641,8 +85500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9310/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=1.28\r",
-      "Epoch 0:  62%|▌| 9310/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  62%|▌| 9311/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  62%|▌| 9311/14932 [13:22<08:04, 11.60it/s, v_num=ui8w, train/loss=1.73"
      ]
     },
     {
@@ -85650,8 +85509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9311/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  62%|▌| 9311/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  62%|▌| 9312/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=1.73\r",
+      "Epoch 0:  62%|▌| 9312/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -85659,8 +85518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9312/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  62%|▌| 9312/14932 [13:23<08:05, 11.59it/s, v_num=o30c, train/loss=2.05"
+      "Epoch 0:  62%|▌| 9313/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  62%|▌| 9313/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=1.78"
      ]
     },
     {
@@ -85668,8 +85527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9313/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=2.05\r",
-      "Epoch 0:  62%|▌| 9313/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  62%|▌| 9314/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=1.78\r",
+      "Epoch 0:  62%|▌| 9314/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -85677,8 +85536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9314/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  62%|▌| 9314/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  62%|▌| 9315/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  62%|▌| 9315/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -85686,8 +85545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9315/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  62%|▌| 9315/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  62%|▌| 9316/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  62%|▌| 9316/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -85695,8 +85554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9316/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  62%|▌| 9316/14932 [13:23<08:04, 11.59it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  62%|▌| 9317/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  62%|▌| 9317/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -85704,8 +85563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9317/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  62%|▌| 9317/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  62%|▌| 9318/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  62%|▌| 9318/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -85713,8 +85572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9318/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  62%|▌| 9318/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  62%|▌| 9319/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  62%|▌| 9319/14932 [13:23<08:04, 11.60it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -85722,8 +85581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9319/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  62%|▌| 9319/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  62%|▌| 9320/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  62%|▌| 9320/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -85731,8 +85590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9320/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  62%|▌| 9320/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  62%|▌| 9321/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  62%|▌| 9321/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -85740,8 +85599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9321/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  62%|▌| 9321/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  62%|▌| 9322/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  62%|▌| 9322/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -85749,8 +85608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9322/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  62%|▌| 9322/14932 [13:24<08:04, 11.59it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  62%|▌| 9323/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  62%|▌| 9323/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -85758,8 +85617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9323/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  62%|▌| 9323/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  62%|▌| 9324/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  62%|▌| 9324/14932 [13:23<08:03, 11.60it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -85767,8 +85626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9324/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  62%|▌| 9324/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  62%|▌| 9325/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  62%|▌| 9325/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -85776,8 +85635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9325/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  62%|▌| 9325/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  62%|▌| 9326/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  62%|▌| 9326/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -85785,8 +85644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9326/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  62%|▌| 9326/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  62%|▌| 9327/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  62%|▌| 9327/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -85794,8 +85653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9327/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  62%|▌| 9327/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  62%|▌| 9328/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  62%|▌| 9328/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -85803,8 +85662,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9328/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  62%|▌| 9328/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  62%|▌| 9329/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -85812,8 +85670,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9329/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  62%|▌| 9329/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  62%|▌| 9329/14932 [13:24<08:03, 11.60it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -85821,8 +85678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9330/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  62%|▌| 9330/14932 [13:24<08:03, 11.59it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  62%|▌| 9330/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  62%|▌| 9330/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -85830,8 +85687,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9331/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  62%|▌| 9331/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  62%|▌| 9331/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -85839,8 +85695,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  62%|▌| 9332/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  62%|▌| 9332/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  62%|▌| 9331/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -85848,8 +85703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9333/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  63%|▋| 9333/14932 [13:25<08:03, 11.59it/s, v_num=o30c, train/loss=1.16"
+      "Epoch 0:  62%|▌| 9332/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  62%|▌| 9332/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -85857,8 +85712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9334/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=1.16\r",
-      "Epoch 0:  63%|▋| 9334/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  63%|▋| 9333/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  63%|▋| 9333/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -85866,8 +85721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9335/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  63%|▋| 9335/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  63%|▋| 9334/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  63%|▋| 9334/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -85875,8 +85730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9336/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  63%|▋| 9336/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  63%|▋| 9335/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  63%|▋| 9335/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -85884,8 +85739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9337/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  63%|▋| 9337/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  63%|▋| 9336/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  63%|▋| 9336/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -85893,8 +85748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9338/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  63%|▋| 9338/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  63%|▋| 9337/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  63%|▋| 9337/14932 [13:24<08:02, 11.60it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -85902,8 +85757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9339/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  63%|▋| 9339/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  63%|▋| 9338/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  63%|▋| 9338/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -85911,8 +85766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9340/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  63%|▋| 9340/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  63%|▋| 9339/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  63%|▋| 9339/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -85920,8 +85775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9341/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  63%|▋| 9341/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=1.37"
+      "Epoch 0:  63%|▋| 9340/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  63%|▋| 9340/14932 [13:25<08:02, 11.60it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -85929,8 +85784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9342/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=1.37\r",
-      "Epoch 0:  63%|▋| 9342/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  63%|▋| 9341/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  63%|▋| 9341/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -85938,8 +85793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9343/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  63%|▋| 9343/14932 [13:25<08:02, 11.59it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  63%|▋| 9342/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  63%|▋| 9342/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -85947,8 +85802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9344/14932 [13:26<08:02, 11.59it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  63%|▋| 9344/14932 [13:26<08:02, 11.59it/s, v_num=o30c, train/loss=1.31"
+      "Epoch 0:  63%|▋| 9343/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  63%|▋| 9343/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -85956,8 +85811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9345/14932 [13:26<08:02, 11.59it/s, v_num=o30c, train/loss=1.31\r",
-      "Epoch 0:  63%|▋| 9345/14932 [13:26<08:02, 11.59it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  63%|▋| 9344/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  63%|▋| 9344/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -85965,8 +85820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9346/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  63%|▋| 9346/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  63%|▋| 9345/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  63%|▋| 9345/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -85974,8 +85829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9347/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  63%|▋| 9347/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  63%|▋| 9346/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  63%|▋| 9346/14932 [13:25<08:01, 11.60it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -85983,8 +85838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9348/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  63%|▋| 9348/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  63%|▋| 9347/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  63%|▋| 9347/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=0.91"
      ]
     },
     {
@@ -85992,8 +85847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9349/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  63%|▋| 9349/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  63%|▋| 9348/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=0.91\r",
+      "Epoch 0:  63%|▋| 9348/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -86001,8 +85856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9350/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  63%|▋| 9350/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  63%|▋| 9349/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  63%|▋| 9349/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=1.66"
      ]
     },
     {
@@ -86010,8 +85865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9351/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  63%|▋| 9351/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  63%|▋| 9350/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=1.66\r",
+      "Epoch 0:  63%|▋| 9350/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=1.94"
      ]
     },
     {
@@ -86019,8 +85874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9352/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  63%|▋| 9352/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  63%|▋| 9351/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=1.94\r",
+      "Epoch 0:  63%|▋| 9351/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -86028,8 +85883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9353/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  63%|▋| 9353/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=1.52"
+      "Epoch 0:  63%|▋| 9352/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  63%|▋| 9352/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -86037,8 +85892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9354/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=1.52\r",
-      "Epoch 0:  63%|▋| 9354/14932 [13:26<08:01, 11.59it/s, v_num=o30c, train/loss=1.78"
+      "Epoch 0:  63%|▋| 9353/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  63%|▋| 9353/14932 [13:26<08:01, 11.60it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -86046,8 +85901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9355/14932 [13:27<08:01, 11.59it/s, v_num=o30c, train/loss=1.78\r",
-      "Epoch 0:  63%|▋| 9355/14932 [13:27<08:01, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  63%|▋| 9354/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  63%|▋| 9354/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -86055,8 +85910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9356/14932 [13:27<08:01, 11.59it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  63%|▋| 9356/14932 [13:27<08:01, 11.59it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  63%|▋| 9355/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  63%|▋| 9355/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -86064,8 +85919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9357/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  63%|▋| 9357/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  63%|▋| 9356/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  63%|▋| 9356/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -86073,8 +85928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9358/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  63%|▋| 9358/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  63%|▋| 9357/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  63%|▋| 9357/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -86082,7 +85937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9359/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  63%|▋| 9358/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  63%|▋| 9358/14932 [13:26<08:00, 11.60it/s, v_num=ui8w, train/loss=1.84"
      ]
     },
     {
@@ -86090,7 +85946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9359/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  63%|▋| 9359/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=1.84\r",
+      "Epoch 0:  63%|▋| 9359/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -86098,8 +85955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9360/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  63%|▋| 9360/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  63%|▋| 9360/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  63%|▋| 9360/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -86107,8 +85964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9361/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  63%|▋| 9361/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  63%|▋| 9361/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  63%|▋| 9361/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -86116,8 +85973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9362/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  63%|▋| 9362/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  63%|▋| 9362/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  63%|▋| 9362/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -86125,8 +85982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9363/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  63%|▋| 9363/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  63%|▋| 9363/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  63%|▋| 9363/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -86134,8 +85991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9364/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  63%|▋| 9364/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  63%|▋| 9364/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  63%|▋| 9364/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -86143,8 +86000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9365/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  63%|▋| 9365/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  63%|▋| 9365/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  63%|▋| 9365/14932 [13:27<08:00, 11.60it/s, v_num=ui8w, train/loss=4.66"
      ]
     },
     {
@@ -86152,8 +86009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9366/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  63%|▋| 9366/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  63%|▋| 9366/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=4.66\r",
+      "Epoch 0:  63%|▋| 9366/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -86161,8 +86018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9367/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  63%|▋| 9367/14932 [13:27<08:00, 11.59it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  63%|▋| 9367/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  63%|▋| 9367/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -86170,8 +86027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9368/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  63%|▋| 9368/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  63%|▋| 9368/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  63%|▋| 9368/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -86179,8 +86036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9369/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  63%|▋| 9369/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  63%|▋| 9369/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  63%|▋| 9369/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -86188,8 +86045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9370/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  63%|▋| 9370/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  63%|▋| 9370/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  63%|▋| 9370/14932 [13:27<07:59, 11.60it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -86197,8 +86054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9371/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  63%|▋| 9371/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  63%|▋| 9371/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  63%|▋| 9371/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -86206,8 +86063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9372/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  63%|▋| 9372/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=5.12"
+      "Epoch 0:  63%|▋| 9372/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  63%|▋| 9372/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -86215,8 +86072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9373/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=5.12\r",
-      "Epoch 0:  63%|▋| 9373/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  63%|▋| 9373/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  63%|▋| 9373/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -86224,8 +86081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9374/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  63%|▋| 9374/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  63%|▋| 9374/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  63%|▋| 9374/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -86233,8 +86090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9375/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  63%|▋| 9375/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  63%|▋| 9375/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  63%|▋| 9375/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -86242,8 +86099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9376/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  63%|▋| 9376/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  63%|▋| 9376/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  63%|▋| 9376/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -86251,8 +86108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9377/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  63%|▋| 9377/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  63%|▋| 9377/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  63%|▋| 9377/14932 [13:28<07:59, 11.60it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -86260,8 +86117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9378/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  63%|▋| 9378/14932 [13:28<07:59, 11.59it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  63%|▋| 9378/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  63%|▋| 9378/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -86269,8 +86126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9379/14932 [13:29<07:59, 11.59it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  63%|▋| 9379/14932 [13:29<07:59, 11.59it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  63%|▋| 9379/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  63%|▋| 9379/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -86278,8 +86135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9380/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  63%|▋| 9380/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.36"
+      "Epoch 0:  63%|▋| 9380/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  63%|▋| 9380/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -86287,8 +86144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9381/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.36\r",
-      "Epoch 0:  63%|▋| 9381/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  63%|▋| 9381/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  63%|▋| 9381/14932 [13:28<07:58, 11.60it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -86296,8 +86153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9382/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  63%|▋| 9382/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.08"
+      "Epoch 0:  63%|▋| 9382/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  63%|▋| 9382/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -86305,8 +86162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9383/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.08\r",
-      "Epoch 0:  63%|▋| 9383/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  63%|▋| 9383/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  63%|▋| 9383/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -86314,8 +86171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9384/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  63%|▋| 9384/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.44"
+      "Epoch 0:  63%|▋| 9384/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  63%|▋| 9384/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -86323,8 +86180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9385/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.44\r",
-      "Epoch 0:  63%|▋| 9385/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  63%|▋| 9385/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  63%|▋| 9385/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -86332,7 +86189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9386/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  63%|▋| 9386/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  63%|▋| 9386/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=1.43"
      ]
     },
     {
@@ -86340,7 +86198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9386/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  63%|▋| 9387/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=1.43\r",
+      "Epoch 0:  63%|▋| 9387/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.16"
      ]
     },
     {
@@ -86348,8 +86207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9387/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  63%|▋| 9387/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  63%|▋| 9388/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.16\r",
+      "Epoch 0:  63%|▋| 9388/14932 [13:29<07:58, 11.60it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -86357,8 +86216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9388/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  63%|▋| 9388/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  63%|▋| 9389/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  63%|▋| 9389/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -86366,8 +86225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9389/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  63%|▋| 9389/14932 [13:29<07:58, 11.59it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  63%|▋| 9390/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  63%|▋| 9390/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -86375,8 +86234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9390/14932 [13:29<07:57, 11.59it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  63%|▋| 9390/14932 [13:29<07:57, 11.59it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  63%|▋| 9391/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  63%|▋| 9391/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -86384,8 +86243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9391/14932 [13:29<07:57, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  63%|▋| 9391/14932 [13:29<07:57, 11.60it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  63%|▋| 9392/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  63%|▋| 9392/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -86393,8 +86252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9392/14932 [13:29<07:57, 11.60it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  63%|▋| 9392/14932 [13:29<07:57, 11.60it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  63%|▋| 9393/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  63%|▋| 9393/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -86402,8 +86261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9393/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  63%|▋| 9393/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  63%|▋| 9394/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  63%|▋| 9394/14932 [13:29<07:57, 11.60it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -86411,8 +86270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9394/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  63%|▋| 9394/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  63%|▋| 9395/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  63%|▋| 9395/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -86420,8 +86279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9395/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  63%|▋| 9395/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=1.46"
+      "Epoch 0:  63%|▋| 9396/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  63%|▋| 9396/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -86429,8 +86288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9396/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=1.46\r",
-      "Epoch 0:  63%|▋| 9396/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  63%|▋| 9397/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  63%|▋| 9397/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -86438,8 +86297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9397/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  63%|▋| 9397/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  63%|▋| 9398/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  63%|▋| 9398/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -86447,8 +86306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9398/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  63%|▋| 9398/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  63%|▋| 9399/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  63%|▋| 9399/14932 [13:30<07:57, 11.60it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -86456,8 +86315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9399/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  63%|▋| 9399/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  63%|▋| 9400/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  63%|▋| 9400/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -86465,8 +86324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9400/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  63%|▋| 9400/14932 [13:30<07:57, 11.60it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  63%|▋| 9401/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  63%|▋| 9401/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.31"
      ]
     },
     {
@@ -86474,8 +86333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9401/14932 [13:30<07:56, 11.60it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  63%|▋| 9401/14932 [13:30<07:56, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  63%|▋| 9402/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.31\r",
+      "Epoch 0:  63%|▋| 9402/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -86483,8 +86342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9402/14932 [13:30<07:56, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  63%|▋| 9402/14932 [13:30<07:56, 11.60it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  63%|▋| 9403/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  63%|▋| 9403/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -86492,8 +86351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9403/14932 [13:30<07:56, 11.59it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  63%|▋| 9403/14932 [13:30<07:56, 11.59it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  63%|▋| 9404/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  63%|▋| 9404/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -86501,8 +86360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9404/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  63%|▋| 9404/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=4.84"
+      "Epoch 0:  63%|▋| 9405/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  63%|▋| 9405/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -86510,8 +86369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9405/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=4.84\r",
-      "Epoch 0:  63%|▋| 9405/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  63%|▋| 9406/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  63%|▋| 9406/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -86519,8 +86378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9406/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  63%|▋| 9406/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  63%|▋| 9407/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  63%|▋| 9407/14932 [13:30<07:56, 11.60it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -86528,8 +86387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9407/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  63%|▋| 9407/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  63%|▋| 9408/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  63%|▋| 9408/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -86537,8 +86396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9408/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  63%|▋| 9408/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  63%|▋| 9409/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  63%|▋| 9409/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=0.83"
      ]
     },
     {
@@ -86546,8 +86405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9409/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  63%|▋| 9409/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  63%|▋| 9410/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=0.83\r",
+      "Epoch 0:  63%|▋| 9410/14932 [13:31<07:56, 11.60it/s, v_num=ui8w, train/loss=1.96"
      ]
     },
     {
@@ -86555,8 +86414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9410/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  63%|▋| 9410/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  63%|▋| 9411/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=1.96\r",
+      "Epoch 0:  63%|▋| 9411/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -86564,8 +86423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9411/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  63%|▋| 9411/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  63%|▋| 9412/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  63%|▋| 9412/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.23"
      ]
     },
     {
@@ -86573,8 +86432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9412/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  63%|▋| 9412/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=1.26"
+      "Epoch 0:  63%|▋| 9413/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.23\r",
+      "Epoch 0:  63%|▋| 9413/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -86582,8 +86441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9413/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=1.26\r",
-      "Epoch 0:  63%|▋| 9413/14932 [13:31<07:56, 11.59it/s, v_num=o30c, train/loss=0.95"
+      "Epoch 0:  63%|▋| 9414/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  63%|▋| 9414/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.05"
      ]
     },
     {
@@ -86591,8 +86450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9414/14932 [13:31<07:55, 11.59it/s, v_num=o30c, train/loss=0.95\r",
-      "Epoch 0:  63%|▋| 9414/14932 [13:31<07:55, 11.59it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  63%|▋| 9415/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.05\r",
+      "Epoch 0:  63%|▋| 9415/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -86600,8 +86459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9415/14932 [13:32<07:55, 11.59it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  63%|▋| 9415/14932 [13:32<07:55, 11.59it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  63%|▋| 9416/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  63%|▋| 9416/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -86609,8 +86468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9416/14932 [13:32<07:55, 11.59it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  63%|▋| 9416/14932 [13:32<07:55, 11.59it/s, v_num=o30c, train/loss=1.14"
+      "Epoch 0:  63%|▋| 9417/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  63%|▋| 9417/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -86618,8 +86477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9417/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=1.14\r",
-      "Epoch 0:  63%|▋| 9417/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  63%|▋| 9418/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  63%|▋| 9418/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -86627,8 +86486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9418/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  63%|▋| 9418/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  63%|▋| 9419/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  63%|▋| 9419/14932 [13:31<07:55, 11.60it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -86636,8 +86495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9419/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  63%|▋| 9419/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  63%|▋| 9420/14932 [13:32<07:55, 11.60it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  63%|▋| 9420/14932 [13:32<07:55, 11.60it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -86645,8 +86504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9420/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  63%|▋| 9420/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  63%|▋| 9421/14932 [13:32<07:55, 11.60it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  63%|▋| 9421/14932 [13:32<07:55, 11.60it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -86654,8 +86513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9421/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  63%|▋| 9421/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  63%|▋| 9422/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  63%|▋| 9422/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -86663,8 +86522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9422/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  63%|▋| 9422/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  63%|▋| 9423/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  63%|▋| 9423/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -86672,8 +86531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9423/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  63%|▋| 9423/14932 [13:32<07:55, 11.60it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  63%|▋| 9424/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  63%|▋| 9424/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -86681,8 +86540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9424/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  63%|▋| 9424/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  63%|▋| 9425/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  63%|▋| 9425/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -86690,8 +86549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9425/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  63%|▋| 9425/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  63%|▋| 9426/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  63%|▋| 9426/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -86699,8 +86558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9426/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  63%|▋| 9426/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  63%|▋| 9427/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  63%|▋| 9427/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -86708,8 +86567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9427/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  63%|▋| 9427/14932 [13:32<07:54, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  63%|▋| 9428/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  63%|▋| 9428/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=1.93"
      ]
     },
     {
@@ -86717,8 +86576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9428/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  63%|▋| 9428/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  63%|▋| 9429/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=1.93\r",
+      "Epoch 0:  63%|▋| 9429/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -86726,8 +86585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9429/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  63%|▋| 9429/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  63%|▋| 9430/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  63%|▋| 9430/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -86735,8 +86594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9430/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  63%|▋| 9430/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  63%|▋| 9431/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  63%|▋| 9431/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -86744,8 +86603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9431/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  63%|▋| 9431/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  63%|▋| 9432/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  63%|▋| 9432/14932 [13:32<07:54, 11.60it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -86753,8 +86612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9432/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  63%|▋| 9432/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  63%|▋| 9433/14932 [13:32<07:53, 11.60it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  63%|▋| 9433/14932 [13:32<07:53, 11.60it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -86762,8 +86621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9433/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  63%|▋| 9433/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  63%|▋| 9434/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  63%|▋| 9434/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -86771,8 +86630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9434/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  63%|▋| 9434/14932 [13:33<07:54, 11.60it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  63%|▋| 9435/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  63%|▋| 9435/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -86780,8 +86639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9435/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  63%|▋| 9435/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=1.89"
+      "Epoch 0:  63%|▋| 9436/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  63%|▋| 9436/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -86789,8 +86648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9436/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=1.89\r",
-      "Epoch 0:  63%|▋| 9436/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  63%|▋| 9437/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  63%|▋| 9437/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -86798,8 +86657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9437/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  63%|▋| 9437/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  63%|▋| 9438/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  63%|▋| 9438/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -86807,8 +86666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9438/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  63%|▋| 9438/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  63%|▋| 9439/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  63%|▋| 9439/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -86816,8 +86675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9439/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  63%|▋| 9439/14932 [13:33<07:53, 11.60it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  63%|▋| 9440/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  63%|▋| 9440/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -86825,8 +86684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9440/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  63%|▋| 9440/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  63%|▋| 9441/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  63%|▋| 9441/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -86834,8 +86693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9441/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  63%|▋| 9441/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  63%|▋| 9442/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  63%|▋| 9442/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -86843,7 +86702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9442/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  63%|▋| 9443/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  63%|▋| 9443/14932 [13:33<07:53, 11.60it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -86851,7 +86711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9442/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  63%|▋| 9444/14932 [13:34<07:53, 11.60it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  63%|▋| 9444/14932 [13:34<07:53, 11.60it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -86859,8 +86720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9443/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  63%|▋| 9443/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  63%|▋| 9445/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  63%|▋| 9445/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -86868,8 +86729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9444/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  63%|▋| 9444/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  63%|▋| 9446/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  63%|▋| 9446/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -86877,8 +86738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9445/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  63%|▋| 9445/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  63%|▋| 9447/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  63%|▋| 9447/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -86886,8 +86747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9446/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  63%|▋| 9446/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=1.57"
+      "Epoch 0:  63%|▋| 9448/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  63%|▋| 9448/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=0.82"
      ]
     },
     {
@@ -86895,8 +86756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9447/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=1.57\r",
-      "Epoch 0:  63%|▋| 9447/14932 [13:34<07:53, 11.59it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  63%|▋| 9449/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=0.82\r",
+      "Epoch 0:  63%|▋| 9449/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -86904,8 +86765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9448/14932 [13:34<07:52, 11.59it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  63%|▋| 9448/14932 [13:34<07:52, 11.59it/s, v_num=o30c, train/loss=2.72"
+      "Epoch 0:  63%|▋| 9450/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  63%|▋| 9450/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -86913,8 +86774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9449/14932 [13:34<07:52, 11.59it/s, v_num=o30c, train/loss=2.72\r",
-      "Epoch 0:  63%|▋| 9449/14932 [13:34<07:52, 11.59it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  63%|▋| 9451/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  63%|▋| 9451/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -86922,8 +86783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9450/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  63%|▋| 9450/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  63%|▋| 9452/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  63%|▋| 9452/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -86931,8 +86792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9451/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  63%|▋| 9451/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  63%|▋| 9453/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  63%|▋| 9453/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -86940,8 +86801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9452/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  63%|▋| 9452/14932 [13:35<07:52, 11.59it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  63%|▋| 9454/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  63%|▋| 9454/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -86949,8 +86810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9453/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  63%|▋| 9453/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  63%|▋| 9455/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  63%|▋| 9455/14932 [13:34<07:52, 11.60it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -86958,8 +86819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9454/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  63%|▋| 9454/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  63%|▋| 9456/14932 [13:34<07:51, 11.60it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  63%|▋| 9456/14932 [13:34<07:51, 11.60it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -86967,8 +86828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9455/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  63%|▋| 9455/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  63%|▋| 9457/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  63%|▋| 9457/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -86976,8 +86837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9456/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  63%|▋| 9456/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  63%|▋| 9458/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  63%|▋| 9458/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=4.88"
      ]
     },
     {
@@ -86985,8 +86846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9457/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  63%|▋| 9457/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  63%|▋| 9459/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=4.88\r",
+      "Epoch 0:  63%|▋| 9459/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -86994,8 +86855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9458/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  63%|▋| 9458/14932 [13:35<07:52, 11.60it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  63%|▋| 9460/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  63%|▋| 9460/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -87003,8 +86864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9459/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  63%|▋| 9459/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  63%|▋| 9461/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  63%|▋| 9461/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -87012,8 +86873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9460/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  63%|▋| 9460/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  63%|▋| 9462/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  63%|▋| 9462/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -87021,8 +86882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9461/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  63%|▋| 9461/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  63%|▋| 9463/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  63%|▋| 9463/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -87030,8 +86891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9462/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  63%|▋| 9462/14932 [13:35<07:51, 11.60it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  63%|▋| 9464/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  63%|▋| 9464/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -87039,8 +86900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9463/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  63%|▋| 9463/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  63%|▋| 9465/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  63%|▋| 9465/14932 [13:35<07:51, 11.60it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -87048,8 +86909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9464/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  63%|▋| 9464/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  63%|▋| 9466/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  63%|▋| 9466/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -87057,8 +86918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9465/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  63%|▋| 9465/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=1.76"
+      "Epoch 0:  63%|▋| 9467/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  63%|▋| 9467/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -87066,8 +86927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9466/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=1.76\r",
-      "Epoch 0:  63%|▋| 9466/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  63%|▋| 9468/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  63%|▋| 9468/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -87075,8 +86936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9467/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  63%|▋| 9467/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  63%|▋| 9469/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  63%|▋| 9469/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -87084,8 +86945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9468/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  63%|▋| 9468/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  63%|▋| 9470/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  63%|▋| 9470/14932 [13:35<07:50, 11.61it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -87093,8 +86954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9469/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  63%|▋| 9469/14932 [13:36<07:51, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  63%|▋| 9471/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  63%|▋| 9471/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -87102,7 +86963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9470/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  63%|▋| 9472/14932 [13:36<07:50, 11.60it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  63%|▋| 9472/14932 [13:36<07:50, 11.60it/s, v_num=ui8w, train/loss=1.89"
      ]
     },
     {
@@ -87110,7 +86972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9470/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  63%|▋| 9473/14932 [13:36<07:50, 11.60it/s, v_num=ui8w, train/loss=1.89\r",
+      "Epoch 0:  63%|▋| 9473/14932 [13:36<07:50, 11.60it/s, v_num=ui8w, train/loss=1.59"
      ]
     },
     {
@@ -87118,8 +86981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9471/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  63%|▋| 9471/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  63%|▋| 9474/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=1.59\r",
+      "Epoch 0:  63%|▋| 9474/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=1.63"
      ]
     },
     {
@@ -87127,8 +86990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9472/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  63%|▋| 9472/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  63%|▋| 9475/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=1.63\r",
+      "Epoch 0:  63%|▋| 9475/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -87136,8 +86999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9473/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  63%|▋| 9473/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=2.38"
+      "Epoch 0:  63%|▋| 9476/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  63%|▋| 9476/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -87145,8 +87008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9474/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=2.38\r",
-      "Epoch 0:  63%|▋| 9474/14932 [13:36<07:50, 11.60it/s, v_num=o30c, train/loss=2.30"
+      "Epoch 0:  63%|▋| 9477/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  63%|▋| 9477/14932 [13:36<07:50, 11.61it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -87154,8 +87017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|��| 9475/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=2.30\r",
-      "Epoch 0:  63%|▋| 9475/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  63%|▋| 9478/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  63%|▋| 9478/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -87163,8 +87026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9476/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  63%|▋| 9476/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  63%|▋| 9479/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  63%|▋| 9479/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -87172,8 +87035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9477/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  63%|▋| 9477/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=1.25"
+      "Epoch 0:  63%|▋| 9480/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  63%|▋| 9480/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -87181,8 +87044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9478/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=1.25\r",
-      "Epoch 0:  63%|▋| 9478/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  63%|▋| 9481/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  63%|▋| 9481/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -87190,8 +87053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9479/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  63%|▋| 9479/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  64%|▋| 9482/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  64%|▋| 9482/14932 [13:36<07:49, 11.61it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -87199,8 +87062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9480/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  63%|▋| 9480/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  64%|▋| 9483/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  64%|▋| 9483/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -87208,8 +87071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  63%|▋| 9481/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  63%|▋| 9481/14932 [13:37<07:50, 11.60it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  64%|▋| 9484/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  64%|▋| 9484/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -87217,8 +87080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9482/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  64%|▋| 9482/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=1.43"
+      "Epoch 0:  64%|▋| 9485/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  64%|▋| 9485/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -87226,8 +87089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9483/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=1.43\r",
-      "Epoch 0:  64%|▋| 9483/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  64%|▋| 9486/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  64%|▋| 9486/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -87235,8 +87098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9484/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  64%|▋| 9484/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  64%|▋| 9487/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  64%|▋| 9487/14932 [13:37<07:49, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -87244,8 +87107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9485/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  64%|▋| 9485/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  64%|▋| 9488/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  64%|▋| 9488/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -87253,8 +87116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9486/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  64%|▋| 9486/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  64%|▋| 9489/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  64%|▋| 9489/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -87262,8 +87125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9487/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  64%|▋| 9487/14932 [13:37<07:49, 11.60it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  64%|▋| 9490/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  64%|▋| 9490/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -87271,8 +87134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9488/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  64%|▋| 9488/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  64%|▋| 9491/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  64%|▋| 9491/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -87280,8 +87143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9489/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  64%|▋| 9489/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  64%|▋| 9492/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  64%|▋| 9492/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -87289,8 +87152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9490/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  64%|▋| 9490/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  64%|▋| 9493/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  64%|▋| 9493/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -87298,8 +87161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9491/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  64%|▋| 9491/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=5.00"
+      "Epoch 0:  64%|▋| 9494/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  64%|▋| 9494/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=4.59"
      ]
     },
     {
@@ -87307,8 +87170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9492/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=5.00\r",
-      "Epoch 0:  64%|▋| 9492/14932 [13:38<07:49, 11.60it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  64%|▋| 9495/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=4.59\r",
+      "Epoch 0:  64%|▋| 9495/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=5.66"
      ]
     },
     {
@@ -87316,8 +87179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9493/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  64%|▋| 9493/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  64%|▋| 9496/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=5.66\r",
+      "Epoch 0:  64%|▋| 9496/14932 [13:37<07:48, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -87325,8 +87188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9494/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  64%|▋| 9494/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  64%|▋| 9497/14932 [13:38<07:48, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  64%|▋| 9497/14932 [13:38<07:48, 11.61it/s, v_num=ui8w, train/loss=1.21"
      ]
     },
     {
@@ -87334,8 +87197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9495/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  64%|▋| 9495/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  64%|▋| 9498/14932 [13:38<07:48, 11.61it/s, v_num=ui8w, train/loss=1.21\r",
+      "Epoch 0:  64%|▋| 9498/14932 [13:38<07:48, 11.61it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -87343,8 +87206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9496/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  64%|▋| 9496/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  64%|▋| 9499/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  64%|▋| 9499/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -87352,8 +87215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9497/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  64%|▋| 9497/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.09"
+      "Epoch 0:  64%|▋| 9500/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  64%|▋| 9500/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -87361,8 +87224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9498/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.09\r",
-      "Epoch 0:  64%|▋| 9498/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  64%|▋| 9501/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  64%|▋| 9501/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -87370,8 +87233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9499/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  64%|▋| 9499/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.72"
+      "Epoch 0:  64%|▋| 9502/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  64%|▋| 9502/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -87379,8 +87242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9500/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=3.72\r",
-      "Epoch 0:  64%|▋| 9500/14932 [13:38<07:48, 11.60it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  64%|▋| 9503/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  64%|▋| 9503/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=1.14"
      ]
     },
     {
@@ -87388,8 +87251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9501/14932 [13:39<07:48, 11.60it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  64%|▋| 9501/14932 [13:39<07:48, 11.60it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  64%|▋| 9504/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=1.14\r",
+      "Epoch 0:  64%|▋| 9504/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -87397,8 +87260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9502/14932 [13:39<07:48, 11.60it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  64%|▋| 9502/14932 [13:39<07:48, 11.60it/s, v_num=o30c, train/loss=2.48"
+      "Epoch 0:  64%|▋| 9505/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  64%|▋| 9505/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -87406,8 +87269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9503/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=2.48\r",
-      "Epoch 0:  64%|▋| 9503/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  64%|▋| 9506/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  64%|▋| 9506/14932 [13:38<07:47, 11.61it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -87415,8 +87278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9504/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  64%|▋| 9504/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  64%|▋| 9507/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  64%|▋| 9507/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -87424,8 +87287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9505/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  64%|▋| 9505/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  64%|▋| 9508/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  64%|▋| 9508/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -87433,8 +87296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9506/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  64%|▋| 9506/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  64%|▋| 9509/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  64%|▋| 9509/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=1.58"
      ]
     },
     {
@@ -87442,8 +87305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9507/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  64%|▋| 9507/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  64%|▋| 9510/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=1.58\r",
+      "Epoch 0:  64%|▋| 9510/14932 [13:39<07:47, 11.61it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -87451,8 +87314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9508/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  64%|▋| 9508/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  64%|▋| 9511/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  64%|▋| 9511/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -87460,8 +87323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9509/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  64%|▋| 9509/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  64%|▋| 9512/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  64%|▋| 9512/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -87469,8 +87332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9510/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  64%|▋| 9510/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  64%|▋| 9513/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  64%|▋| 9513/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -87478,8 +87341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9511/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  64%|▋| 9511/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  64%|▋| 9514/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  64%|▋| 9514/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -87487,8 +87350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9512/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  64%|▋| 9512/14932 [13:39<07:47, 11.60it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  64%|▋| 9515/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  64%|▋| 9515/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -87496,8 +87359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9513/14932 [13:40<07:47, 11.60it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  64%|▋| 9513/14932 [13:40<07:47, 11.60it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  64%|▋| 9516/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  64%|▋| 9516/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -87505,8 +87368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9514/14932 [13:40<07:47, 11.60it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  64%|▋| 9514/14932 [13:40<07:47, 11.60it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  64%|▋| 9517/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  64%|▋| 9517/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -87514,8 +87377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9515/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  64%|▋| 9515/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  64%|▋| 9518/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  64%|▋| 9518/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -87523,8 +87386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9516/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  64%|▋| 9516/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  64%|▋| 9519/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  64%|▋| 9519/14932 [13:39<07:46, 11.61it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -87532,8 +87395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9517/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  64%|▋| 9517/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  64%|▋| 9520/14932 [13:40<07:46, 11.61it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  64%|▋| 9520/14932 [13:40<07:46, 11.61it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -87541,8 +87404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9518/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  64%|▋| 9518/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  64%|▋| 9521/14932 [13:40<07:46, 11.61it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  64%|▋| 9521/14932 [13:40<07:46, 11.61it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -87550,8 +87413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9519/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  64%|▋| 9519/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  64%|▋| 9522/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  64%|▋| 9522/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.78"
      ]
     },
     {
@@ -87559,8 +87422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9520/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  64%|▋| 9520/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  64%|▋| 9523/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.78\r",
+      "Epoch 0:  64%|▋| 9523/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.20"
      ]
     },
     {
@@ -87568,8 +87431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9521/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  64%|▋| 9521/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  64%|▋| 9524/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.20\r",
+      "Epoch 0:  64%|▋| 9524/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -87577,8 +87440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9522/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  64%|▋| 9522/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=1.62"
+      "Epoch 0:  64%|▋| 9525/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  64%|▋| 9525/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -87586,8 +87449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9523/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=1.62\r",
-      "Epoch 0:  64%|▋| 9523/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  64%|▋| 9526/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  64%|▋| 9526/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -87595,8 +87458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9524/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  64%|▋| 9524/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  64%|▋| 9527/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  64%|▋| 9527/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -87604,8 +87467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9525/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  64%|▋| 9525/14932 [13:40<07:46, 11.60it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  64%|▋| 9528/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  64%|▋| 9528/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=4.47"
      ]
     },
     {
@@ -87613,8 +87476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9526/14932 [13:40<07:45, 11.60it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  64%|▋| 9526/14932 [13:40<07:45, 11.60it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  64%|▋| 9529/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=4.47\r",
+      "Epoch 0:  64%|▋| 9529/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -87622,8 +87485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9527/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  64%|▋| 9527/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  64%|▋| 9530/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  64%|▋| 9530/14932 [13:40<07:45, 11.61it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -87631,8 +87494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9528/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  64%|▋| 9528/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  64%|▋| 9531/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  64%|▋| 9531/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -87640,8 +87503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9529/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  64%|▋| 9529/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  64%|▋| 9532/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  64%|▋| 9532/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=2.03"
      ]
     },
     {
@@ -87649,8 +87512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9530/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  64%|▋| 9530/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  64%|▋| 9533/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=2.03\r",
+      "Epoch 0:  64%|▋| 9533/14932 [13:41<07:45, 11.61it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -87658,8 +87521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9531/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  64%|▋| 9531/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  64%|▋| 9534/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  64%|▋| 9534/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=4.28"
      ]
     },
     {
@@ -87667,8 +87530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9532/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  64%|▋| 9532/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.40"
+      "Epoch 0:  64%|▋| 9535/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=4.28\r",
+      "Epoch 0:  64%|▋| 9535/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.48"
      ]
     },
     {
@@ -87676,8 +87539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9533/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=1.40\r",
-      "Epoch 0:  64%|▋| 9533/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  64%|▋| 9536/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.48\r",
+      "Epoch 0:  64%|▋| 9536/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.90"
      ]
     },
     {
@@ -87685,8 +87548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9534/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  64%|▋| 9534/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  64%|▋| 9537/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.90\r",
+      "Epoch 0:  64%|▋| 9537/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -87694,8 +87557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9535/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  64%|▋| 9535/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  64%|▋| 9538/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  64%|▋| 9538/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -87703,8 +87566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9536/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  64%|▋| 9536/14932 [13:41<07:45, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  64%|▋| 9539/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  64%|▋| 9539/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -87712,8 +87575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9537/14932 [13:41<07:44, 11.60it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  64%|▋| 9537/14932 [13:41<07:44, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  64%|▋| 9540/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  64%|▋| 9540/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -87721,8 +87584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9538/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  64%|▋| 9538/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  64%|▋| 9541/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  64%|▋| 9541/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -87730,8 +87593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9539/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  64%|▋| 9539/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  64%|▋| 9542/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  64%|▋| 9542/14932 [13:41<07:44, 11.61it/s, v_num=ui8w, train/loss=1.24"
      ]
     },
     {
@@ -87739,8 +87602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9540/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  64%|▋| 9540/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  64%|▋| 9543/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=1.24\r",
+      "Epoch 0:  64%|▋| 9543/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -87748,8 +87611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9541/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  64%|▋| 9541/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  64%|▋| 9544/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  64%|▋| 9544/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -87757,8 +87620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9542/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  64%|▋| 9542/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  64%|▋| 9545/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  64%|▋| 9545/14932 [13:42<07:44, 11.61it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -87766,8 +87629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9543/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  64%|▋| 9543/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  64%|▋| 9546/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  64%|▋| 9546/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -87775,8 +87638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9544/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  64%|▋| 9544/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=4.47"
+      "Epoch 0:  64%|▋| 9547/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  64%|▋| 9547/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -87784,8 +87647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9545/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=4.47\r",
-      "Epoch 0:  64%|▋| 9545/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  64%|▋| 9548/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  64%|▋| 9548/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -87793,8 +87656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9546/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  64%|▋| 9546/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  64%|▋| 9549/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  64%|▋| 9549/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -87802,8 +87665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9547/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  64%|▋| 9547/14932 [13:42<07:44, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  64%|▋| 9550/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  64%|▋| 9550/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -87811,8 +87674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9548/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  64%|▋| 9548/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  64%|▋| 9551/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  64%|▋| 9551/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -87820,8 +87683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9549/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  64%|▋| 9549/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  64%|▋| 9552/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  64%|▋| 9552/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -87829,8 +87692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9550/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  64%|▋| 9550/14932 [13:42<07:43, 11.60it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  64%|▋| 9553/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  64%|▋| 9553/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -87838,8 +87701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9551/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  64%|▋| 9551/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  64%|▋| 9554/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  64%|▋| 9554/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -87847,8 +87710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9552/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  64%|▋| 9552/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  64%|▋| 9555/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  64%|▋| 9555/14932 [13:42<07:43, 11.61it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -87856,8 +87719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9553/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  64%|▋| 9553/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  64%|▋| 9556/14932 [13:43<07:43, 11.61it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  64%|▋| 9556/14932 [13:43<07:43, 11.61it/s, v_num=ui8w, train/loss=3.50"
      ]
     },
     {
@@ -87865,8 +87728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9554/14932 [13:43<07:43, 11.61it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  64%|▋| 9554/14932 [13:43<07:43, 11.61it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  64%|▋| 9557/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.50\r",
+      "Epoch 0:  64%|▋| 9557/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.27"
      ]
     },
     {
@@ -87874,8 +87737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9555/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  64%|▋| 9555/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  64%|▋| 9558/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.27\r",
+      "Epoch 0:  64%|▋| 9558/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -87883,8 +87746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9556/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  64%|▋| 9556/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  64%|▋| 9559/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  64%|▋| 9559/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.08"
      ]
     },
     {
@@ -87892,8 +87755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9557/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  64%|▋| 9557/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  64%|▋| 9560/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.08\r",
+      "Epoch 0:  64%|▋| 9560/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=1.75"
      ]
     },
     {
@@ -87901,8 +87764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9558/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  64%|▋| 9558/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  64%|▋| 9561/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=1.75\r",
+      "Epoch 0:  64%|▋| 9561/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -87910,8 +87773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9559/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  64%|▋| 9559/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  64%|▋| 9562/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  64%|▋| 9562/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -87919,8 +87782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9560/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  64%|▋| 9560/14932 [13:43<07:43, 11.60it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  64%|▋| 9563/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  64%|▋| 9563/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -87928,8 +87791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9561/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  64%|▋| 9561/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  64%|▋| 9564/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  64%|▋| 9564/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -87937,8 +87800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9562/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  64%|▋| 9562/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  64%|▋| 9565/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=1.95\r",
+      "Epoch 0:  64%|▋| 9565/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -87946,8 +87809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9563/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  64%|▋| 9563/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=5.12"
+      "Epoch 0:  64%|▋| 9566/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  64%|▋| 9566/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -87955,8 +87818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9564/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=5.12\r",
-      "Epoch 0:  64%|▋| 9564/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  64%|▋| 9567/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  64%|▋| 9567/14932 [13:43<07:42, 11.61it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -87964,8 +87827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9565/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  64%|▋| 9565/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  64%|▋| 9568/14932 [13:44<07:42, 11.61it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  64%|▋| 9568/14932 [13:44<07:42, 11.61it/s, v_num=ui8w, train/loss=1.12"
      ]
     },
     {
@@ -87973,8 +87836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9566/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  64%|▋| 9566/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  64%|▋| 9569/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=1.12\r",
+      "Epoch 0:  64%|▋| 9569/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -87982,8 +87845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9567/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  64%|▋| 9567/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  64%|▋| 9570/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  64%|▋| 9570/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -87991,8 +87854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9568/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  64%|▋| 9568/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  64%|▋| 9571/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  64%|▋| 9571/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -88000,8 +87863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9569/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  64%|▋| 9569/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  64%|▋| 9572/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  64%|▋| 9572/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -88009,8 +87872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9570/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  64%|▋| 9570/14932 [13:44<07:42, 11.60it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  64%|▋| 9573/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  64%|▋| 9573/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -88018,8 +87881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9571/14932 [13:45<07:42, 11.60it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  64%|▋| 9571/14932 [13:45<07:42, 11.60it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  64%|▋| 9574/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  64%|▋| 9574/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -88027,8 +87890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9572/14932 [13:45<07:42, 11.60it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  64%|▋| 9572/14932 [13:45<07:42, 11.60it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  64%|▋| 9575/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  64%|▋| 9575/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -88036,8 +87899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9573/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  64%|▋| 9573/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  64%|▋| 9576/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  64%|▋| 9576/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -88045,8 +87908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9574/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  64%|▋| 9574/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  64%|▋| 9577/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  64%|▋| 9577/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -88054,8 +87917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9575/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  64%|▋| 9575/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  64%|▋| 9578/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  64%|▋| 9578/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -88063,8 +87926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9576/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  64%|▋| 9576/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=3.02"
+      "Epoch 0:  64%|▋| 9579/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  64%|▋| 9579/14932 [13:44<07:41, 11.61it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -88072,8 +87935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9577/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=3.02\r",
-      "Epoch 0:  64%|▋| 9577/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  64%|▋| 9580/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  64%|▋| 9580/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -88081,8 +87944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9578/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  64%|▋| 9578/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  64%|▋| 9581/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  64%|▋| 9581/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -88090,8 +87953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9579/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  64%|▋| 9579/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  64%|▋| 9582/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  64%|▋| 9582/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -88099,8 +87962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9580/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  64%|▋| 9580/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  64%|▋| 9583/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  64%|▋| 9583/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=1.44"
      ]
     },
     {
@@ -88108,8 +87971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9581/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  64%|▋| 9581/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  64%|▋| 9584/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=1.44\r",
+      "Epoch 0:  64%|▋| 9584/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -88117,8 +87980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9582/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  64%|▋| 9582/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  64%|▋| 9585/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  64%|▋| 9585/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=4.81"
      ]
     },
     {
@@ -88126,8 +87989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9583/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  64%|▋| 9583/14932 [13:45<07:41, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  64%|▋| 9586/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=4.81\r",
+      "Epoch 0:  64%|▋| 9586/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -88135,8 +87998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9584/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  64%|▋| 9584/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  64%|▋| 9587/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  64%|▋| 9587/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -88144,8 +88007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9585/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  64%|▋| 9585/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  64%|▋| 9588/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  64%|▋| 9588/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -88153,8 +88016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9586/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  64%|▋| 9586/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  64%|▋| 9589/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  64%|▋| 9589/14932 [13:45<07:40, 11.61it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -88162,8 +88025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9587/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  64%|▋| 9587/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  64%|▋| 9590/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  64%|▋| 9590/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -88171,8 +88034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9588/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  64%|▋| 9588/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  64%|▋| 9591/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  64%|▋| 9591/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=4.34"
      ]
     },
     {
@@ -88180,8 +88043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9589/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  64%|▋| 9589/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  64%|▋| 9592/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=4.34\r",
+      "Epoch 0:  64%|▋| 9592/14932 [13:45<07:39, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -88189,8 +88052,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9590/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  64%|▋| 9590/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=1.34"
+      "Epoch 0:  64%|▋| 9593/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -88198,8 +88060,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9591/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=1.34\r",
-      "Epoch 0:  64%|▋| 9591/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  64%|▋| 9593/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -88207,8 +88068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9592/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  64%|▋| 9592/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  64%|▋| 9594/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  64%|▋| 9594/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.64"
      ]
     },
     {
@@ -88216,8 +88077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9593/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  64%|▋| 9593/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  64%|▋| 9595/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.64\r",
+      "Epoch 0:  64%|▋| 9595/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -88225,8 +88086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9594/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  64%|▋| 9594/14932 [13:46<07:40, 11.60it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  64%|▋| 9596/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  64%|▋| 9596/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -88234,8 +88095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9595/14932 [13:46<07:39, 11.60it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  64%|▋| 9595/14932 [13:46<07:39, 11.60it/s, v_num=o30c, train/loss=1.90"
+      "Epoch 0:  64%|▋| 9597/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  64%|▋| 9597/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=1.41"
      ]
     },
     {
@@ -88243,8 +88104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9596/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=1.90\r",
-      "Epoch 0:  64%|▋| 9596/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  64%|▋| 9598/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=1.41\r",
+      "Epoch 0:  64%|▋| 9598/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -88252,8 +88113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9597/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  64%|▋| 9597/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  64%|▋| 9599/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  64%|▋| 9599/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -88261,8 +88122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9598/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  64%|▋| 9598/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  64%|▋| 9600/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  64%|▋| 9600/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -88270,8 +88131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9599/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  64%|▋| 9599/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  64%|▋| 9601/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  64%|▋| 9601/14932 [13:46<07:39, 11.61it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -88279,8 +88140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9600/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  64%|▋| 9600/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  64%|▋| 9602/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  64%|▋| 9602/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=3.47"
      ]
     },
     {
@@ -88288,8 +88149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9601/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  64%|▋| 9601/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=1.13"
+      "Epoch 0:  64%|▋| 9603/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=3.47\r",
+      "Epoch 0:  64%|▋| 9603/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -88297,8 +88158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9602/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=1.13\r",
-      "Epoch 0:  64%|▋| 9602/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  64%|▋| 9604/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  64%|▋| 9604/14932 [13:46<07:38, 11.61it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -88306,8 +88167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9603/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  64%|▋| 9603/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  64%|▋| 9605/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  64%|▋| 9605/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -88315,8 +88176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9604/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  64%|▋| 9604/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  64%|▋| 9606/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  64%|▋| 9606/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -88324,8 +88185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9605/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  64%|▋| 9605/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.44"
+      "Epoch 0:  64%|▋| 9607/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  64%|▋| 9607/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.55"
      ]
     },
     {
@@ -88333,8 +88194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9606/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=2.44\r",
-      "Epoch 0:  64%|▋| 9606/14932 [13:47<07:39, 11.60it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  64%|▋| 9608/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.55\r",
+      "Epoch 0:  64%|▋| 9608/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -88342,8 +88203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9607/14932 [13:47<07:38, 11.60it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  64%|▋| 9607/14932 [13:47<07:38, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  64%|▋| 9609/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  64%|▋| 9609/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -88351,8 +88212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9608/14932 [13:48<07:39, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  64%|▋| 9608/14932 [13:48<07:39, 11.60it/s, v_num=o30c, train/loss=4.31"
+      "Epoch 0:  64%|▋| 9610/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  64%|▋| 9610/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -88360,8 +88221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9609/14932 [13:48<07:39, 11.60it/s, v_num=o30c, train/loss=4.31\r",
-      "Epoch 0:  64%|▋| 9609/14932 [13:48<07:39, 11.60it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  64%|▋| 9611/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  64%|▋| 9611/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -88369,8 +88230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9610/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  64%|▋| 9610/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  64%|▋| 9612/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  64%|▋| 9612/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -88378,8 +88239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9611/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  64%|▋| 9611/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  64%|▋| 9613/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  64%|▋| 9613/14932 [13:47<07:38, 11.61it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -88387,8 +88248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9612/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  64%|▋| 9612/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  64%|▋| 9614/14932 [13:47<07:37, 11.61it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  64%|▋| 9614/14932 [13:47<07:37, 11.61it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -88396,8 +88257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9613/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  64%|▋| 9613/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  64%|▋| 9615/14932 [13:47<07:37, 11.61it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  64%|▋| 9615/14932 [13:47<07:37, 11.61it/s, v_num=ui8w, train/loss=3.91"
      ]
     },
     {
@@ -88405,8 +88266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9614/14932 [13:48<07:38, 11.60it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  64%|▋| 9614/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  64%|▋| 9616/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.91\r",
+      "Epoch 0:  64%|▋| 9616/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -88414,8 +88275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9615/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  64%|▋| 9615/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  64%|▋| 9617/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  64%|▋| 9617/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -88423,8 +88284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9616/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  64%|▋| 9616/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  64%|▋| 9618/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  64%|▋| 9618/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -88432,8 +88293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9617/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  64%|▋| 9617/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  64%|▋| 9619/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  64%|▋| 9619/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -88441,8 +88302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9618/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  64%|▋| 9618/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  64%|▋| 9620/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  64%|▋| 9620/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=1.09"
      ]
     },
     {
@@ -88450,8 +88311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9619/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  64%|▋| 9619/14932 [13:49<07:38, 11.60it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  64%|▋| 9621/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=1.09\r",
+      "Epoch 0:  64%|▋| 9621/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -88459,8 +88320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9620/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  64%|▋| 9620/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  64%|▋| 9622/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  64%|▋| 9622/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -88468,8 +88329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9621/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  64%|▋| 9621/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.53"
+      "Epoch 0:  64%|▋| 9623/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  64%|▋| 9623/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -88477,8 +88338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9622/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.53\r",
-      "Epoch 0:  64%|▋| 9622/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  64%|▋| 9624/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  64%|▋| 9624/14932 [13:48<07:37, 11.61it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -88486,8 +88347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9623/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  64%|▋| 9623/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  64%|▋| 9625/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  64%|▋| 9625/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -88495,8 +88356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9624/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  64%|▋| 9624/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  64%|▋| 9626/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  64%|▋| 9626/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -88504,8 +88365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9625/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  64%|▋| 9625/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  64%|▋| 9627/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  64%|▋| 9627/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -88513,8 +88374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9626/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  64%|▋| 9626/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.12"
+      "Epoch 0:  64%|▋| 9628/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  64%|▋| 9628/14932 [13:48<07:36, 11.61it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -88522,8 +88383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9627/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=2.12\r",
-      "Epoch 0:  64%|▋| 9627/14932 [13:49<07:37, 11.60it/s, v_num=o30c, train/loss=4.12"
+      "Epoch 0:  64%|▋| 9629/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  64%|▋| 9629/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -88531,8 +88392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9628/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=4.12\r",
-      "Epoch 0:  64%|▋| 9628/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  64%|▋| 9630/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  64%|▋| 9630/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -88540,8 +88401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9629/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  64%|▋| 9629/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  64%|▋| 9631/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  64%|▋| 9631/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=1.69"
      ]
     },
     {
@@ -88549,8 +88410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9630/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  64%|▋| 9630/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  65%|▋| 9632/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=1.69\r",
+      "Epoch 0:  65%|▋| 9632/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -88558,8 +88419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  64%|▋| 9631/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  64%|▋| 9631/14932 [13:50<07:37, 11.60it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  65%|▋| 9633/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  65%|▋| 9633/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -88567,8 +88428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9632/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  65%|▋| 9632/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  65%|▋| 9634/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  65%|▋| 9634/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -88576,8 +88437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9633/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  65%|▋| 9633/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  65%|▋| 9635/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  65%|▋| 9635/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -88585,8 +88446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9634/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  65%|▋| 9634/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  65%|▋| 9636/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  65%|▋| 9636/14932 [13:49<07:36, 11.61it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -88594,8 +88455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9635/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  65%|▋| 9635/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  65%|▋| 9637/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  65%|▋| 9637/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -88603,8 +88464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9636/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  65%|▋| 9636/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  65%|▋| 9638/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  65%|▋| 9638/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=5.06"
      ]
     },
     {
@@ -88612,8 +88473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9637/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  65%|▋| 9637/14932 [13:50<07:36, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  65%|▋| 9639/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=5.06\r",
+      "Epoch 0:  65%|▋| 9639/14932 [13:50<07:36, 11.61it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -88621,8 +88482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9638/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  65%|▋| 9638/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=4.72"
+      "Epoch 0:  65%|▋| 9640/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  65%|▋| 9640/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -88630,8 +88491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9639/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=4.72\r",
-      "Epoch 0:  65%|▋| 9639/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  65%|▋| 9641/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  65%|▋| 9641/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -88639,8 +88500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9640/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  65%|▋| 9640/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  65%|▋| 9642/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  65%|▋| 9642/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.61"
      ]
     },
     {
@@ -88648,8 +88509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9641/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  65%|▋| 9641/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  65%|▋| 9643/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.61\r",
+      "Epoch 0:  65%|▋| 9643/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -88657,8 +88518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9642/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  65%|▋| 9642/14932 [13:51<07:36, 11.59it/s, v_num=o30c, train/loss=1.66"
+      "Epoch 0:  65%|▋| 9644/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  65%|▋| 9644/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -88666,8 +88527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9643/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=1.66\r",
-      "Epoch 0:  65%|▋| 9643/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  65%|▋| 9645/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  65%|▋| 9645/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -88675,8 +88536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9644/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  65%|▋| 9644/14932 [13:51<07:36, 11.60it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  65%|▋| 9646/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  65%|▋| 9646/14932 [13:50<07:35, 11.61it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -88684,8 +88545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9645/14932 [13:51<07:35, 11.59it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  65%|▋| 9645/14932 [13:51<07:35, 11.59it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  65%|▋| 9647/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  65%|▋| 9647/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -88693,8 +88554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9646/14932 [13:51<07:35, 11.59it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  65%|▋| 9646/14932 [13:51<07:35, 11.59it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  65%|▋| 9648/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  65%|▋| 9648/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -88702,8 +88563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9647/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  65%|▋| 9647/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  65%|▋| 9649/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  65%|▋| 9649/14932 [13:51<07:35, 11.61it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -88711,8 +88572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9648/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  65%|▋| 9648/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  65%|▋| 9650/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  65%|▋| 9650/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -88720,8 +88581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9649/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  65%|▋| 9649/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.91"
+      "Epoch 0:  65%|▋| 9651/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  65%|▋| 9651/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -88729,8 +88590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9650/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=3.91\r",
-      "Epoch 0:  65%|▋| 9650/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=2.84"
+      "Epoch 0:  65%|▋| 9652/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  65%|▋| 9652/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -88738,8 +88599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9651/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=2.84\r",
-      "Epoch 0:  65%|▋| 9651/14932 [13:52<07:35, 11.59it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  65%|▋| 9653/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  65%|▋| 9653/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -88747,8 +88608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9652/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  65%|▋| 9652/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=2.00"
+      "Epoch 0:  65%|▋| 9654/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  65%|▋| 9654/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -88756,8 +88617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9653/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=2.00\r",
-      "Epoch 0:  65%|▋| 9653/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=2.52"
+      "Epoch 0:  65%|▋| 9655/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  65%|▋| 9655/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -88765,8 +88626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9654/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=2.52\r",
-      "Epoch 0:  65%|▋| 9654/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  65%|▋| 9656/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  65%|▋| 9656/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -88774,8 +88635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9655/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  65%|▋| 9655/14932 [13:52<07:35, 11.60it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  65%|▋| 9657/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  65%|▋| 9657/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -88783,8 +88644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9656/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  65%|▋| 9656/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.75"
+      "Epoch 0:  65%|▋| 9658/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  65%|▋| 9658/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -88792,8 +88653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9657/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.75\r",
-      "Epoch 0:  65%|▋| 9657/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  65%|▋| 9659/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  65%|▋| 9659/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=1.86"
      ]
     },
     {
@@ -88801,8 +88662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9658/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  65%|▋| 9658/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  65%|▋| 9660/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=1.86\r",
+      "Epoch 0:  65%|▋| 9660/14932 [13:51<07:34, 11.61it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -88810,8 +88671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9659/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  65%|▋| 9659/14932 [13:52<07:34, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  65%|▋| 9661/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  65%|▋| 9661/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.56"
      ]
     },
     {
@@ -88819,8 +88680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9660/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  65%|▋| 9660/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  65%|▋| 9662/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.56\r",
+      "Epoch 0:  65%|▋| 9662/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -88828,8 +88689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9661/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  65%|▋| 9661/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  65%|▋| 9663/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  65%|▋| 9663/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -88837,8 +88698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9662/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  65%|▋| 9662/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  65%|▋| 9664/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  65%|▋| 9664/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=0.94"
      ]
     },
     {
@@ -88846,8 +88707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9663/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  65%|▋| 9663/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  65%|▋| 9665/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=0.94\r",
+      "Epoch 0:  65%|▋| 9665/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -88855,8 +88716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9664/14932 [13:53<07:34, 11.59it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  65%|▋| 9664/14932 [13:53<07:34, 11.59it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  65%|▋| 9666/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  65%|▋| 9666/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -88864,8 +88725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9665/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  65%|▋| 9665/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.55"
+      "Epoch 0:  65%|▋| 9667/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  65%|▋| 9667/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -88873,8 +88734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9666/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=2.55\r",
-      "Epoch 0:  65%|▋| 9666/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  65%|▋| 9668/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  65%|▋| 9668/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.66"
      ]
     },
     {
@@ -88882,8 +88743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9667/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  65%|▋| 9667/14932 [13:53<07:34, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  65%|▋| 9669/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.66\r",
+      "Epoch 0:  65%|▋| 9669/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -88891,8 +88752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9668/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  65%|▋| 9668/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  65%|▋| 9670/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  65%|▋| 9670/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.69"
      ]
     },
     {
@@ -88900,8 +88761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9669/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  65%|▋| 9669/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=4.38"
+      "Epoch 0:  65%|▋| 9671/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.69\r",
+      "Epoch 0:  65%|▋| 9671/14932 [13:52<07:33, 11.61it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -88909,8 +88770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9670/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=4.38\r",
-      "Epoch 0:  65%|▋| 9670/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  65%|▋| 9672/14932 [13:52<07:32, 11.61it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  65%|▋| 9672/14932 [13:52<07:32, 11.61it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -88918,8 +88779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9671/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  65%|▋| 9671/14932 [13:53<07:33, 11.60it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  65%|▋| 9673/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  65%|▋| 9673/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -88927,8 +88788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9672/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  65%|▋| 9672/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  65%|▋| 9674/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  65%|▋| 9674/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=4.91"
      ]
     },
     {
@@ -88936,8 +88797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9673/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.34\r",
-      "Epoch 0:  65%|▋| 9673/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  65%|▋| 9675/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=4.91\r",
+      "Epoch 0:  65%|▋| 9675/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -88945,8 +88806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9674/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  65%|▋| 9674/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  65%|▋| 9676/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  65%|▋| 9676/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -88954,8 +88815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9675/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  65%|▋| 9675/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=1.67"
+      "Epoch 0:  65%|▋| 9677/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  65%|▋| 9677/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.39"
      ]
     },
     {
@@ -88963,8 +88824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9676/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=1.67\r",
-      "Epoch 0:  65%|▋| 9676/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  65%|▋| 9678/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.39\r",
+      "Epoch 0:  65%|▋| 9678/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -88972,8 +88833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9677/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  65%|▋| 9677/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.69"
+      "Epoch 0:  65%|▋| 9679/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  65%|▋| 9679/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -88981,8 +88842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9678/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=3.69\r",
-      "Epoch 0:  65%|▋| 9678/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  65%|▋| 9680/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  65%|▋| 9680/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.22"
      ]
     },
     {
@@ -88990,8 +88851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9679/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  65%|▋| 9679/14932 [13:54<07:33, 11.59it/s, v_num=o30c, train/loss=4.41"
+      "Epoch 0:  65%|▋| 9681/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=2.22\r",
+      "Epoch 0:  65%|▋| 9681/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -88999,8 +88860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9680/14932 [13:54<07:32, 11.59it/s, v_num=o30c, train/loss=4.41\r",
-      "Epoch 0:  65%|▋| 9680/14932 [13:54<07:32, 11.59it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  65%|▋| 9682/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  65%|▋| 9682/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -89008,8 +88869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9681/14932 [13:54<07:32, 11.59it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  65%|▋| 9681/14932 [13:54<07:32, 11.59it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  65%|▋| 9683/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  65%|▋| 9683/14932 [13:53<07:32, 11.61it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -89017,8 +88878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9682/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  65%|▋| 9682/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  65%|▋| 9684/14932 [13:53<07:31, 11.61it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  65%|▋| 9684/14932 [13:53<07:31, 11.61it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -89026,8 +88887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9683/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  65%|▋| 9683/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  65%|▋| 9685/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  65%|▋| 9685/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=2.11"
      ]
     },
     {
@@ -89035,8 +88896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9684/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  65%|▋| 9684/14932 [13:55<07:32, 11.59it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  65%|▋| 9686/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=2.11\r",
+      "Epoch 0:  65%|▋| 9686/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -89044,8 +88905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9685/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  65%|▋| 9685/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=1.60"
+      "Epoch 0:  65%|▋| 9687/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  65%|▋| 9687/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -89053,8 +88914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9686/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=1.60\r",
-      "Epoch 0:  65%|▋| 9686/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  65%|▋| 9688/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  65%|▋| 9688/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -89062,8 +88923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9687/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  65%|▋| 9687/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=1.47"
+      "Epoch 0:  65%|▋| 9689/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  65%|▋| 9689/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.34"
      ]
     },
     {
@@ -89071,8 +88932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9688/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=1.47\r",
-      "Epoch 0:  65%|▋| 9688/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  65%|▋| 9690/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.34\r",
+      "Epoch 0:  65%|▋| 9690/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.73"
      ]
     },
     {
@@ -89080,8 +88941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9689/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  65%|▋| 9689/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.53"
+      "Epoch 0:  65%|▋| 9691/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.73\r",
+      "Epoch 0:  65%|▋| 9691/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -89089,8 +88950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9690/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.53\r",
-      "Epoch 0:  65%|▋| 9690/14932 [13:55<07:32, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  65%|▋| 9692/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  65%|▋| 9692/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -89098,8 +88959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9691/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  65%|▋| 9691/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  65%|▋| 9693/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  65%|▋| 9693/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -89107,8 +88968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9692/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  65%|▋| 9692/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  65%|▋| 9694/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  65%|▋| 9694/14932 [13:54<07:31, 11.61it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -89116,8 +88977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9693/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  65%|▋| 9693/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  65%|▋| 9695/14932 [13:54<07:30, 11.61it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  65%|▋| 9695/14932 [13:54<07:30, 11.61it/s, v_num=ui8w, train/loss=2.30"
      ]
     },
     {
@@ -89125,8 +88986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9694/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  65%|▋| 9694/14932 [13:55<07:31, 11.60it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  65%|▋| 9696/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.30\r",
+      "Epoch 0:  65%|▋| 9696/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.54"
      ]
     },
     {
@@ -89134,8 +88995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9695/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  65%|▋| 9695/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  65%|▋| 9697/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.54\r",
+      "Epoch 0:  65%|▋| 9697/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=3.05"
      ]
     },
     {
@@ -89143,8 +89004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9696/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  65%|▋| 9696/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=4.22"
+      "Epoch 0:  65%|▋| 9698/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=3.05\r",
+      "Epoch 0:  65%|▋| 9698/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.17"
      ]
     },
     {
@@ -89152,8 +89013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9697/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=4.22\r",
-      "Epoch 0:  65%|▋| 9697/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  65%|▋| 9699/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.17\r",
+      "Epoch 0:  65%|▋| 9699/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -89161,8 +89022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9698/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  65%|▋| 9698/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=2.83"
+      "Epoch 0:  65%|▋| 9700/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  65%|▋| 9700/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -89170,8 +89031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9699/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=2.83\r",
-      "Epoch 0:  65%|▋| 9699/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.26"
+      "Epoch 0:  65%|▋| 9701/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  65%|▋| 9701/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -89179,8 +89040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9700/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.26\r",
-      "Epoch 0:  65%|▋| 9700/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  65%|▋| 9702/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  65%|▋| 9702/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.50"
      ]
     },
     {
@@ -89188,8 +89049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9701/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  65%|▋| 9701/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.81"
+      "Epoch 0:  65%|▋| 9703/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=1.50\r",
+      "Epoch 0:  65%|▋| 9703/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -89197,8 +89058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9702/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=1.81\r",
-      "Epoch 0:  65%|▋| 9702/14932 [13:56<07:31, 11.60it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  65%|▋| 9704/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  65%|▋| 9704/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -89206,8 +89067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9703/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  65%|▋| 9703/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  65%|▋| 9705/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  65%|▋| 9705/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -89215,8 +89076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9704/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  65%|▋| 9704/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  65%|▋| 9706/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  65%|▋| 9706/14932 [13:55<07:30, 11.61it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -89224,8 +89085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9705/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  65%|▋| 9705/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  65%|▋| 9707/14932 [13:55<07:29, 11.61it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  65%|▋| 9707/14932 [13:55<07:29, 11.61it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -89233,8 +89094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9706/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  65%|▋| 9706/14932 [13:56<07:30, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  65%|▋| 9708/14932 [13:55<07:29, 11.61it/s, v_num=ui8w, train/loss=4.22\r",
+      "Epoch 0:  65%|▋| 9708/14932 [13:55<07:29, 11.61it/s, v_num=ui8w, train/loss=1.62"
      ]
     },
     {
@@ -89242,8 +89103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9707/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  65%|▋| 9707/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  65%|▋| 9709/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=1.62\r",
+      "Epoch 0:  65%|▋| 9709/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -89251,8 +89112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9708/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  65%|▋| 9708/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  65%|▋| 9710/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  65%|▋| 9710/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -89260,8 +89121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9709/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  65%|▋| 9709/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.66"
+      "Epoch 0:  65%|▋| 9711/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  65%|▋| 9711/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.06"
      ]
     },
     {
@@ -89269,8 +89130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9710/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.66\r",
-      "Epoch 0:  65%|▋| 9710/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=1.99"
+      "Epoch 0:  65%|▋| 9712/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.06\r",
+      "Epoch 0:  65%|▋| 9712/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -89278,8 +89139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9711/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=1.99\r",
-      "Epoch 0:  65%|▋| 9711/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  65%|▋| 9713/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  65%|▋| 9713/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -89287,8 +89148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9712/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  65%|▋| 9712/14932 [13:57<07:30, 11.60it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  65%|▋| 9714/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  65%|▋| 9714/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -89296,8 +89157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9713/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  65%|▋| 9713/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  65%|▋| 9715/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  65%|▋| 9715/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=4.56"
      ]
     },
     {
@@ -89305,8 +89166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9714/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  65%|▋| 9714/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  65%|▋| 9716/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=4.56\r",
+      "Epoch 0:  65%|▋| 9716/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -89314,8 +89175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9715/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  65%|▋| 9715/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=1.41"
+      "Epoch 0:  65%|▋| 9717/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  65%|▋| 9717/14932 [13:56<07:29, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -89323,8 +89184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9716/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=1.41\r",
-      "Epoch 0:  65%|▋| 9716/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  65%|▋| 9718/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  65%|▋| 9718/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -89332,8 +89193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9717/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  65%|▋| 9717/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  65%|▋| 9719/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  65%|▋| 9719/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -89341,8 +89202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9718/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  65%|▋| 9718/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  65%|▋| 9720/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  65%|▋| 9720/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -89350,8 +89211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9719/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  65%|▋| 9719/14932 [13:57<07:29, 11.60it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  65%|▋| 9721/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  65%|▋| 9721/14932 [13:56<07:28, 11.61it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -89359,8 +89220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9720/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  65%|▋| 9720/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  65%|▋| 9722/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  65%|▋| 9722/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -89368,8 +89229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9721/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  65%|▋| 9721/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  65%|▋| 9723/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=1.91\r",
+      "Epoch 0:  65%|▋| 9723/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -89377,8 +89238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9722/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  65%|▋| 9722/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  65%|▋| 9724/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  65%|▋| 9724/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=1.60"
      ]
     },
     {
@@ -89386,8 +89247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9723/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  65%|▋| 9723/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  65%|▋| 9725/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=1.60\r",
+      "Epoch 0:  65%|▋| 9725/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=3.02"
      ]
     },
     {
@@ -89395,8 +89256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9724/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  65%|▋| 9724/14932 [13:58<07:29, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  65%|▋| 9726/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=3.02\r",
+      "Epoch 0:  65%|▋| 9726/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=0.90"
      ]
     },
     {
@@ -89404,8 +89265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9725/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  65%|▋| 9725/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  65%|▋| 9727/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=0.90\r",
+      "Epoch 0:  65%|▋| 9727/14932 [13:57<07:28, 11.62it/s, v_num=ui8w, train/loss=1.71"
      ]
     },
     {
@@ -89413,8 +89274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9726/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  65%|▋| 9726/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=1.65"
+      "Epoch 0:  65%|▋| 9728/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=1.71\r",
+      "Epoch 0:  65%|▋| 9728/14932 [13:57<07:28, 11.61it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -89422,8 +89283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9727/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=1.65\r",
-      "Epoch 0:  65%|▋| 9727/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  65%|▋| 9729/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  65%|▋| 9729/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -89431,8 +89292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9728/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  65%|▋| 9728/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=2.47"
+      "Epoch 0:  65%|▋| 9730/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  65%|▋| 9730/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -89440,8 +89301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9729/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=2.47\r",
-      "Epoch 0:  65%|▋| 9729/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  65%|▋| 9731/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  65%|▋| 9731/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -89449,8 +89310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9730/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  65%|▋| 9730/14932 [13:58<07:28, 11.60it/s, v_num=o30c, train/loss=1.91"
+      "Epoch 0:  65%|▋| 9732/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  65%|▋| 9732/14932 [13:57<07:27, 11.61it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -89458,8 +89319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9731/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=1.91\r",
-      "Epoch 0:  65%|▋| 9731/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  65%|▋| 9733/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  65%|▋| 9733/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -89467,8 +89328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9732/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  65%|▋| 9732/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  65%|▋| 9734/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  65%|▋| 9734/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=2.53"
      ]
     },
     {
@@ -89476,8 +89337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9733/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  65%|▋| 9733/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  65%|▋| 9735/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=2.53\r",
+      "Epoch 0:  65%|▋| 9735/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -89485,8 +89346,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9734/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  65%|▋| 9734/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  65%|▋| 9736/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=4.22"
      ]
     },
     {
@@ -89494,8 +89354,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9735/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  65%|▋| 9735/14932 [13:59<07:28, 11.60it/s, v_num=o30c, train/loss=3.58"
+      "Epoch 0:  65%|▋| 9736/14932 [13:58<07:27, 11.61it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -89503,8 +89362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9736/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.58\r",
-      "Epoch 0:  65%|▋| 9736/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  65%|▋| 9737/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  65%|▋| 9737/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -89512,8 +89371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9737/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  65%|▋| 9737/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  65%|▋| 9738/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  65%|▋| 9738/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=3.55"
      ]
     },
     {
@@ -89521,8 +89380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9738/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  65%|▋| 9738/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  65%|▋| 9739/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=3.55\r",
+      "Epoch 0:  65%|▋| 9739/14932 [13:58<07:27, 11.62it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -89530,8 +89389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9739/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  65%|▋| 9739/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  65%|▋| 9740/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  65%|▋| 9740/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -89539,8 +89398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9740/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  65%|▋| 9740/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  65%|▋| 9741/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  65%|▋| 9741/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -89548,8 +89407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9741/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  65%|▋| 9741/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  65%|▋| 9742/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  65%|▋| 9742/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -89557,8 +89416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9742/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  65%|▋| 9742/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  65%|▋| 9743/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  65%|▋| 9743/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=2.81"
      ]
     },
     {
@@ -89566,8 +89425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9743/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  65%|▋| 9743/14932 [13:59<07:27, 11.60it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  65%|▋| 9744/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=2.81\r",
+      "Epoch 0:  65%|▋| 9744/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -89575,8 +89434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9744/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  65%|▋| 9744/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  65%|▋| 9745/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  65%|▋| 9745/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -89584,8 +89443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9745/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  65%|▋| 9745/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  65%|▋| 9746/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  65%|▋| 9746/14932 [13:58<07:26, 11.62it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -89593,8 +89452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9746/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=2.86\r",
-      "Epoch 0:  65%|▋| 9746/14932 [14:00<07:27, 11.60it/s, v_num=o30c, train/loss=0.92"
+      "Epoch 0:  65%|▋| 9747/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  65%|▋| 9747/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -89602,8 +89461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9747/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=0.92\r",
-      "Epoch 0:  65%|▋| 9747/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  65%|▋| 9748/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  65%|▋| 9748/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -89611,8 +89470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9748/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  65%|▋| 9748/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.11"
+      "Epoch 0:  65%|▋| 9749/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  65%|▋| 9749/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=1.31"
      ]
     },
     {
@@ -89620,8 +89479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9749/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.11\r",
-      "Epoch 0:  65%|▋| 9749/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  65%|▋| 9750/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=1.31\r",
+      "Epoch 0:  65%|▋| 9750/14932 [13:59<07:26, 11.62it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -89629,8 +89488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9750/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  65%|▋| 9750/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=0.86"
+      "Epoch 0:  65%|▋| 9751/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  65%|▋| 9751/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -89638,8 +89497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9751/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=0.86\r",
-      "Epoch 0:  65%|▋| 9751/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=4.00"
+      "Epoch 0:  65%|▋| 9752/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  65%|▋| 9752/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=1.34"
      ]
     },
     {
@@ -89647,8 +89506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9752/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=4.00\r",
-      "Epoch 0:  65%|▋| 9752/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  65%|▋| 9753/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=1.34\r",
+      "Epoch 0:  65%|▋| 9753/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -89656,8 +89515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9753/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  65%|▋| 9753/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  65%|▋| 9754/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  65%|▋| 9754/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -89665,8 +89524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9754/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  65%|▋| 9754/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  65%|▋| 9755/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  65%|▋| 9755/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -89674,8 +89533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9755/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  65%|▋| 9755/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  65%|▋| 9756/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  65%|▋| 9756/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -89683,8 +89542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9756/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  65%|▋| 9756/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=1.84"
+      "Epoch 0:  65%|▋| 9757/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  65%|▋| 9757/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=4.41"
      ]
     },
     {
@@ -89692,8 +89551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9757/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=1.84\r",
-      "Epoch 0:  65%|▋| 9757/14932 [14:00<07:26, 11.60it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  65%|▋| 9758/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=4.41\r",
+      "Epoch 0:  65%|▋| 9758/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -89701,8 +89560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9758/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  65%|▋| 9758/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  65%|▋| 9759/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  65%|▋| 9759/14932 [13:59<07:25, 11.62it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -89710,8 +89569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9759/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  65%|▋| 9759/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.25"
+      "Epoch 0:  65%|▋| 9760/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  65%|▋| 9760/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=3.62"
      ]
     },
     {
@@ -89719,8 +89578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9760/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.25\r",
-      "Epoch 0:  65%|▋| 9760/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  65%|▋| 9761/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=3.62\r",
+      "Epoch 0:  65%|▋| 9761/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -89728,8 +89587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9761/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  65%|▋| 9761/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.78"
+      "Epoch 0:  65%|▋| 9762/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  65%|▋| 9762/14932 [14:00<07:25, 11.62it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -89737,8 +89596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9762/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.78\r",
-      "Epoch 0:  65%|▋| 9762/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  65%|▋| 9763/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  65%|▋| 9763/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -89746,8 +89605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9763/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  65%|▋| 9763/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  65%|▋| 9764/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  65%|▋| 9764/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -89755,8 +89614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9764/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  65%|▋| 9764/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  65%|▋| 9765/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  65%|▋| 9765/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.09"
      ]
     },
     {
@@ -89764,8 +89623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9765/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  65%|▋| 9765/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  65%|▋| 9766/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.09\r",
+      "Epoch 0:  65%|▋| 9766/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -89773,8 +89632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9766/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  65%|▋| 9766/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  65%|▋| 9767/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  65%|▋| 9767/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -89782,8 +89641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9767/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  65%|▋| 9767/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  65%|▋| 9768/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  65%|▋| 9768/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -89791,8 +89650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9768/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  65%|▋| 9768/14932 [14:01<07:25, 11.60it/s, v_num=o30c, train/loss=2.06"
+      "Epoch 0:  65%|▋| 9769/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  65%|▋| 9769/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -89800,8 +89659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9769/14932 [14:01<07:24, 11.60it/s, v_num=o30c, train/loss=2.06\r",
-      "Epoch 0:  65%|▋| 9769/14932 [14:01<07:24, 11.60it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  65%|▋| 9770/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  65%|▋| 9770/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -89809,8 +89668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9770/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  65%|▋| 9770/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  65%|▋| 9771/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  65%|▋| 9771/14932 [14:00<07:24, 11.62it/s, v_num=ui8w, train/loss=1.80"
      ]
     },
     {
@@ -89818,8 +89677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9771/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  65%|▋| 9771/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  65%|▋| 9772/14932 [14:01<07:24, 11.62it/s, v_num=ui8w, train/loss=1.80\r",
+      "Epoch 0:  65%|▋| 9772/14932 [14:01<07:24, 11.62it/s, v_num=ui8w, train/loss=2.88"
      ]
     },
     {
@@ -89827,8 +89686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9772/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  65%|▋| 9772/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  65%|▋| 9773/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=2.88\r",
+      "Epoch 0:  65%|▋| 9773/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -89836,8 +89695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9773/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  65%|▋| 9773/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  65%|▋| 9774/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  65%|▋| 9774/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -89845,8 +89704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9774/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  65%|▋| 9774/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  65%|▋| 9775/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  65%|▋| 9775/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=0.99"
      ]
     },
     {
@@ -89854,8 +89713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9775/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  65%|▋| 9775/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  65%|▋| 9776/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=0.99\r",
+      "Epoch 0:  65%|▋| 9776/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.30"
      ]
     },
     {
@@ -89863,8 +89722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9776/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  65%|▋| 9776/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  65%|▋| 9777/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.30\r",
+      "Epoch 0:  65%|▋| 9777/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -89872,8 +89731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9777/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  65%|▋| 9777/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.77"
+      "Epoch 0:  65%|▋| 9778/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  65%|▋| 9778/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -89881,8 +89740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9778/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=2.77\r",
-      "Epoch 0:  65%|▋| 9778/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  65%|▋| 9779/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  65%|▋| 9779/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -89890,8 +89749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9779/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  65%|▋| 9779/14932 [14:02<07:24, 11.60it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  65%|▋| 9780/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  65%|▋| 9780/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=1.67"
      ]
     },
     {
@@ -89899,8 +89758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  65%|▋| 9780/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  65%|▋| 9780/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  66%|▋| 9781/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=1.67\r",
+      "Epoch 0:  66%|▋| 9781/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=1.74"
      ]
     },
     {
@@ -89908,8 +89767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9781/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  66%|▋| 9781/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.17"
+      "Epoch 0:  66%|▋| 9782/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=1.74\r",
+      "Epoch 0:  66%|▋| 9782/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=0.80"
      ]
     },
     {
@@ -89917,8 +89776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9782/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.17\r",
-      "Epoch 0:  66%|▋| 9782/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.42"
+      "Epoch 0:  66%|▋| 9783/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=0.80\r",
+      "Epoch 0:  66%|▋| 9783/14932 [14:01<07:23, 11.62it/s, v_num=ui8w, train/loss=2.41"
      ]
     },
     {
@@ -89926,8 +89785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9783/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.42\r",
-      "Epoch 0:  66%|▋| 9783/14932 [14:02<07:23, 11.61it/s, v_num=o30c, train/loss=2.70"
+      "Epoch 0:  66%|▋| 9784/14932 [14:01<07:22, 11.62it/s, v_num=ui8w, train/loss=2.41\r",
+      "Epoch 0:  66%|▋| 9784/14932 [14:01<07:22, 11.62it/s, v_num=ui8w, train/loss=1.08"
      ]
     },
     {
@@ -89935,8 +89794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9784/14932 [14:03<07:23, 11.61it/s, v_num=o30c, train/loss=2.70\r",
-      "Epoch 0:  66%|▋| 9784/14932 [14:03<07:23, 11.61it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  66%|▋| 9785/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=1.08\r",
+      "Epoch 0:  66%|▋| 9785/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -89944,8 +89803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9785/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  66%|▋| 9785/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=4.69"
+      "Epoch 0:  66%|▋| 9786/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  66%|▋| 9786/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.41"
      ]
     },
     {
@@ -89953,8 +89812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9786/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=4.69\r",
-      "Epoch 0:  66%|▋| 9786/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=2.11"
+      "Epoch 0:  66%|▋| 9787/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.41\r",
+      "Epoch 0:  66%|▋| 9787/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.14"
      ]
     },
     {
@@ -89962,8 +89821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9787/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=2.11\r",
-      "Epoch 0:  66%|▋| 9787/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.80"
+      "Epoch 0:  66%|▋| 9788/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.14\r",
+      "Epoch 0:  66%|▋| 9788/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -89971,8 +89830,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9788/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.80\r",
-      "Epoch 0:  66%|▋| 9788/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  66%|▋| 9789/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=1.91"
      ]
     },
     {
@@ -89980,8 +89838,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9789/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  66%|▋| 9789/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  66%|▋| 9789/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -89989,8 +89846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9790/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  66%|▋| 9790/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=1.02"
+      "Epoch 0:  66%|▋| 9790/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  66%|▋| 9790/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -89998,8 +89855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9791/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=1.02\r",
-      "Epoch 0:  66%|▋| 9791/14932 [14:03<07:23, 11.60it/s, v_num=o30c, train/loss=1.95"
+      "Epoch 0:  66%|▋| 9791/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  66%|▋| 9791/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -90007,8 +89864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9792/14932 [14:03<07:22, 11.60it/s, v_num=o30c, train/loss=1.95\r",
-      "Epoch 0:  66%|▋| 9792/14932 [14:03<07:22, 11.60it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  66%|▋| 9792/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  66%|▋| 9792/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=4.16"
      ]
     },
     {
@@ -90016,8 +89873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9793/14932 [14:03<07:22, 11.60it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  66%|▋| 9793/14932 [14:03<07:22, 11.60it/s, v_num=o30c, train/loss=3.45"
+      "Epoch 0:  66%|▋| 9793/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=4.16\r",
+      "Epoch 0:  66%|▋| 9793/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.61"
      ]
     },
     {
@@ -90025,8 +89882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9794/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.45\r",
-      "Epoch 0:  66%|▋| 9794/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  66%|▋| 9794/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.61\r",
+      "Epoch 0:  66%|▋| 9794/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -90034,8 +89891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9795/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  66%|▋| 9795/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.78"
+      "Epoch 0:  66%|▋| 9795/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=3.12\r",
+      "Epoch 0:  66%|▋| 9795/14932 [14:02<07:22, 11.62it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -90043,8 +89900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9796/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.78\r",
-      "Epoch 0:  66%|▋| 9796/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  66%|▋| 9796/14932 [14:02<07:21, 11.62it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  66%|▋| 9796/14932 [14:02<07:21, 11.62it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -90052,7 +89909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9797/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  66%|▋| 9797/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  66%|▋| 9797/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.00"
      ]
     },
     {
@@ -90060,7 +89918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9797/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  66%|▋| 9798/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.00\r",
+      "Epoch 0:  66%|▋| 9798/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=1.10"
      ]
     },
     {
@@ -90068,8 +89927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9798/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  66%|▋| 9798/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  66%|▋| 9799/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=1.10\r",
+      "Epoch 0:  66%|▋| 9799/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -90077,8 +89936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9799/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  66%|▋| 9799/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  66%|▋| 9800/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  66%|▋| 9800/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -90086,8 +89945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9800/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  66%|▋| 9800/14932 [14:04<07:22, 11.60it/s, v_num=o30c, train/loss=4.62"
+      "Epoch 0:  66%|▋| 9801/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  66%|▋| 9801/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -90095,8 +89954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9801/14932 [14:04<07:22, 11.61it/s, v_num=o30c, train/loss=4.62\r",
-      "Epoch 0:  66%|▋| 9801/14932 [14:04<07:22, 11.61it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  66%|▋| 9802/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  66%|▋| 9802/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=1.07"
      ]
     },
     {
@@ -90104,8 +89963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9802/14932 [14:04<07:22, 11.61it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  66%|▋| 9802/14932 [14:04<07:22, 11.61it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  66%|▋| 9803/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=1.07\r",
+      "Epoch 0:  66%|▋| 9803/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -90113,8 +89972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9803/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  66%|▋| 9803/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  66%|▋| 9804/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  66%|▋| 9804/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -90122,8 +89981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9804/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  66%|▋| 9804/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  66%|▋| 9805/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  66%|▋| 9805/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -90131,8 +89990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9805/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  66%|▋| 9805/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  66%|▋| 9806/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  66%|▋| 9806/14932 [14:03<07:21, 11.62it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -90140,8 +89999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9806/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  66%|▋| 9806/14932 [14:04<07:21, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  66%|▋| 9807/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  66%|▋| 9807/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=1.42"
      ]
     },
     {
@@ -90149,7 +90008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9807/14932 [14:05<07:21, 11.60it/s, v_num=o30c, train/loss=2.86"
+      "Epoch 0:  66%|▋| 9808/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=1.42\r",
+      "Epoch 0:  66%|▋| 9808/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -90157,7 +90017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9807/14932 [14:05<07:21, 11.60it/s, v_num=o30c, train/loss=2.02"
+      "Epoch 0:  66%|▋| 9809/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  66%|▋| 9809/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=2.64"
      ]
     },
     {
@@ -90165,8 +90026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9808/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=2.02\r",
-      "Epoch 0:  66%|▋| 9808/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.88"
+      "Epoch 0:  66%|▋| 9810/14932 [14:03<07:20, 11.62it/s, v_num=ui8w, train/loss=2.64\r",
+      "Epoch 0:  66%|▋| 9810/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -90174,8 +90035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9809/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.88\r",
-      "Epoch 0:  66%|▋| 9809/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  66%|▋| 9811/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  66%|▋| 9811/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.03"
      ]
     },
     {
@@ -90183,8 +90044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9810/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  66%|▋| 9810/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  66%|▋| 9812/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.03\r",
+      "Epoch 0:  66%|▋| 9812/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=4.94"
      ]
     },
     {
@@ -90192,8 +90053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9811/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  66%|▋| 9811/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=4.19"
+      "Epoch 0:  66%|▋| 9813/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=4.94\r",
+      "Epoch 0:  66%|▋| 9813/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -90201,8 +90062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9812/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=4.19\r",
-      "Epoch 0:  66%|▋| 9812/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  66%|▋| 9814/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  66%|▋| 9814/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.31"
      ]
     },
     {
@@ -90210,8 +90071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9813/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  66%|▋| 9813/14932 [14:05<07:21, 11.61it/s, v_num=o30c, train/loss=3.92"
+      "Epoch 0:  66%|▋| 9815/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=3.31\r",
+      "Epoch 0:  66%|▋| 9815/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -90219,8 +90080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9814/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.92\r",
-      "Epoch 0:  66%|▋| 9814/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  66%|▋| 9816/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  66%|▋| 9816/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=2.86"
      ]
     },
     {
@@ -90228,8 +90089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9815/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  66%|▋| 9815/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=4.03"
+      "Epoch 0:  66%|▋| 9817/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=2.86\r",
+      "Epoch 0:  66%|▋| 9817/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -90237,8 +90098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9816/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=4.03\r",
-      "Epoch 0:  66%|▋| 9816/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.77"
+      "Epoch 0:  66%|▋| 9818/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  66%|▋| 9818/14932 [14:04<07:20, 11.62it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -90246,8 +90107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9817/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.77\r",
-      "Epoch 0:  66%|▋| 9817/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=1.59"
+      "Epoch 0:  66%|▋| 9819/14932 [14:04<07:19, 11.62it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  66%|▋| 9819/14932 [14:04<07:19, 11.62it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -90255,8 +90116,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9818/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=1.59\r",
-      "Epoch 0:  66%|▋| 9818/14932 [14:05<07:20, 11.61it/s, v_num=o30c, train/loss=3.61"
+      "Epoch 0:  66%|▋| 9820/14932 [14:04<07:19, 11.62it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -90264,8 +90124,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9819/14932 [14:06<07:20, 11.61it/s, v_num=o30c, train/loss=3.61\r",
-      "Epoch 0:  66%|▋| 9819/14932 [14:06<07:20, 11.61it/s, v_num=o30c, train/loss=3.41"
+      "Epoch 0:  66%|▋| 9820/14932 [14:04<07:19, 11.62it/s, v_num=ui8w, train/loss=3.97"
      ]
     },
     {
@@ -90273,8 +90132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9820/14932 [14:06<07:20, 11.61it/s, v_num=o30c, train/loss=3.41\r",
-      "Epoch 0:  66%|▋| 9820/14932 [14:06<07:20, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  66%|▋| 9821/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.97\r",
+      "Epoch 0:  66%|▋| 9821/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -90282,8 +90141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9821/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  66%|▋| 9821/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  66%|▋| 9822/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  66%|▋| 9822/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=1.16"
      ]
     },
     {
@@ -90291,8 +90150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9822/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  66%|▋| 9822/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.98"
+      "Epoch 0:  66%|▋| 9823/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=1.16\r",
+      "Epoch 0:  66%|▋| 9823/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.92"
      ]
     },
     {
@@ -90300,8 +90159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9823/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.98\r",
-      "Epoch 0:  66%|▋| 9823/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.47"
+      "Epoch 0:  66%|▋| 9824/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.92\r",
+      "Epoch 0:  66%|▋| 9824/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -90309,8 +90168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9824/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.47\r",
-      "Epoch 0:  66%|▋| 9824/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  66%|▋| 9825/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  66%|▋| 9825/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.75"
      ]
     },
     {
@@ -90318,8 +90177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9825/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  66%|▋| 9825/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  66%|▋| 9826/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.75\r",
+      "Epoch 0:  66%|▋| 9826/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -90327,8 +90186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9826/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  66%|▋| 9826/14932 [14:06<07:20, 11.60it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  66%|▋| 9827/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  66%|▋| 9827/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.22"
      ]
     },
     {
@@ -90336,8 +90195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9827/14932 [14:07<07:20, 11.60it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  66%|▋| 9827/14932 [14:07<07:20, 11.60it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  66%|▋| 9828/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.22\r",
+      "Epoch 0:  66%|▋| 9828/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.39"
      ]
     },
     {
@@ -90345,8 +90204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9828/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  66%|▋| 9828/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  66%|▋| 9829/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.39\r",
+      "Epoch 0:  66%|▋| 9829/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -90354,8 +90213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9829/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  66%|▋| 9829/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  66%|▋| 9830/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  66%|▋| 9830/14932 [14:05<07:19, 11.62it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -90363,8 +90222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9830/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  66%|▋| 9830/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  66%|▋| 9831/14932 [14:05<07:18, 11.62it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  66%|▋| 9831/14932 [14:05<07:18, 11.62it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -90372,8 +90231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9831/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  66%|▋| 9831/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.31"
+      "Epoch 0:  66%|▋| 9832/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  66%|▋| 9832/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=0.83"
      ]
     },
     {
@@ -90381,8 +90240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9832/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.31\r",
-      "Epoch 0:  66%|▋| 9832/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  66%|▋| 9833/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=0.83\r",
+      "Epoch 0:  66%|▋| 9833/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -90390,8 +90249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9833/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  66%|▋| 9833/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.41"
+      "Epoch 0:  66%|▋| 9834/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  66%|▋| 9834/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -90399,8 +90258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9834/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.41\r",
-      "Epoch 0:  66%|▋| 9834/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  66%|▋| 9835/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  66%|▋| 9835/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -90408,8 +90267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9835/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  66%|▋| 9835/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  66%|▋| 9836/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  66%|▋| 9836/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -90417,8 +90276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9836/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  66%|▋| 9836/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=1.83"
+      "Epoch 0:  66%|▋| 9837/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  66%|▋| 9837/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -90426,8 +90285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9837/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=1.83\r",
-      "Epoch 0:  66%|▋| 9837/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.58"
+      "Epoch 0:  66%|▋| 9838/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  66%|▋| 9838/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -90435,8 +90294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9838/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=2.58\r",
-      "Epoch 0:  66%|▋| 9838/14932 [14:07<07:19, 11.60it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  66%|▋| 9839/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  66%|▋| 9839/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -90444,8 +90303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9839/14932 [14:07<07:18, 11.60it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  66%|▋| 9839/14932 [14:07<07:18, 11.60it/s, v_num=o30c, train/loss=1.22"
+      "Epoch 0:  66%|▋| 9840/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  66%|▋| 9840/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -90453,8 +90312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9840/14932 [14:07<07:18, 11.60it/s, v_num=o30c, train/loss=1.22\r",
-      "Epoch 0:  66%|▋| 9840/14932 [14:07<07:18, 11.60it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  66%|▋| 9841/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  66%|▋| 9841/14932 [14:06<07:18, 11.62it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -90462,8 +90321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9841/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  66%|▋| 9841/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.62"
+      "Epoch 0:  66%|▋| 9842/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  66%|▋| 9842/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -90471,8 +90330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9842/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.62\r",
-      "Epoch 0:  66%|▋| 9842/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  66%|▋| 9843/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  66%|▋| 9843/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=2.02"
      ]
     },
     {
@@ -90480,8 +90339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9843/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  66%|▋| 9843/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=4.09"
+      "Epoch 0:  66%|▋| 9844/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=2.02\r",
+      "Epoch 0:  66%|▋| 9844/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=3.92"
      ]
     },
     {
@@ -90489,8 +90348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9844/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=4.09\r",
-      "Epoch 0:  66%|▋| 9844/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  66%|▋| 9845/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=3.92\r",
+      "Epoch 0:  66%|▋| 9845/14932 [14:06<07:17, 11.62it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -90498,8 +90357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9845/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  66%|▋| 9845/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=2.34"
+      "Epoch 0:  66%|▋| 9846/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  66%|▋| 9846/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.25"
      ]
     },
     {
@@ -90507,8 +90366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9846/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=2.34\r",
-      "Epoch 0:  66%|▋| 9846/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  66%|▋| 9847/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.25\r",
+      "Epoch 0:  66%|▋| 9847/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -90516,8 +90375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9847/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  66%|▋| 9847/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  66%|▋| 9848/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  66%|▋| 9848/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.38"
      ]
     },
     {
@@ -90525,8 +90384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9848/14932 [14:08<07:18, 11.61it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  66%|▋| 9848/14932 [14:08<07:18, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  66%|▋| 9849/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.38\r",
+      "Epoch 0:  66%|▋| 9849/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -90534,8 +90393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9849/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  66%|▋| 9849/14932 [14:08<07:18, 11.60it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  66%|▋| 9850/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  66%|▋| 9850/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -90543,8 +90402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9850/14932 [14:08<07:17, 11.60it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  66%|▋| 9850/14932 [14:08<07:17, 11.60it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  66%|▋| 9851/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  66%|▋| 9851/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -90552,8 +90411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9851/14932 [14:08<07:17, 11.60it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  66%|▋| 9851/14932 [14:08<07:17, 11.60it/s, v_num=o30c, train/loss=2.45"
+      "Epoch 0:  66%|▋| 9852/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  66%|▋| 9852/14932 [14:07<07:17, 11.62it/s, v_num=ui8w, train/loss=4.09"
      ]
     },
     {
@@ -90561,8 +90420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9852/14932 [14:08<07:17, 11.61it/s, v_num=o30c, train/loss=2.45\r",
-      "Epoch 0:  66%|▋| 9852/14932 [14:08<07:17, 11.61it/s, v_num=o30c, train/loss=2.22"
+      "Epoch 0:  66%|▋| 9853/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=4.09\r",
+      "Epoch 0:  66%|▋| 9853/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -90570,8 +90429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9853/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=2.22\r",
-      "Epoch 0:  66%|▋| 9853/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=0.80"
+      "Epoch 0:  66%|▋| 9854/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  66%|▋| 9854/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=2.50"
      ]
     },
     {
@@ -90579,8 +90438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9854/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=0.80\r",
-      "Epoch 0:  66%|▋| 9854/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  66%|▋| 9855/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=2.50\r",
+      "Epoch 0:  66%|▋| 9855/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -90588,8 +90447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9855/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  66%|▋| 9855/14932 [14:09<07:17, 11.61it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  66%|▋| 9856/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  66%|▋| 9856/14932 [14:07<07:16, 11.62it/s, v_num=ui8w, train/loss=3.25"
      ]
     },
     {
@@ -90597,8 +90456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9856/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  66%|▋| 9856/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  66%|▋| 9857/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.25\r",
+      "Epoch 0:  66%|▋| 9857/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -90606,8 +90465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9857/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  66%|▋| 9857/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  66%|▋| 9858/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  66%|▋| 9858/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -90615,8 +90474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9858/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  66%|▋| 9858/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  66%|▋| 9859/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  66%|▋| 9859/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -90624,8 +90483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9859/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  66%|▋| 9859/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.20"
+      "Epoch 0:  66%|▋| 9860/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  66%|▋| 9860/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -90633,8 +90492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9860/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.20\r",
-      "Epoch 0:  66%|▋| 9860/14932 [14:09<07:17, 11.60it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  66%|▋| 9861/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  66%|▋| 9861/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -90642,8 +90501,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9861/14932 [14:09<07:16, 11.60it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  66%|▋| 9861/14932 [14:09<07:16, 11.60it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  66%|▋| 9862/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -90651,8 +90509,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9862/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  66%|▋| 9862/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  66%|▋| 9862/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -90660,8 +90517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9863/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  66%|▋| 9863/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=4.88"
+      "Epoch 0:  66%|▋| 9863/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  66%|▋| 9863/14932 [14:08<07:16, 11.62it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -90669,8 +90526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9864/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=4.88\r",
-      "Epoch 0:  66%|▋| 9864/14932 [14:09<07:16, 11.61it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  66%|▋| 9864/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  66%|▋| 9864/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=1.92"
      ]
     },
     {
@@ -90678,8 +90535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9865/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  66%|▋| 9865/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  66%|▋| 9865/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=1.92\r",
+      "Epoch 0:  66%|▋| 9865/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -90687,8 +90544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9866/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  66%|▋| 9866/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  66%|▋| 9866/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  66%|▋| 9866/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -90696,8 +90553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9867/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  66%|▋| 9867/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  66%|▋| 9867/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  66%|▋| 9867/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -90705,8 +90562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9868/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  66%|▋| 9868/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.98"
+      "Epoch 0:  66%|▋| 9868/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  66%|▋| 9868/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -90714,8 +90571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9869/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.98\r",
-      "Epoch 0:  66%|▋| 9869/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  66%|▋| 9869/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  66%|▋| 9869/14932 [14:08<07:15, 11.62it/s, v_num=ui8w, train/loss=1.77"
      ]
     },
     {
@@ -90723,8 +90580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9870/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  66%|▋| 9870/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  66%|▋| 9870/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=1.77\r",
+      "Epoch 0:  66%|▋| 9870/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=3.72"
      ]
     },
     {
@@ -90732,8 +90589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9871/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  66%|▋| 9871/14932 [14:10<07:16, 11.61it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  66%|▋| 9871/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=3.72\r",
+      "Epoch 0:  66%|▋| 9871/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -90741,8 +90598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9872/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  66%|▋| 9872/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  66%|▋| 9872/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  66%|▋| 9872/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -90750,8 +90607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9873/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  66%|▋| 9873/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  66%|▋| 9873/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  66%|▋| 9873/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=1.70"
      ]
     },
     {
@@ -90759,8 +90616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9874/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  66%|▋| 9874/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  66%|▋| 9874/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=1.70\r",
+      "Epoch 0:  66%|▋| 9874/14932 [14:09<07:15, 11.63it/s, v_num=ui8w, train/loss=2.83"
      ]
     },
     {
@@ -90768,7 +90625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9875/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.34"
+      "Epoch 0:  66%|▋| 9875/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=2.83\r",
+      "Epoch 0:  66%|▋| 9875/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -90776,7 +90634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9875/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  66%|▋| 9876/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  66%|▋| 9876/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=1.56"
      ]
     },
     {
@@ -90784,8 +90643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9876/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  66%|▋| 9876/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  66%|▋| 9877/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=1.56\r",
+      "Epoch 0:  66%|▋| 9877/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -90793,8 +90652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9877/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  66%|▋| 9877/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  66%|▋| 9878/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  66%|▋| 9878/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=4.69"
      ]
     },
     {
@@ -90802,8 +90661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9878/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  66%|▋| 9878/14932 [14:10<07:15, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  66%|▋| 9879/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=4.69\r",
+      "Epoch 0:  66%|▋| 9879/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -90811,8 +90670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9879/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  66%|▋| 9879/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.08"
+      "Epoch 0:  66%|▋| 9880/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  66%|▋| 9880/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=2.59"
      ]
     },
     {
@@ -90820,8 +90679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9880/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.08\r",
-      "Epoch 0:  66%|▋| 9880/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  66%|▋| 9881/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=2.59\r",
+      "Epoch 0:  66%|▋| 9881/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.86"
      ]
     },
     {
@@ -90829,8 +90688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9881/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  66%|▋| 9881/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  66%|▋| 9882/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.86\r",
+      "Epoch 0:  66%|▋| 9882/14932 [14:09<07:14, 11.63it/s, v_num=ui8w, train/loss=3.69"
      ]
     },
     {
@@ -90838,8 +90697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9882/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  66%|▋| 9882/14932 [14:11<07:15, 11.61it/s, v_num=o30c, train/loss=1.38"
+      "Epoch 0:  66%|▋| 9883/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=3.69\r",
+      "Epoch 0:  66%|▋| 9883/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=4.44"
      ]
     },
     {
@@ -90847,8 +90706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9883/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=1.38\r",
-      "Epoch 0:  66%|▋| 9883/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  66%|▋| 9884/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=4.44\r",
+      "Epoch 0:  66%|▋| 9884/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=3.89"
      ]
     },
     {
@@ -90856,8 +90715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9884/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  66%|▋| 9884/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=1.71"
+      "Epoch 0:  66%|▋| 9885/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=3.89\r",
+      "Epoch 0:  66%|▋| 9885/14932 [14:10<07:14, 11.63it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -90865,8 +90724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9885/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=1.71\r",
-      "Epoch 0:  66%|▋| 9885/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  66%|▋| 9886/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  66%|▋| 9886/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.19"
      ]
     },
     {
@@ -90874,8 +90733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9886/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  66%|▋| 9886/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.27"
+      "Epoch 0:  66%|▋| 9887/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.19\r",
+      "Epoch 0:  66%|▋| 9887/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.45"
      ]
     },
     {
@@ -90883,8 +90742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9887/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.27\r",
-      "Epoch 0:  66%|▋| 9887/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=3.30"
+      "Epoch 0:  66%|▋| 9888/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.45\r",
+      "Epoch 0:  66%|▋| 9888/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -90892,8 +90751,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9888/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=3.30\r",
-      "Epoch 0:  66%|▋| 9888/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  66%|▋| 9889/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -90901,8 +90759,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9889/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  66%|▋| 9889/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  66%|▋| 9889/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=4.00"
      ]
     },
     {
@@ -90910,8 +90767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9890/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  66%|▋| 9890/14932 [14:11<07:14, 11.61it/s, v_num=o30c, train/loss=3.64"
+      "Epoch 0:  66%|▋| 9890/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=4.00\r",
+      "Epoch 0:  66%|▋| 9890/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.42"
      ]
     },
     {
@@ -90919,8 +90776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9891/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=3.64\r",
-      "Epoch 0:  66%|▋| 9891/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=2.50"
+      "Epoch 0:  66%|▋| 9891/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.42\r",
+      "Epoch 0:  66%|▋| 9891/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.27"
      ]
     },
     {
@@ -90928,8 +90785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9892/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=2.50\r",
-      "Epoch 0:  66%|▋| 9892/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  66%|▋| 9892/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.27\r",
+      "Epoch 0:  66%|▋| 9892/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.67"
      ]
     },
     {
@@ -90937,8 +90794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9893/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  66%|▋| 9893/14932 [14:12<07:14, 11.61it/s, v_num=o30c, train/loss=2.80"
+      "Epoch 0:  66%|▋| 9893/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.67\r",
+      "Epoch 0:  66%|▋| 9893/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.44"
      ]
     },
     {
@@ -90946,8 +90803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9894/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.80\r",
-      "Epoch 0:  66%|▋| 9894/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  66%|▋| 9894/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.44\r",
+      "Epoch 0:  66%|▋| 9894/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -90955,8 +90812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9895/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  66%|▋| 9895/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  66%|▋| 9895/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  66%|▋| 9895/14932 [14:10<07:13, 11.63it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -90964,8 +90821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9896/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  66%|▋| 9896/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.14"
+      "Epoch 0:  66%|▋| 9896/14932 [14:11<07:13, 11.63it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  66%|▋| 9896/14932 [14:11<07:13, 11.63it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -90973,8 +90830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9897/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.14\r",
-      "Epoch 0:  66%|▋| 9897/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  66%|▋| 9897/14932 [14:11<07:13, 11.63it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  66%|▋| 9897/14932 [14:11<07:13, 11.63it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -90982,8 +90839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9898/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  66%|▋| 9898/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  66%|▋| 9898/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  66%|▋| 9898/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -90991,8 +90848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9899/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  66%|▋| 9899/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.36"
+      "Epoch 0:  66%|▋| 9899/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  66%|▋| 9899/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.66"
      ]
     },
     {
@@ -91000,8 +90857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9900/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.36\r",
-      "Epoch 0:  66%|▋| 9900/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.67"
+      "Epoch 0:  66%|▋| 9900/14932 [14:11<07:12, 11.62it/s, v_num=ui8w, train/loss=3.66\r",
+      "Epoch 0:  66%|▋| 9900/14932 [14:11<07:12, 11.62it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -91009,8 +90866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9901/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=2.67\r",
-      "Epoch 0:  66%|▋| 9901/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  66%|▋| 9901/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  66%|▋| 9901/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.53"
      ]
     },
     {
@@ -91018,8 +90875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9902/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  66%|▋| 9902/14932 [14:12<07:13, 11.61it/s, v_num=o30c, train/loss=3.56"
+      "Epoch 0:  66%|▋| 9902/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.53\r",
+      "Epoch 0:  66%|▋| 9902/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=2.00"
      ]
     },
     {
@@ -91027,8 +90884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9903/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=3.56\r",
-      "Epoch 0:  66%|▋| 9903/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=2.64"
+      "Epoch 0:  66%|▋| 9903/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=2.00\r",
+      "Epoch 0:  66%|▋| 9903/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.77"
      ]
     },
     {
@@ -91036,8 +90893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9904/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=2.64\r",
-      "Epoch 0:  66%|▋| 9904/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=2.62"
+      "Epoch 0:  66%|▋| 9904/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.77\r",
+      "Epoch 0:  66%|▋| 9904/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -91045,8 +90902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9905/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=2.62\r",
-      "Epoch 0:  66%|▋| 9905/14932 [14:13<07:13, 11.61it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  66%|▋| 9905/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  66%|▋| 9905/14932 [14:11<07:12, 11.63it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -91054,8 +90911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9906/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  66%|▋| 9906/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.73"
+      "Epoch 0:  66%|▋| 9906/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  66%|▋| 9906/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=2.77"
      ]
     },
     {
@@ -91063,8 +90920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9907/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.73\r",
-      "Epoch 0:  66%|▋| 9907/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  66%|▋| 9907/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=2.77\r",
+      "Epoch 0:  66%|▋| 9907/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=2.36"
      ]
     },
     {
@@ -91072,8 +90929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9908/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  66%|▋| 9908/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  66%|▋| 9908/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=2.36\r",
+      "Epoch 0:  66%|▋| 9908/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=3.33"
      ]
     },
     {
@@ -91081,8 +90938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9909/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  66%|▋| 9909/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=2.39"
+      "Epoch 0:  66%|▋| 9909/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=3.33\r",
+      "Epoch 0:  66%|▋| 9909/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=3.95"
      ]
     },
     {
@@ -91090,8 +90947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9910/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=2.39\r",
-      "Epoch 0:  66%|▋| 9910/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.23"
+      "Epoch 0:  66%|▋| 9910/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=3.95\r",
+      "Epoch 0:  66%|▋| 9910/14932 [14:12<07:12, 11.62it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -91099,8 +90956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9911/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.23\r",
-      "Epoch 0:  66%|▋| 9911/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=2.28"
+      "Epoch 0:  66%|▋| 9911/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  66%|▋| 9911/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=3.75"
      ]
     },
     {
@@ -91108,8 +90965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9912/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=2.28\r",
-      "Epoch 0:  66%|▋| 9912/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.42"
+      "Epoch 0:  66%|▋| 9912/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=3.75\r",
+      "Epoch 0:  66%|▋| 9912/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=3.09"
      ]
     },
     {
@@ -91117,8 +90974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9913/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=3.42\r",
-      "Epoch 0:  66%|▋| 9913/14932 [14:13<07:12, 11.61it/s, v_num=o30c, train/loss=1.49"
+      "Epoch 0:  66%|▋| 9913/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=3.09\r",
+      "Epoch 0:  66%|▋| 9913/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=1.28"
      ]
     },
     {
@@ -91126,8 +90983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9914/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=1.49\r",
-      "Epoch 0:  66%|▋| 9914/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=3.52"
+      "Epoch 0:  66%|▋| 9914/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=1.28\r",
+      "Epoch 0:  66%|▋| 9914/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -91135,8 +90992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9915/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=3.52\r",
-      "Epoch 0:  66%|▋| 9915/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  66%|▋| 9915/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  66%|▋| 9915/14932 [14:12<07:11, 11.62it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -91144,8 +91001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9916/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  66%|▋| 9916/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=2.75"
+      "Epoch 0:  66%|▋| 9916/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  66%|▋| 9916/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -91153,8 +91010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9917/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=2.75\r",
-      "Epoch 0:  66%|▋| 9917/14932 [14:14<07:12, 11.61it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  66%|▋| 9917/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  66%|▋| 9917/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -91162,8 +91019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9918/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  66%|▋| 9918/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.86"
+      "Epoch 0:  66%|▋| 9918/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  66%|▋| 9918/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=3.42"
      ]
     },
     {
@@ -91171,8 +91028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9919/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.86\r",
-      "Epoch 0:  66%|▋| 9919/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  66%|▋| 9919/14932 [14:13<07:11, 11.63it/s, v_num=ui8w, train/loss=3.42\r",
+      "Epoch 0:  66%|▋| 9919/14932 [14:13<07:11, 11.63it/s, v_num=ui8w, train/loss=2.52"
      ]
     },
     {
@@ -91180,8 +91037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9920/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  66%|▋| 9920/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  66%|▋| 9920/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=2.52\r",
+      "Epoch 0:  66%|▋| 9920/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=2.45"
      ]
     },
     {
@@ -91189,8 +91046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9921/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  66%|▋| 9921/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  66%|▋| 9921/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=2.45\r",
+      "Epoch 0:  66%|▋| 9921/14932 [14:13<07:11, 11.62it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -91198,8 +91055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9922/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  66%|▋| 9922/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=4.25"
+      "Epoch 0:  66%|▋| 9922/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  66%|▋| 9922/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -91207,8 +91064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9923/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=4.25\r",
-      "Epoch 0:  66%|▋| 9923/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.06"
+      "Epoch 0:  66%|▋| 9923/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  66%|▋| 9923/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -91216,8 +91073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9924/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.06\r",
-      "Epoch 0:  66%|▋| 9924/14932 [14:14<07:11, 11.61it/s, v_num=o30c, train/loss=3.00"
+      "Epoch 0:  66%|▋| 9924/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  66%|▋| 9924/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=3.28"
      ]
     },
     {
@@ -91225,8 +91082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9925/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=3.00\r",
-      "Epoch 0:  66%|▋| 9925/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=3.39"
+      "Epoch 0:  66%|▋| 9925/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=3.28\r",
+      "Epoch 0:  66%|▋| 9925/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=3.48"
      ]
     },
     {
@@ -91234,8 +91091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9926/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=3.39\r",
-      "Epoch 0:  66%|▋| 9926/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=1.92"
+      "Epoch 0:  66%|▋| 9926/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=3.48\r",
+      "Epoch 0:  66%|▋| 9926/14932 [14:13<07:10, 11.62it/s, v_num=ui8w, train/loss=0.98"
      ]
     },
     {
@@ -91243,8 +91100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9927/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=1.92\r",
-      "Epoch 0:  66%|▋| 9927/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  66%|▋| 9927/14932 [14:13<07:10, 11.63it/s, v_num=ui8w, train/loss=0.98\r",
+      "Epoch 0:  66%|▋| 9927/14932 [14:13<07:10, 11.63it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -91252,8 +91109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9928/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  66%|▋| 9928/14932 [14:15<07:11, 11.61it/s, v_num=o30c, train/loss=1.72"
+      "Epoch 0:  66%|▋| 9928/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  66%|▋| 9928/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.23"
      ]
     },
     {
@@ -91261,8 +91118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  66%|▋| 9929/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=1.72\r",
-      "Epoch 0:  66%|▋| 9929/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.17"
+      "Epoch 0:  66%|▋| 9929/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.23\r",
+      "Epoch 0:  66%|▋| 9929/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.78"
      ]
     },
     {
@@ -91270,8 +91127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9930/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.17\r",
-      "Epoch 0:  67%|▋| 9930/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  67%|▋| 9930/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.78\r",
+      "Epoch 0:  67%|▋| 9930/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.52"
      ]
     },
     {
@@ -91279,8 +91136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9931/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  67%|▋| 9931/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=4.34"
+      "Epoch 0:  67%|▋| 9931/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.52\r",
+      "Epoch 0:  67%|▋| 9931/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=1.52"
      ]
     },
     {
@@ -91288,8 +91145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9932/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=4.34\r",
-      "Epoch 0:  67%|▋| 9932/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.44"
+      "Epoch 0:  67%|▋| 9932/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=1.52\r",
+      "Epoch 0:  67%|▋| 9932/14932 [14:14<07:10, 11.63it/s, v_num=ui8w, train/loss=3.81"
      ]
     },
     {
@@ -91297,8 +91154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9933/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.44\r",
-      "Epoch 0:  67%|▋| 9933/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  67%|▋| 9933/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=3.81\r",
+      "Epoch 0:  67%|▋| 9933/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.95"
      ]
     },
     {
@@ -91306,8 +91163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9934/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  67%|▋| 9934/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=1.70"
+      "Epoch 0:  67%|▋| 9934/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.95\r",
+      "Epoch 0:  67%|▋| 9934/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=3.08"
      ]
     },
     {
@@ -91315,8 +91172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9935/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=1.70\r",
-      "Epoch 0:  67%|▋| 9935/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=4.50"
+      "Epoch 0:  67%|▋| 9935/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=3.08\r",
+      "Epoch 0:  67%|▋| 9935/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=3.38"
      ]
     },
     {
@@ -91324,8 +91181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9936/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=4.50\r",
-      "Epoch 0:  67%|▋| 9936/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=1.29"
+      "Epoch 0:  67%|▋| 9936/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=3.38\r",
+      "Epoch 0:  67%|▋| 9936/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.39"
      ]
     },
     {
@@ -91333,8 +91190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9937/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=1.29\r",
-      "Epoch 0:  67%|▋| 9937/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=2.88"
+      "Epoch 0:  67%|▋| 9937/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.39\r",
+      "Epoch 0:  67%|▋| 9937/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.33"
      ]
     },
     {
@@ -91342,8 +91199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9938/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=2.88\r",
-      "Epoch 0:  67%|▋| 9938/14932 [14:15<07:10, 11.61it/s, v_num=o30c, train/loss=2.73"
+      "Epoch 0:  67%|▋| 9938/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.33\r",
+      "Epoch 0:  67%|▋| 9938/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.23"
      ]
     },
     {
@@ -91351,8 +91208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9939/14932 [14:16<07:10, 11.61it/s, v_num=o30c, train/loss=2.73\r",
-      "Epoch 0:  67%|▋| 9939/14932 [14:16<07:10, 11.61it/s, v_num=o30c, train/loss=2.97"
+      "Epoch 0:  67%|▋| 9939/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.23\r",
+      "Epoch 0:  67%|▋| 9939/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.30"
      ]
     },
     {
@@ -91360,8 +91217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9940/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=2.97\r",
-      "Epoch 0:  67%|▋| 9940/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  67%|▋| 9940/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=1.30\r",
+      "Epoch 0:  67%|▋| 9940/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -91369,8 +91226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9941/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  67%|▋| 9941/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=1.12"
+      "Epoch 0:  67%|▋| 9941/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  67%|▋| 9941/14932 [14:14<07:09, 11.63it/s, v_num=ui8w, train/loss=2.98"
      ]
     },
     {
@@ -91378,8 +91235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9942/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=1.12\r",
-      "Epoch 0:  67%|▋| 9942/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=4.06"
+      "Epoch 0:  67%|▋| 9942/14932 [14:15<07:09, 11.63it/s, v_num=ui8w, train/loss=2.98\r",
+      "Epoch 0:  67%|▋| 9942/14932 [14:15<07:09, 11.63it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -91387,8 +91244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9943/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=4.06\r",
-      "Epoch 0:  67%|▋| 9943/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.27"
+      "Epoch 0:  67%|▋| 9943/14932 [14:15<07:09, 11.63it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  67%|▋| 9943/14932 [14:15<07:09, 11.63it/s, v_num=ui8w, train/loss=3.44"
      ]
     },
     {
@@ -91396,8 +91253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9944/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.27\r",
-      "Epoch 0:  67%|▋| 9944/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.94"
+      "Epoch 0:  67%|▋| 9944/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=3.44\r",
+      "Epoch 0:  67%|▋| 9944/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.58"
      ]
     },
     {
@@ -91405,8 +91262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9945/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.94\r",
-      "Epoch 0:  67%|▋| 9945/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.83"
+      "Epoch 0:  67%|▋| 9945/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.58\r",
+      "Epoch 0:  67%|▋| 9945/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.17"
      ]
     },
     {
@@ -91414,8 +91271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9946/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.83\r",
-      "Epoch 0:  67%|▋| 9946/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  67%|▋| 9946/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.17\r",
+      "Epoch 0:  67%|▋| 9946/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.73"
      ]
     },
     {
@@ -91423,8 +91280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9947/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  67%|▋| 9947/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=4.53"
+      "Epoch 0:  67%|▋| 9947/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.73\r",
+      "Epoch 0:  67%|▋| 9947/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.62"
      ]
     },
     {
@@ -91432,8 +91289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9948/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=4.53\r",
-      "Epoch 0:  67%|▋| 9948/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.50"
+      "Epoch 0:  67%|▋| 9948/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.62\r",
+      "Epoch 0:  67%|▋| 9948/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -91441,8 +91298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9949/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.50\r",
-      "Epoch 0:  67%|▋| 9949/14932 [14:16<07:09, 11.61it/s, v_num=o30c, train/loss=3.16"
+      "Epoch 0:  67%|▋| 9949/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  67%|▋| 9949/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -91450,8 +91307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9950/14932 [14:17<07:09, 11.61it/s, v_num=o30c, train/loss=3.16\r",
-      "Epoch 0:  67%|▋| 9950/14932 [14:17<07:09, 11.61it/s, v_num=o30c, train/loss=3.89"
+      "Epoch 0:  67%|▋| 9950/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  67%|▋| 9950/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.72"
      ]
     },
     {
@@ -91459,8 +91316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9951/14932 [14:17<07:09, 11.61it/s, v_num=o30c, train/loss=3.89\r",
-      "Epoch 0:  67%|▋| 9951/14932 [14:17<07:09, 11.61it/s, v_num=o30c, train/loss=4.28"
+      "Epoch 0:  67%|▋| 9951/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.72\r",
+      "Epoch 0:  67%|▋| 9951/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.20"
      ]
     },
     {
@@ -91468,8 +91325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9952/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=4.28\r",
-      "Epoch 0:  67%|▋| 9952/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.48"
+      "Epoch 0:  67%|▋| 9952/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.20\r",
+      "Epoch 0:  67%|▋| 9952/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.67"
      ]
     },
     {
@@ -91477,8 +91334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9953/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.48\r",
-      "Epoch 0:  67%|▋| 9953/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=1.93"
+      "Epoch 0:  67%|▋| 9953/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=2.67\r",
+      "Epoch 0:  67%|▋| 9953/14932 [14:15<07:08, 11.63it/s, v_num=ui8w, train/loss=3.11"
      ]
     },
     {
@@ -91486,8 +91343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9954/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=1.93\r",
-      "Epoch 0:  67%|▋| 9954/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.31"
+      "Epoch 0:  67%|▋| 9954/14932 [14:16<07:08, 11.63it/s, v_num=ui8w, train/loss=3.11\r",
+      "Epoch 0:  67%|▋| 9954/14932 [14:16<07:08, 11.63it/s, v_num=ui8w, train/loss=3.88"
      ]
     },
     {
@@ -91495,8 +91352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9955/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.31\r",
-      "Epoch 0:  67%|▋| 9955/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=1.30"
+      "Epoch 0:  67%|▋| 9955/14932 [14:16<07:08, 11.63it/s, v_num=ui8w, train/loss=3.88\r",
+      "Epoch 0:  67%|▋| 9955/14932 [14:16<07:08, 11.63it/s, v_num=ui8w, train/loss=2.38"
      ]
     },
     {
@@ -91504,8 +91361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9956/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=1.30\r",
-      "Epoch 0:  67%|▋| 9956/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.22"
+      "Epoch 0:  67%|▋| 9956/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.38\r",
+      "Epoch 0:  67%|▋| 9956/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.98"
      ]
     },
     {
@@ -91513,8 +91370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9957/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.22\r",
-      "Epoch 0:  67%|▋| 9957/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.28"
+      "Epoch 0:  67%|▋| 9957/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.98\r",
+      "Epoch 0:  67%|▋| 9957/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.97"
      ]
     },
     {
@@ -91522,8 +91379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9958/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=3.28\r",
-      "Epoch 0:  67%|▋| 9958/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.03"
+      "Epoch 0:  67%|▋| 9958/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.97\r",
+      "Epoch 0:  67%|▋| 9958/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.91"
      ]
     },
     {
@@ -91531,8 +91388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9959/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.03\r",
-      "Epoch 0:  67%|▋| 9959/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.66"
+      "Epoch 0:  67%|▋| 9959/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.91\r",
+      "Epoch 0:  67%|▋| 9959/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.36"
      ]
     },
     {
@@ -91540,8 +91397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9960/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.66\r",
-      "Epoch 0:  67%|▋| 9960/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.23"
+      "Epoch 0:  67%|▋| 9960/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.36\r",
+      "Epoch 0:  67%|▋| 9960/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -91549,8 +91406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9961/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.23\r",
-      "Epoch 0:  67%|▋| 9961/14932 [14:17<07:08, 11.61it/s, v_num=o30c, train/loss=2.89"
+      "Epoch 0:  67%|▋| 9961/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  67%|▋| 9961/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -91558,8 +91415,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9962/14932 [14:18<07:08, 11.61it/s, v_num=o30c, train/loss=2.89\r",
-      "Epoch 0:  67%|▋| 9962/14932 [14:18<07:08, 11.61it/s, v_num=o30c, train/loss=3.38"
+      "Epoch 0:  67%|▋| 9962/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.12"
      ]
     },
     {
@@ -91567,8 +91423,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9963/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.38\r",
-      "Epoch 0:  67%|▋| 9963/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.70"
+      "Epoch 0:  67%|▋| 9962/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.80"
      ]
     },
     {
@@ -91576,8 +91431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9964/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.70\r",
-      "Epoch 0:  67%|▋| 9964/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.81"
+      "Epoch 0:  67%|▋| 9963/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=2.80\r",
+      "Epoch 0:  67%|▋| 9963/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.58"
      ]
     },
     {
@@ -91585,8 +91440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9965/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.81\r",
-      "Epoch 0:  67%|▋| 9965/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  67%|▋| 9964/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.58\r",
+      "Epoch 0:  67%|▋| 9964/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -91594,8 +91449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9966/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  67%|▋| 9966/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.92"
+      "Epoch 0:  67%|▋| 9965/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  67%|▋| 9965/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=5.12"
      ]
     },
     {
@@ -91603,8 +91458,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9967/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.92\r",
-      "Epoch 0:  67%|▋| 9967/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.67"
+      "Epoch 0:  67%|▋| 9966/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=5.12"
      ]
     },
     {
@@ -91612,8 +91466,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9968/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.67\r",
-      "Epoch 0:  67%|▋| 9968/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.12"
+      "Epoch 0:  67%|▋| 9966/14932 [14:16<07:07, 11.63it/s, v_num=ui8w, train/loss=3.19"
      ]
     },
     {
@@ -91621,8 +91474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9969/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.12\r",
-      "Epoch 0:  67%|▋| 9969/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.33"
+      "Epoch 0:  67%|▋| 9967/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.19\r",
+      "Epoch 0:  67%|▋| 9967/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=4.06"
      ]
     },
     {
@@ -91630,8 +91483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9970/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.33\r",
-      "Epoch 0:  67%|▋| 9970/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.59"
+      "Epoch 0:  67%|▋| 9968/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=4.06\r",
+      "Epoch 0:  67%|▋| 9968/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.06"
      ]
     },
     {
@@ -91639,8 +91492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9971/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.59\r",
-      "Epoch 0:  67%|▋| 9971/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.69"
+      "Epoch 0:  67%|▋| 9969/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.06\r",
+      "Epoch 0:  67%|▋| 9969/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -91648,8 +91501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9972/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=2.69\r",
-      "Epoch 0:  67%|▋| 9972/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  67%|▋| 9970/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  67%|▋| 9970/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=2.89"
      ]
     },
     {
@@ -91657,8 +91510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9973/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  67%|▋| 9973/14932 [14:18<07:07, 11.61it/s, v_num=o30c, train/loss=3.19"
+      "Epoch 0:  67%|▋| 9971/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=2.89\r",
+      "Epoch 0:  67%|▋| 9971/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.17"
      ]
     },
     {
@@ -91666,8 +91519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9974/14932 [14:19<07:07, 11.61it/s, v_num=o30c, train/loss=3.19\r",
-      "Epoch 0:  67%|▋| 9974/14932 [14:19<07:07, 11.61it/s, v_num=o30c, train/loss=1.82"
+      "Epoch 0:  67%|▋| 9972/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.17\r",
+      "Epoch 0:  67%|▋| 9972/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.16"
      ]
     },
     {
@@ -91675,8 +91528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9975/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=1.82\r",
-      "Epoch 0:  67%|▋| 9975/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=4.44"
+      "Epoch 0:  67%|▋| 9973/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.16\r",
+      "Epoch 0:  67%|▋| 9973/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=4.31"
      ]
     },
     {
@@ -91684,8 +91537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9976/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=4.44\r",
-      "Epoch 0:  67%|▋| 9976/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.91"
+      "Epoch 0:  67%|▋| 9974/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=4.31\r",
+      "Epoch 0:  67%|▋| 9974/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=1.98"
      ]
     },
     {
@@ -91693,8 +91546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9977/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.91\r",
-      "Epoch 0:  67%|▋| 9977/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.33"
+      "Epoch 0:  67%|▋| 9975/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=1.98\r",
+      "Epoch 0:  67%|▋| 9975/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=2.47"
      ]
     },
     {
@@ -91702,8 +91555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9978/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.33\r",
-      "Epoch 0:  67%|▋| 9978/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.16"
+      "Epoch 0:  67%|▋| 9976/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=2.47\r",
+      "Epoch 0:  67%|▋| 9976/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.70"
      ]
     },
     {
@@ -91711,8 +91564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9979/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.16\r",
-      "Epoch 0:  67%|▋| 9979/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.94"
+      "Epoch 0:  67%|▋| 9977/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=3.70\r",
+      "Epoch 0:  67%|▋| 9977/14932 [14:17<07:06, 11.63it/s, v_num=ui8w, train/loss=4.62"
      ]
     },
     {
@@ -91720,8 +91573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9980/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.94\r",
-      "Epoch 0:  67%|▋| 9980/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.25"
+      "Epoch 0:  67%|▋| 9978/14932 [14:17<07:05, 11.63it/s, v_num=ui8w, train/loss=4.62\r",
+      "Epoch 0:  67%|▋| 9978/14932 [14:17<07:05, 11.63it/s, v_num=ui8w, train/loss=1.47"
      ]
     },
     {
@@ -91729,8 +91582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9981/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.25\r",
-      "Epoch 0:  67%|▋| 9981/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.61"
+      "Epoch 0:  67%|▋| 9979/14932 [14:17<07:05, 11.63it/s, v_num=ui8w, train/loss=1.47\r",
+      "Epoch 0:  67%|▋| 9979/14932 [14:17<07:05, 11.63it/s, v_num=ui8w, train/loss=1.83"
      ]
     },
     {
@@ -91738,8 +91591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9982/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.61\r",
-      "Epoch 0:  67%|▋| 9982/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=1.63"
+      "Epoch 0:  67%|▋| 9980/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=1.83\r",
+      "Epoch 0:  67%|▋| 9980/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=3.59"
      ]
     },
     {
@@ -91747,8 +91600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9983/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=1.63\r",
-      "Epoch 0:  67%|▋| 9983/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.95"
+      "Epoch 0:  67%|▋| 9981/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=3.59\r",
+      "Epoch 0:  67%|▋| 9981/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=4.19"
      ]
     },
     {
@@ -91756,8 +91609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9984/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=2.95\r",
-      "Epoch 0:  67%|▋| 9984/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.05"
+      "Epoch 0:  67%|▋| 9982/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=4.19\r",
+      "Epoch 0:  67%|▋| 9982/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.34"
      ]
     },
     {
@@ -91765,8 +91618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9985/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.05\r",
-      "Epoch 0:  67%|▋| 9985/14932 [14:19<07:06, 11.61it/s, v_num=o30c, train/loss=3.09"
+      "Epoch 0:  67%|▋| 9983/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.34\r",
+      "Epoch 0:  67%|▋| 9983/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.48"
      ]
     },
     {
@@ -91774,8 +91627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9986/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.09\r",
-      "Epoch 0:  67%|▋| 9986/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  67%|▋| 9984/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.48\r",
+      "Epoch 0:  67%|▋| 9984/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=4.12"
      ]
     },
     {
@@ -91783,8 +91636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9987/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  67%|▋| 9987/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.55"
+      "Epoch 0:  67%|▋| 9985/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=4.12\r",
+      "Epoch 0:  67%|▋| 9985/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=1.99"
      ]
     },
     {
@@ -91792,8 +91645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9988/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.55\r",
-      "Epoch 0:  67%|▋| 9988/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.84"
+      "Epoch 0:  67%|▋| 9986/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=1.99\r",
+      "Epoch 0:  67%|▋| 9986/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -91801,8 +91654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9989/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.84\r",
-      "Epoch 0:  67%|▋| 9989/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.56"
+      "Epoch 0:  67%|▋| 9987/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  67%|▋| 9987/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.56"
      ]
     },
     {
@@ -91810,8 +91663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9990/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.56\r",
-      "Epoch 0:  67%|▋| 9990/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.59"
+      "Epoch 0:  67%|▋| 9988/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.56\r",
+      "Epoch 0:  67%|▋| 9988/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.84"
      ]
     },
     {
@@ -91819,8 +91672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9991/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.59\r",
-      "Epoch 0:  67%|▋| 9991/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.20"
+      "Epoch 0:  67%|▋| 9989/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.84\r",
+      "Epoch 0:  67%|▋| 9989/14932 [14:18<07:05, 11.63it/s, v_num=ui8w, train/loss=2.94"
      ]
     },
     {
@@ -91828,8 +91681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9992/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.20\r",
-      "Epoch 0:  67%|▋| 9992/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  67%|▋| 9990/14932 [14:18<07:04, 11.63it/s, v_num=ui8w, train/loss=2.94\r",
+      "Epoch 0:  67%|▋| 9990/14932 [14:18<07:04, 11.63it/s, v_num=ui8w, train/loss=2.14"
      ]
     },
     {
@@ -91837,7 +91690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9993/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  67%|▋| 9991/14932 [14:18<07:04, 11.63it/s, v_num=ui8w, train/loss=2.14\r",
+      "Epoch 0:  67%|▋| 9991/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=2.70"
      ]
     },
     {
@@ -91845,7 +91699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9993/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.95"
+      "Epoch 0:  67%|▋| 9992/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=2.70\r",
+      "Epoch 0:  67%|▋| 9992/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.94"
      ]
     },
     {
@@ -91853,8 +91708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9994/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.95\r",
-      "Epoch 0:  67%|▋| 9994/14932 [14:20<07:05, 11.61it/s, v_num=o30c, train/loss=3.03"
+      "Epoch 0:  67%|▋| 9993/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.94\r",
+      "Epoch 0:  67%|▋| 9993/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.83"
      ]
     },
     {
@@ -91862,8 +91717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9995/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=3.03\r",
-      "Epoch 0:  67%|▋| 9995/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=2.81"
+      "Epoch 0:  67%|▋| 9994/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.83\r",
+      "Epoch 0:  67%|▋| 9994/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=4.50"
      ]
     },
     {
@@ -91871,8 +91726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9996/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=2.81\r",
-      "Epoch 0:  67%|▋| 9996/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=0.84"
+      "Epoch 0:  67%|▋| 9995/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=4.50\r",
+      "Epoch 0:  67%|▋| 9995/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=4.03"
      ]
     },
     {
@@ -91880,8 +91735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9997/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=0.84\r",
-      "Epoch 0:  67%|▋| 9997/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=4.16"
+      "Epoch 0:  67%|▋| 9996/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=4.03\r",
+      "Epoch 0:  67%|▋| 9996/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.80"
      ]
     },
     {
@@ -91889,8 +91744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9998/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=4.16\r",
-      "Epoch 0:  67%|▋| 9998/14932 [14:21<07:05, 11.61it/s, v_num=o30c, train/loss=3.97"
+      "Epoch 0:  67%|▋| 9997/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.80\r",
+      "Epoch 0:  67%|▋| 9997/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=2.28"
      ]
     },
     {
@@ -91898,8 +91753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 9999/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.97\r",
-      "Epoch 0:  67%|▋| 9999/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=0.89"
+      "Epoch 0:  67%|▋| 9998/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=2.28\r",
+      "Epoch 0:  67%|▋| 9998/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.84"
      ]
     },
     {
@@ -91907,8 +91762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10000/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  67%|▋| 10000/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  67%|▋| 9999/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.84\r",
+      "Epoch 0:  67%|▋| 9999/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=1.95"
      ]
     },
     {
@@ -91916,8 +91771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10001/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  67%|▋| 10001/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  67%|▋| 10000/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  67%|▋| 10000/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -91925,8 +91780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10002/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  67%|▋| 10002/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10001/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  67%|▋| 10001/14932 [14:19<07:04, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -91934,8 +91789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10003/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10003/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  67%|▋| 10002/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10002/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -91943,8 +91798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10004/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  67%|▋| 10004/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  67%|▋| 10003/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  67%|▋| 10003/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -91952,8 +91807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10005/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  67%|▋| 10005/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  67%|▋| 10004/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  67%|▋| 10004/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -91961,8 +91816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10006/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  67%|▋| 10006/14932 [14:21<07:04, 11.61it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  67%|▋| 10005/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  67%|▋| 10005/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -91970,8 +91825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10007/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  67%|▋| 10007/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  67%|▋| 10006/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  67%|▋| 10006/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -91979,8 +91834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10008/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  67%|▋| 10008/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10007/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  67%|▋| 10007/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -91988,8 +91843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10009/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10009/14932 [14:22<07:04, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  67%|▋| 10008/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  67%|▋| 10008/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -91997,8 +91852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10010/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  67%|▋| 10010/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  67%|▋| 10009/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  67%|▋| 10009/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -92006,8 +91861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10011/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  67%|▋| 10011/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  67%|▋| 10010/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  67%|▋| 10010/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -92015,8 +91870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10012/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  67%|▋| 10012/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  67%|▋| 10011/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  67%|▋| 10011/14932 [14:20<07:03, 11.63it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -92024,8 +91879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10013/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  67%|▋| 10013/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10012/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  67%|▋| 10012/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -92033,8 +91888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10014/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10014/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  67%|▋| 10013/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  67%|▋| 10013/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -92042,8 +91897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10015/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  67%|▋| 10015/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  67%|▋| 10014/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  67%|▋| 10014/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92051,8 +91906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10016/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  67%|▋| 10016/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  67%|▋| 10015/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10015/14932 [14:20<07:02, 11.63it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -92060,8 +91915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10017/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  67%|▋| 10017/14932 [14:22<07:03, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  67%|▋| 10016/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  67%|▋| 10016/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92069,8 +91924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10018/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  67%|▋| 10018/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  67%|▋| 10017/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  67%|▋| 10017/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -92078,8 +91933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10019/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  67%|▋| 10019/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  67%|▋| 10018/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  67%|▋| 10018/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -92087,8 +91942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10020/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  67%|▋| 10020/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  67%|▋| 10019/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  67%|▋| 10019/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -92096,8 +91951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10021/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  67%|▋| 10021/14932 [14:23<07:03, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  67%|▋| 10020/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  67%|▋| 10020/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -92105,8 +91960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10022/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  67%|▋| 10022/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  67%|▋| 10021/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  67%|▋| 10021/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92114,8 +91969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10023/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  67%|▋| 10023/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  67%|▋| 10022/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  67%|▋| 10022/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -92123,8 +91978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10024/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  67%|▋| 10024/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10023/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  67%|▋| 10023/14932 [14:21<07:02, 11.63it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -92132,8 +91987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10025/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10025/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  67%|▋| 10024/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  67%|▋| 10024/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -92141,8 +91996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10026/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  67%|▋| 10026/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  67%|▋| 10025/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  67%|▋| 10025/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92150,8 +92005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10027/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  67%|▋| 10027/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  67%|▋| 10026/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  67%|▋| 10026/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92159,8 +92014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10028/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  67%|▋| 10028/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  67%|▋| 10027/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10027/14932 [14:21<07:01, 11.63it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -92168,8 +92023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10029/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  67%|▋| 10029/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  67%|▋| 10028/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  67%|▋| 10028/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -92177,8 +92032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10030/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  67%|▋| 10030/14932 [14:23<07:02, 11.61it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  67%|▋| 10029/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  67%|▋| 10029/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -92186,8 +92041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10031/14932 [14:24<07:02, 11.61it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  67%|▋| 10031/14932 [14:24<07:02, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  67%|▋| 10030/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  67%|▋| 10030/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -92195,8 +92050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10032/14932 [14:24<07:02, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  67%|▋| 10032/14932 [14:24<07:02, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  67%|▋| 10031/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  67%|▋| 10031/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -92204,8 +92059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10033/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  67%|▋| 10033/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  67%|▋| 10032/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  67%|▋| 10032/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92213,8 +92068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10034/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  67%|▋| 10034/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  67%|▋| 10033/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  67%|▋| 10033/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92222,8 +92077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10035/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  67%|▋| 10035/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  67%|▋| 10034/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  67%|▋| 10034/14932 [14:22<07:01, 11.63it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -92231,8 +92086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10036/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  67%|▋| 10036/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  67%|▋| 10035/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  67%|▋| 10035/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -92240,8 +92095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10037/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  67%|▋| 10037/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  67%|▋| 10036/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  67%|▋| 10036/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -92249,8 +92104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10038/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  67%|▋| 10038/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  67%|▋| 10037/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  67%|▋| 10037/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92258,8 +92113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10039/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  67%|▋| 10039/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  67%|▋| 10038/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  67%|▋| 10038/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -92267,8 +92122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10040/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  67%|▋| 10040/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  67%|▋| 10039/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  67%|▋| 10039/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92276,8 +92131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10041/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  67%|▋| 10041/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  67%|▋| 10040/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10040/14932 [14:22<07:00, 11.63it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92285,8 +92140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10042/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  67%|▋| 10042/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10041/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  67%|▋| 10041/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -92294,8 +92149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10043/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10043/14932 [14:24<07:01, 11.61it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  67%|▋| 10042/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  67%|▋| 10042/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -92303,8 +92158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10044/14932 [14:24<07:00, 11.61it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  67%|▋| 10044/14932 [14:24<07:00, 11.61it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  67%|▋| 10043/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  67%|▋| 10043/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -92312,8 +92167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10045/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  67%|▋| 10045/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  67%|▋| 10044/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  67%|▋| 10044/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -92321,8 +92176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10046/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  67%|▋| 10046/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  67%|▋| 10045/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  67%|▋| 10045/14932 [14:23<07:00, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92330,8 +92185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10047/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  67%|▋| 10047/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  67%|▋| 10046/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10046/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92339,8 +92194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10048/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  67%|▋| 10048/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  67%|▋| 10047/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  67%|▋| 10047/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92348,8 +92203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10049/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  67%|▋| 10049/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  67%|▋| 10048/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10048/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -92357,8 +92212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10050/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  67%|▋| 10050/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  67%|▋| 10049/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  67%|▋| 10049/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -92366,8 +92221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10051/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  67%|▋| 10051/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  67%|▋| 10050/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  67%|▋| 10050/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92375,8 +92230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10052/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  67%|▋| 10052/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  67%|▋| 10051/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  67%|▋| 10051/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -92384,8 +92239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10053/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  67%|▋| 10053/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  67%|▋| 10052/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  67%|▋| 10052/14932 [14:23<06:59, 11.63it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92393,8 +92248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10054/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  67%|▋| 10054/14932 [14:25<07:00, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  67%|▋| 10053/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  67%|▋| 10053/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -92402,8 +92257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10055/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  67%|▋| 10055/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  67%|▋| 10054/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  67%|▋| 10054/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -92411,8 +92266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10056/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  67%|▋| 10056/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  67%|▋| 10055/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  67%|▋| 10055/14932 [14:24<06:59, 11.63it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -92420,8 +92275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10057/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  67%|▋| 10057/14932 [14:25<06:59, 11.61it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  67%|▋| 10056/14932 [14:24<06:59, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  67%|▋| 10056/14932 [14:24<06:59, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -92429,8 +92284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10058/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  67%|▋| 10058/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  67%|▋| 10057/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  67%|▋| 10057/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -92438,8 +92293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10059/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  67%|▋| 10059/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  67%|▋| 10058/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  67%|▋| 10058/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -92447,8 +92302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10060/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  67%|▋| 10060/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  67%|▋| 10059/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  67%|▋| 10059/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92456,8 +92311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10061/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  67%|▋| 10061/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  67%|▋| 10060/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  67%|▋| 10060/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -92465,8 +92320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10062/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  67%|▋| 10062/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  67%|▋| 10061/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  67%|▋| 10061/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -92474,8 +92329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10063/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  67%|▋| 10063/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  67%|▋| 10062/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  67%|▋| 10062/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -92483,8 +92338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10064/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  67%|▋| 10064/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  67%|▋| 10063/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  67%|▋| 10063/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -92492,8 +92347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10065/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  67%|▋| 10065/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  67%|▋| 10064/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  67%|▋| 10064/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92501,8 +92356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10066/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  67%|▋| 10066/14932 [14:26<06:59, 11.61it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  67%|▋| 10065/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  67%|▋| 10065/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92510,8 +92365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10067/14932 [14:26<06:58, 11.61it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  67%|▋| 10067/14932 [14:26<06:58, 11.61it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  67%|▋| 10066/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  67%|▋| 10066/14932 [14:24<06:58, 11.64it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -92519,8 +92374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10068/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  67%|▋| 10068/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  67%|▋| 10067/14932 [14:25<06:58, 11.64it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  67%|▋| 10067/14932 [14:25<06:58, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92528,8 +92383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10069/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  67%|▋| 10069/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  67%|▋| 10068/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  67%|▋| 10068/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -92537,8 +92392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10070/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  67%|▋| 10070/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  67%|▋| 10069/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  67%|▋| 10069/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92546,8 +92401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10071/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  67%|▋| 10071/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  67%|▋| 10070/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  67%|▋| 10070/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92555,8 +92410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10072/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  67%|▋| 10072/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  67%|▋| 10071/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  67%|▋| 10071/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92564,8 +92419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10073/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  67%|▋| 10073/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  67%|▋| 10072/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  67%|▋| 10072/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92573,8 +92428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10074/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  67%|▋| 10074/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  67%|▋| 10073/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  67%|▋| 10073/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -92582,8 +92437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10075/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  67%|▋| 10075/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  67%|▋| 10074/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  67%|▋| 10074/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92591,8 +92446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10076/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  67%|▋| 10076/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  67%|▋| 10075/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10075/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92600,8 +92455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10077/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  67%|▋| 10077/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  67%|▋| 10076/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  67%|▋| 10076/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -92609,8 +92464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10078/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  67%|▋| 10078/14932 [14:27<06:58, 11.61it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  67%|▋| 10077/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  67%|▋| 10077/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92618,8 +92473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  67%|▋| 10079/14932 [14:27<06:57, 11.61it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  67%|▋| 10079/14932 [14:27<06:57, 11.61it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  67%|▋| 10078/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  67%|▋| 10078/14932 [14:25<06:57, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -92627,8 +92482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10080/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  68%|▋| 10080/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  67%|▋| 10079/14932 [14:25<06:56, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  67%|▋| 10079/14932 [14:25<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92636,8 +92491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10081/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10081/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  68%|▋| 10080/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10080/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -92645,8 +92500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10082/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  68%|▋| 10082/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10081/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10081/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92654,8 +92509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10083/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10083/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10082/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10082/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -92663,8 +92518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10084/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10084/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  68%|▋| 10083/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  68%|▋| 10083/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92672,8 +92527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10085/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  68%|▋| 10085/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  68%|▋| 10084/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10084/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -92681,8 +92536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10086/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  68%|▋| 10086/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  68%|▋| 10085/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  68%|▋| 10085/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -92690,8 +92545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10087/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  68%|▋| 10087/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  68%|▋| 10086/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  68%|▋| 10086/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92699,8 +92554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10088/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  68%|▋| 10088/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10087/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  68%|▋| 10087/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -92708,8 +92563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10089/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10089/14932 [14:28<06:57, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10088/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  68%|▋| 10088/14932 [14:26<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -92717,8 +92572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10090/14932 [14:28<06:56, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10090/14932 [14:28<06:56, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10089/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10089/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -92726,8 +92581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10091/14932 [14:28<06:56, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10091/14932 [14:28<06:56, 11.61it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  68%|▋| 10090/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10090/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -92735,8 +92590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10092/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  68%|▋| 10092/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10091/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10091/14932 [14:27<06:56, 11.64it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -92744,8 +92599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10093/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10093/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10092/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  68%|▋| 10092/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -92753,8 +92608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10094/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10094/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10093/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10093/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92762,8 +92617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10095/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10095/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10094/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  68%|▋| 10094/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -92771,8 +92626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10096/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10096/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  68%|▋| 10095/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10095/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -92780,8 +92635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10097/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  68%|▋| 10097/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10096/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  68%|▋| 10096/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -92789,8 +92644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10098/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10098/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  68%|▋| 10097/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  68%|▋| 10097/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -92798,8 +92653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10099/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  68%|▋| 10099/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10098/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  68%|▋| 10098/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -92807,8 +92662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10100/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10100/14932 [14:29<06:56, 11.61it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  68%|▋| 10099/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10099/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -92816,8 +92671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10101/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  68%|▋| 10101/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10100/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  68%|▋| 10100/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92825,8 +92680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10102/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10102/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10101/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10101/14932 [14:27<06:55, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92834,8 +92689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10103/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10103/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  68%|▋| 10102/14932 [14:28<06:55, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  68%|▋| 10102/14932 [14:28<06:55, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -92843,8 +92698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10104/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  68%|▋| 10104/14932 [14:29<06:55, 11.61it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10103/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10103/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -92852,8 +92707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10105/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10105/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10104/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  68%|▋| 10104/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -92861,8 +92716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10106/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10106/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  68%|▋| 10105/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  68%|▋| 10105/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92870,8 +92725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10107/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  68%|▋| 10107/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10106/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10106/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -92879,8 +92734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10108/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10108/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10107/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  68%|▋| 10107/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -92888,8 +92743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10109/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10109/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  68%|▋| 10108/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10108/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -92897,8 +92752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10110/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  68%|▋| 10110/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10109/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  68%|▋| 10109/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92906,8 +92761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10111/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10111/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10110/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  68%|▋| 10110/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -92915,8 +92770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10112/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10112/14932 [14:30<06:55, 11.61it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10111/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  68%|▋| 10111/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -92924,8 +92779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10113/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10113/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  68%|▋| 10112/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  68%|▋| 10112/14932 [14:28<06:54, 11.64it/s, v_num=ui8w, train/loss=5.6"
      ]
     },
     {
@@ -92933,8 +92788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10114/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  68%|▋| 10114/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10113/14932 [14:29<06:54, 11.64it/s, v_num=ui8w, train/loss=5.6\r",
+      "Epoch 0:  68%|▋| 10113/14932 [14:29<06:54, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -92942,8 +92797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10115/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10115/14932 [14:30<06:54, 11.61it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10114/14932 [14:29<06:54, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10114/14932 [14:29<06:54, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -92951,8 +92806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10116/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10116/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10115/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10115/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92960,8 +92815,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10117/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10117/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10116/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92969,8 +92823,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10118/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10118/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  68%|▋| 10116/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -92978,8 +92831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10119/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  68%|▋| 10119/14932 [14:31<06:54, 11.61it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10117/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  68%|▋| 10117/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -92987,8 +92840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10120/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10120/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10118/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10118/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -92996,8 +92849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10121/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10121/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10119/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10119/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93005,8 +92858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10122/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10122/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  68%|▋| 10120/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10120/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93014,8 +92867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10123/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  68%|▋| 10123/14932 [14:31<06:54, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10121/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10121/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93023,8 +92876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10124/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10124/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  68%|▋| 10122/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10122/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -93032,8 +92885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10125/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  68%|▋| 10125/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  68%|▋| 10123/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10123/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -93041,8 +92894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10126/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  68%|▋| 10126/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10124/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  68%|▋| 10124/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93050,8 +92903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10127/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10127/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  68%|▋| 10125/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10125/14932 [14:29<06:53, 11.64it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -93059,8 +92912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10128/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  68%|▋| 10128/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  68%|▋| 10126/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  68%|▋| 10126/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93068,8 +92921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10129/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  68%|▋| 10129/14932 [14:31<06:53, 11.62it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10127/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10127/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93077,8 +92930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10130/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10130/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10128/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10128/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93086,8 +92939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10131/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10131/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10129/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10129/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -93095,8 +92948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10132/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10132/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  68%|▋| 10130/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  68%|▋| 10130/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -93104,8 +92957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10133/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  68%|▋| 10133/14932 [14:32<06:53, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10131/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10131/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93113,8 +92966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10134/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10134/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10132/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10132/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -93122,8 +92975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10135/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10135/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  68%|▋| 10133/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  68%|▋| 10133/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -93131,8 +92984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10136/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  68%|▋| 10136/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10134/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  68%|▋| 10134/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -93140,8 +92993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10137/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10137/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  68%|▋| 10135/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  68%|▋| 10135/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -93149,8 +93002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10138/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  68%|▋| 10138/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10136/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  68%|▋| 10136/14932 [14:30<06:52, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -93158,8 +93011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10139/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10139/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  68%|▋| 10137/14932 [14:30<06:51, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  68%|▋| 10137/14932 [14:30<06:51, 11.64it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -93167,8 +93020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10140/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  68%|▋| 10140/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10138/14932 [14:30<06:51, 11.64it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  68%|▋| 10138/14932 [14:30<06:51, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93176,8 +93029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10141/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10141/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10139/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10139/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93185,8 +93038,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10142/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10142/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  68%|▋| 10140/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93194,8 +93046,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10143/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  68%|▋| 10143/14932 [14:32<06:52, 11.62it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10140/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -93203,8 +93054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10144/14932 [14:33<06:52, 11.62it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10144/14932 [14:33<06:52, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10141/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  68%|▋| 10141/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93212,8 +93063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10145/14932 [14:33<06:52, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10145/14932 [14:33<06:52, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10142/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10142/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -93221,8 +93072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10146/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10146/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10143/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  68%|▋| 10143/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -93230,8 +93081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10147/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10147/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  68%|▋| 10144/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  68%|▋| 10144/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93239,8 +93090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10148/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  68%|▋| 10148/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10145/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10145/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -93248,8 +93099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10149/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10149/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10146/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  68%|▋| 10146/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -93257,8 +93108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10150/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10150/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10147/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  68%|▋| 10147/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -93266,8 +93117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10151/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10151/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  68%|▋| 10148/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  68%|▋| 10148/14932 [14:31<06:51, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93275,8 +93126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10152/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  68%|▋| 10152/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10149/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10149/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93284,8 +93135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10153/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10153/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10150/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10150/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -93293,8 +93144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10154/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10154/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10151/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10151/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -93302,8 +93153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10155/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10155/14932 [14:33<06:51, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10152/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  68%|▋| 10152/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93311,8 +93162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10156/14932 [14:34<06:51, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10156/14932 [14:34<06:51, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10153/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10153/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93320,8 +93171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10157/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10157/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10154/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10154/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -93329,8 +93180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10158/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10158/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10155/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  68%|▋| 10155/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -93338,8 +93189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10159/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10159/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  68%|▋| 10156/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  68%|▋| 10156/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93347,8 +93198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10160/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  68%|▋| 10160/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  68%|▋| 10157/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10157/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93356,8 +93207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10161/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  68%|▋| 10161/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10158/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10158/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -93365,8 +93216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10162/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10162/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10159/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  68%|▋| 10159/14932 [14:32<06:50, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93374,8 +93225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10163/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10163/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10160/14932 [14:32<06:49, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10160/14932 [14:32<06:49, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93383,8 +93234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10164/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10164/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10161/14932 [14:32<06:49, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10161/14932 [14:32<06:49, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93392,8 +93243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10165/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10165/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  68%|▋| 10162/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10162/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -93401,7 +93252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10166/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  68%|▋| 10163/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10163/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93409,7 +93261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10166/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  68%|▋| 10164/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10164/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93417,8 +93270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10167/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  68%|▋| 10167/14932 [14:34<06:50, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10165/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10165/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93426,8 +93279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10168/14932 [14:34<06:49, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10168/14932 [14:34<06:49, 11.62it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10166/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10166/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93435,8 +93288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10169/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10169/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10167/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10167/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93444,8 +93297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10170/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10170/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  68%|▋| 10168/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10168/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -93453,8 +93306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10171/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  68%|▋| 10171/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  68%|▋| 10169/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10169/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -93462,8 +93315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10172/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  68%|▋| 10172/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10170/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  68%|▋| 10170/14932 [14:33<06:49, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -93471,8 +93324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10173/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10173/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10171/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10171/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -93480,8 +93333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10174/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10174/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  68%|▋| 10172/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  68%|▋| 10172/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -93489,8 +93342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10175/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  68%|▋| 10175/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10173/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  68%|▋| 10173/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -93498,8 +93351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10176/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10176/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10174/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  68%|▋| 10174/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -93507,8 +93360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10177/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  68%|▋| 10177/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  68%|▋| 10175/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10175/14932 [14:33<06:48, 11.64it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -93516,8 +93369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10178/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  68%|▋| 10178/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10176/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  68%|▋| 10176/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -93525,7 +93378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10179/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10177/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  68%|▋| 10177/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93533,7 +93387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10179/14932 [14:35<06:49, 11.62it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  68%|▋| 10178/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10178/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -93541,8 +93396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10180/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  68%|▋| 10180/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10179/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  68%|▋| 10179/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93550,8 +93405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10181/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10181/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10180/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10180/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -93559,8 +93414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10182/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10182/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  68%|▋| 10181/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  68%|▋| 10181/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93568,8 +93423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10183/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  68%|▋| 10183/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  68%|▋| 10182/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10182/14932 [14:34<06:48, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93577,8 +93432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10184/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  68%|▋| 10184/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  68%|▋| 10183/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10183/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -93586,8 +93441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10185/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  68%|▋| 10185/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  68%|▋| 10184/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  68%|▋| 10184/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93595,7 +93450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10186/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  68%|▋| 10185/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10185/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93603,7 +93459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10186/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10186/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10186/14932 [14:34<06:47, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93611,8 +93468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10187/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10187/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  68%|▋| 10187/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10187/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93620,8 +93477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10188/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  68%|▋| 10188/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  68%|▋| 10188/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10188/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -93629,8 +93486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10189/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  68%|▋| 10189/14932 [14:36<06:48, 11.62it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  68%|▋| 10189/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  68%|▋| 10189/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93638,8 +93495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10190/14932 [14:37<06:48, 11.62it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  68%|▋| 10190/14932 [14:37<06:48, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10190/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10190/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -93647,8 +93504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10191/14932 [14:37<06:48, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  68%|▋| 10191/14932 [14:37<06:48, 11.62it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  68%|▋| 10191/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  68%|▋| 10191/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93656,8 +93513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10192/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  68%|▋| 10192/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10192/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10192/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -93665,8 +93522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10193/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10193/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  68%|▋| 10193/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  68%|▋| 10193/14932 [14:35<06:47, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -93674,8 +93531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10194/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  68%|▋| 10194/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10194/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10194/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93683,8 +93540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10195/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10195/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10195/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10195/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93692,8 +93549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10196/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10196/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  68%|▋| 10196/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  68%|▋| 10196/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -93701,8 +93558,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10197/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  68%|▋| 10197/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10197/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -93710,8 +93566,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10198/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10198/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=5.8"
+      "Epoch 0:  68%|▋| 10197/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93719,8 +93574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10199/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=5.8\r",
-      "Epoch 0:  68%|▋| 10199/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  68%|▋| 10198/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10198/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93728,8 +93583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10200/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  68%|▋| 10200/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  68%|▋| 10199/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10199/14932 [14:35<06:46, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93737,8 +93592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10201/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  68%|▋| 10201/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  68%|▋| 10200/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10200/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -93746,8 +93601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10202/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  68%|▋| 10202/14932 [14:37<06:47, 11.62it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  68%|▋| 10201/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  68%|▋| 10201/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -93755,8 +93610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10203/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  68%|▋| 10203/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10202/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  68%|▋| 10202/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93764,8 +93619,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10204/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10204/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10203/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -93773,8 +93627,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10205/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10205/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10203/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -93782,8 +93635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10206/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10206/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10204/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10204/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -93791,8 +93644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10207/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10207/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  68%|▋| 10205/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  68%|▋| 10205/14932 [14:36<06:46, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93800,8 +93653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10208/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  68%|▋| 10208/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  68%|▋| 10206/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10206/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93809,8 +93662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10209/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  68%|▋| 10209/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  68%|▋| 10207/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10207/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -93818,8 +93671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10210/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  68%|▋| 10210/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  68%|▋| 10208/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10208/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -93827,8 +93680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10211/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  68%|▋| 10211/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10209/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  68%|▋| 10209/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -93836,8 +93689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10212/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10212/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  68%|▋| 10210/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  68%|▋| 10210/14932 [14:36<06:45, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93845,8 +93698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10213/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  68%|▋| 10213/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  68%|▋| 10211/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10211/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -93854,8 +93707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10214/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  68%|▋| 10214/14932 [14:38<06:46, 11.62it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  68%|▋| 10212/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10212/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -93863,8 +93716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10215/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  68%|▋| 10215/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  68%|▋| 10213/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  68%|▋| 10213/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93872,8 +93725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10216/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  68%|▋| 10216/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  68%|▋| 10214/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10214/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -93881,8 +93734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10217/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  68%|▋| 10217/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  68%|▋| 10215/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  68%|▋| 10215/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -93890,8 +93743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10218/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  68%|▋| 10218/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  68%|▋| 10216/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  68%|▋| 10216/14932 [14:37<06:45, 11.64it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -93899,8 +93752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10219/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  68%|▋| 10219/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  68%|▋| 10217/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  68%|▋| 10217/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -93908,8 +93761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10220/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  68%|▋| 10220/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  68%|▋| 10218/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  68%|▋| 10218/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -93917,8 +93770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10221/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  68%|▋| 10221/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  68%|▋| 10219/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  68%|▋| 10219/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -93926,8 +93779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10222/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  68%|▋| 10222/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  68%|▋| 10220/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  68%|▋| 10220/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -93935,8 +93788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10223/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  68%|▋| 10223/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  68%|▋| 10221/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  68%|▋| 10221/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -93944,8 +93797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10224/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  68%|▋| 10224/14932 [14:39<06:45, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  68%|▋| 10222/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  68%|▋| 10222/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -93953,8 +93806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10225/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  68%|▋| 10225/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  68%|▋| 10223/14932 [14:37<06:44, 11.64it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  68%|▋| 10223/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -93962,8 +93815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10226/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  68%|▋| 10226/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  68%|▋| 10224/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  68%|▋| 10224/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -93971,8 +93824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10227/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  68%|▋| 10227/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  68%|▋| 10225/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  68%|▋| 10225/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -93980,8 +93833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  68%|▋| 10228/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  68%|▋| 10228/14932 [14:39<06:44, 11.62it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  68%|▋| 10226/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  68%|▋| 10226/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -93989,8 +93842,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10229/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  69%|▋| 10229/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  68%|▋| 10227/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  68%|▋| 10227/14932 [14:38<06:44, 11.64it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -93998,8 +93851,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10230/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10230/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  68%|▋| 10228/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  68%|▋| 10228/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -94007,8 +93860,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10231/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10231/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  69%|▋| 10229/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  69%|▋| 10229/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -94016,8 +93869,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10232/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  69%|▋| 10232/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10230/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  69%|▋| 10230/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94025,8 +93878,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10233/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10233/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10231/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10231/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -94034,8 +93887,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10234/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10234/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10232/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  69%|▋| 10232/14932 [14:38<06:43, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94043,8 +93896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10235/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10235/14932 [14:40<06:44, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10233/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10233/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -94052,8 +93905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10236/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10236/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10234/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10234/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -94061,8 +93914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10237/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10237/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  69%|▋| 10235/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  69%|▋| 10235/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -94070,8 +93923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10238/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  69%|▋| 10238/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10236/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  69%|▋| 10236/14932 [14:38<06:43, 11.65it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -94079,8 +93932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10239/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10239/14932 [14:40<06:43, 11.62it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10237/14932 [14:39<06:43, 11.65it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  69%|▋| 10237/14932 [14:39<06:43, 11.65it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -94088,8 +93941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10240/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10240/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10238/14932 [14:39<06:43, 11.65it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  69%|▋| 10238/14932 [14:39<06:43, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94097,8 +93950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10241/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10241/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10239/14932 [14:39<06:42, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10239/14932 [14:39<06:42, 11.65it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -94106,8 +93959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10242/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10242/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  69%|▋| 10240/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  69%|▋| 10240/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -94115,8 +93968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10243/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  69%|▋| 10243/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10241/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  69%|▋| 10241/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -94124,8 +93977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10244/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10244/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10242/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10242/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94133,8 +93986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10245/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10245/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10243/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10243/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94142,8 +93995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10246/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10246/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  69%|▋| 10244/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10244/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -94151,8 +94004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10247/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  69%|▋| 10247/14932 [14:41<06:43, 11.62it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  69%|▋| 10245/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  69%|▋| 10245/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94160,8 +94013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10248/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  69%|▋| 10248/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10246/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10246/14932 [14:39<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94169,8 +94022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10249/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10249/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  69%|▋| 10247/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10247/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -94178,8 +94031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10250/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  69%|▋| 10250/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10248/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  69%|▋| 10248/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -94187,8 +94040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10251/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10251/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10249/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  69%|▋| 10249/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -94196,8 +94049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10252/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10252/14932 [14:41<06:42, 11.62it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  69%|▋| 10250/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  69%|▋| 10250/14932 [14:40<06:42, 11.64it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -94205,8 +94058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10253/14932 [14:41<06:42, 11.63it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  69%|▋| 10253/14932 [14:41<06:42, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10251/14932 [14:40<06:41, 11.64it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  69%|▋| 10251/14932 [14:40<06:41, 11.64it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94214,8 +94067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10254/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10254/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10252/14932 [14:40<06:41, 11.64it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10252/14932 [14:40<06:41, 11.64it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -94223,8 +94076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10255/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10255/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  69%|▋| 10253/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  69%|▋| 10253/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -94232,8 +94085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10256/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  69%|▋| 10256/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10254/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10254/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -94241,8 +94094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10257/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10257/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  69%|▋| 10255/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  69%|▋| 10255/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -94250,8 +94103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10258/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  69%|▋| 10258/14932 [14:42<06:42, 11.63it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  69%|▋| 10256/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  69%|▋| 10256/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -94259,8 +94112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10259/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  69%|▋| 10259/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  69%|▋| 10257/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  69%|▋| 10257/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -94268,8 +94121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10260/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  69%|▋| 10260/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  69%|▋| 10258/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  69%|▋| 10258/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -94277,8 +94130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10261/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  69%|▋| 10261/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  69%|▋| 10259/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10259/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -94286,8 +94139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10262/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  69%|▋| 10262/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  69%|▋| 10260/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  69%|▋| 10260/14932 [14:40<06:41, 11.65it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -94295,8 +94148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10263/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  69%|��| 10263/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  69%|▋| 10261/14932 [14:41<06:41, 11.65it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  69%|▋| 10261/14932 [14:41<06:41, 11.65it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -94304,8 +94157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10264/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  69%|▋| 10264/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  69%|▋| 10262/14932 [14:41<06:41, 11.65it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  69%|▋| 10262/14932 [14:41<06:41, 11.65it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -94313,8 +94166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10265/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  69%|▋| 10265/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10263/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10263/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -94322,8 +94175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10266/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10266/14932 [14:42<06:41, 11.63it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10264/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  69%|▋| 10264/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -94331,8 +94184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10267/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10267/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  69%|▋| 10265/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  69%|▋| 10265/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -94340,8 +94193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10268/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  69%|▋| 10268/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10266/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10266/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -94349,8 +94202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10269/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10269/14932 [14:43<06:41, 11.63it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  69%|▋| 10267/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10267/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -94358,8 +94211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10270/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  69%|▋| 10270/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10268/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  69%|▋| 10268/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94367,8 +94220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10271/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10271/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  69%|▋| 10269/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10269/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -94376,8 +94229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10272/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  69%|▋| 10272/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  69%|▋| 10270/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10270/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -94385,8 +94238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10273/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  69%|▋| 10273/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  69%|▋| 10271/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  69%|▋| 10271/14932 [14:41<06:40, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94394,8 +94247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10274/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  69%|▋| 10274/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  69%|▋| 10272/14932 [14:42<06:40, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10272/14932 [14:42<06:40, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -94403,8 +94256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10275/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  69%|▋| 10275/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  69%|▋| 10273/14932 [14:42<06:40, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10273/14932 [14:42<06:40, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -94412,8 +94265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10276/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  69%|▋| 10276/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10274/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10274/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -94421,8 +94274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10277/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10277/14932 [14:43<06:40, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10275/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10275/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94430,8 +94283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10278/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10278/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10276/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10276/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -94439,8 +94292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10279/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10279/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10277/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  69%|▋| 10277/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94448,8 +94301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10280/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10280/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  69%|▋| 10278/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10278/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -94457,8 +94310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10281/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  69%|▋| 10281/14932 [14:44<06:40, 11.63it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10279/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  69%|▋| 10279/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -94466,8 +94319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10282/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10282/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10280/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  69%|▋| 10280/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94475,8 +94328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10283/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10283/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10281/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10281/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -94484,8 +94337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10284/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10284/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10282/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10282/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -94493,8 +94346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10285/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10285/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10283/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10283/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -94502,8 +94355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10286/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10286/14932 [14:44<06:39, 11.62it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10284/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  69%|▋| 10284/14932 [14:42<06:39, 11.65it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -94511,8 +94364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10287/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10287/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10285/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  69%|▋| 10285/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -94520,8 +94373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10288/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10288/14932 [14:44<06:39, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10286/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10286/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -94529,8 +94382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10289/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10289/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10287/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  69%|▋| 10287/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -94538,8 +94391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10290/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  69%|▋| 10290/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  69%|▋| 10288/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  69%|▋| 10288/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -94547,8 +94400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10291/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  69%|▋| 10291/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10289/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  69%|▋| 10289/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94556,8 +94409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10292/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10292/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10290/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10290/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -94565,8 +94418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10293/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10293/14932 [14:45<06:39, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10291/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10291/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -94574,8 +94427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10294/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10294/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  69%|▋| 10292/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10292/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -94583,8 +94436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10295/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  69%|▋| 10295/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10293/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  69%|▋| 10293/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -94592,8 +94445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10296/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10296/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  69%|▋| 10294/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10294/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -94601,8 +94454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10297/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  69%|▋| 10297/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  69%|▋| 10295/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  69%|▋| 10295/14932 [14:43<06:38, 11.65it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -94610,8 +94463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10298/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  69%|▋| 10298/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  69%|▋| 10296/14932 [14:43<06:37, 11.65it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  69%|▋| 10296/14932 [14:43<06:37, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94619,8 +94472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10299/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  69%|▋| 10299/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  69%|▋| 10297/14932 [14:43<06:37, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10297/14932 [14:43<06:37, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -94628,8 +94481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10300/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  69%|▋| 10300/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10298/14932 [14:43<06:37, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10298/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -94637,8 +94490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10301/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10301/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  69%|▋| 10299/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10299/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -94646,8 +94499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10302/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  69%|▋| 10302/14932 [14:45<06:38, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10300/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  69%|▋| 10300/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -94655,8 +94508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10303/14932 [14:46<06:38, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10303/14932 [14:46<06:38, 11.63it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  69%|▋| 10301/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  69%|▋| 10301/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -94664,8 +94517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10304/14932 [14:46<06:38, 11.63it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  69%|▋| 10304/14932 [14:46<06:38, 11.63it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  69%|▋| 10302/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  69%|▋| 10302/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94673,8 +94526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10305/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  69%|▋| 10305/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10303/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10303/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -94682,8 +94535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10306/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10306/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  69%|▋| 10304/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  69%|▋| 10304/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -94691,8 +94544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10307/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  69%|▋| 10307/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10305/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10305/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -94700,8 +94553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10308/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10308/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10306/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  69%|▋| 10306/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -94709,8 +94562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10309/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10309/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  69%|▋| 10307/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  69%|▋| 10307/14932 [14:44<06:37, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -94718,8 +94571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10310/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  69%|▋| 10310/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10308/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10308/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -94727,8 +94580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10311/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10311/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  69%|▋| 10309/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  69%|▋| 10309/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94736,8 +94589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10312/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  69%|▋| 10312/14932 [14:46<06:37, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10310/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10310/14932 [14:44<06:36, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -94745,8 +94598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10313/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10313/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  69%|▋| 10311/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10311/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=5.8"
      ]
     },
     {
@@ -94754,8 +94607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10314/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  69%|▋| 10314/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10312/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=5.8\r",
+      "Epoch 0:  69%|▋| 10312/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94763,8 +94616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10315/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10315/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10313/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10313/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -94772,8 +94625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10316/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10316/14932 [14:47<06:37, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10314/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  69%|▋| 10314/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -94781,8 +94634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10317/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10317/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  69%|▋| 10315/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  69%|▋| 10315/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -94790,8 +94643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10318/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  69%|▋| 10318/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10316/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10316/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -94799,8 +94652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10319/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10319/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  69%|▋| 10317/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10317/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -94808,8 +94661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10320/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  69%|▋| 10320/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10318/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  69%|▋| 10318/14932 [14:45<06:36, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -94817,8 +94670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10321/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10321/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10319/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  69%|▋| 10319/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94826,8 +94679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10322/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10322/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10320/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10320/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -94835,8 +94688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10323/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10323/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10321/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  69%|▋| 10321/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -94844,8 +94697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10324/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10324/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10322/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  69%|▋| 10322/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -94853,8 +94706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10325/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10325/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  69%|▋| 10323/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10323/14932 [14:45<06:35, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -94862,8 +94715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10326/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  69%|▋| 10326/14932 [14:47<06:36, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10324/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  69%|▋| 10324/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -94871,8 +94724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10327/14932 [14:48<06:36, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10327/14932 [14:48<06:36, 11.63it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  69%|▋| 10325/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10325/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94880,8 +94733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10328/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  69%|▋| 10328/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  69%|▋| 10326/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10326/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -94889,8 +94742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10329/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  69%|▋| 10329/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  69%|▋| 10327/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  69%|▋| 10327/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -94898,8 +94751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10330/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  69%|▋| 10330/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10328/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  69%|▋| 10328/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -94907,8 +94760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10331/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10331/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  69%|▋| 10329/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  69%|▋| 10329/14932 [14:46<06:35, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -94916,8 +94769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10332/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  69%|▋| 10332/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  69%|▋| 10330/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10330/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94925,8 +94778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10333/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  69%|▋| 10333/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  69%|▋| 10331/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10331/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -94934,8 +94787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10334/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  69%|▋| 10334/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  69%|▋| 10332/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10332/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -94943,8 +94796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10335/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  69%|▋| 10335/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10333/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10333/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -94952,8 +94805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10336/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10336/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10334/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  69%|▋| 10334/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -94961,8 +94814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10337/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10337/14932 [14:48<06:35, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10335/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10335/14932 [14:46<06:34, 11.65it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -94970,7 +94823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10338/14932 [14:49<06:35, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10336/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  69%|▋| 10336/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -94978,7 +94832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10338/14932 [14:49<06:35, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10337/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  69%|▋| 10337/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -94986,8 +94841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10339/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10339/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10338/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  69%|▋| 10338/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -94995,8 +94850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10340/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10340/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10339/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  69%|▋| 10339/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -95004,8 +94859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10341/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10341/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  69%|▋| 10340/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  69%|▋| 10340/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95013,8 +94868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10342/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  69%|▋| 10342/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10341/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10341/14932 [14:47<06:34, 11.65it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -95022,8 +94877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10343/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10343/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10342/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  69%|▋| 10342/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -95031,8 +94886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10344/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10344/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  69%|▋| 10343/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  69%|▋| 10343/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95040,8 +94895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10345/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  69%|▋| 10345/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10344/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  69%|▋| 10344/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95049,8 +94904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10346/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10346/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10345/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10345/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -95058,8 +94913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10347/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10347/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10346/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  69%|▋| 10346/14932 [14:47<06:33, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -95067,8 +94922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10348/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10348/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  69%|▋| 10347/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  69%|▋| 10347/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -95076,8 +94931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10349/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  69%|▋| 10349/14932 [14:49<06:34, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10348/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  69%|▋| 10348/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -95085,8 +94940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10350/14932 [14:49<06:33, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10350/14932 [14:49<06:33, 11.63it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10349/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10349/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95094,8 +94949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10351/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10351/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  69%|▋| 10350/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  69%|▋| 10350/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95103,8 +94958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10352/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  69%|▋| 10352/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  69%|▋| 10351/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10351/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -95112,8 +94967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10353/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  69%|▋| 10353/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  69%|▋| 10352/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10352/14932 [14:48<06:33, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -95121,8 +94976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10354/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  69%|▋| 10354/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  69%|▋| 10353/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  69%|▋| 10353/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -95130,8 +94985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10355/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  69%|▋| 10355/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  69%|▋| 10354/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  69%|▋| 10354/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95139,8 +94994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10356/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  69%|▋| 10356/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10355/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  69%|▋| 10355/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95148,8 +95003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10357/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10357/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10356/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  69%|▋| 10356/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95157,8 +95012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10358/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10358/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  69%|▋| 10357/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10357/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -95166,8 +95021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10359/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  69%|▋| 10359/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  69%|▋| 10358/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10358/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95175,8 +95030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10360/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  69%|▋| 10360/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  69%|▋| 10359/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  69%|▋| 10359/14932 [14:48<06:32, 11.65it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -95184,8 +95039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10361/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  69%|▋| 10361/14932 [14:50<06:33, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  69%|▋| 10360/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  69%|▋| 10360/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95193,8 +95048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10362/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  69%|▋| 10362/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  69%|▋| 10361/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10361/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95202,8 +95057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10363/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  69%|▋| 10363/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  69%|▋| 10362/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10362/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95211,8 +95066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10364/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  69%|▋| 10364/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  69%|▋| 10363/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10363/14932 [14:49<06:32, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -95220,8 +95075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10365/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  69%|▋| 10365/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  69%|▋| 10364/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10364/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95229,8 +95084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10366/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  69%|▋| 10366/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10365/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  69%|▋| 10365/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -95238,8 +95093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10367/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10367/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  69%|▋| 10366/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  69%|▋| 10366/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95247,8 +95102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10368/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  69%|▋| 10368/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10367/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  69%|▋| 10367/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95256,8 +95111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10369/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10369/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  69%|▋| 10368/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  69%|▋| 10368/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -95265,8 +95120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10370/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  69%|▋| 10370/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  69%|▋| 10369/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  69%|▋| 10369/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95274,8 +95129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10371/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  69%|▋| 10371/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  69%|▋| 10370/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10370/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95283,8 +95138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10372/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  69%|▋| 10372/14932 [14:51<06:32, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  69%|▋| 10371/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  69%|▋| 10371/14932 [14:49<06:31, 11.65it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -95292,8 +95147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10373/14932 [14:51<06:31, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  69%|▋| 10373/14932 [14:51<06:31, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  69%|▋| 10372/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  69%|▋| 10372/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -95301,8 +95156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10374/14932 [14:51<06:31, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  69%|▋| 10374/14932 [14:51<06:31, 11.63it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  69%|▋| 10373/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  69%|▋| 10373/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95310,8 +95165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10375/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  69%|▋| 10375/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  69%|▋| 10374/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10374/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -95319,8 +95174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10376/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  69%|▋| 10376/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10375/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  69%|▋| 10375/14932 [14:50<06:31, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95328,8 +95183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  69%|▋| 10377/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  69%|▋| 10377/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  69%|▋| 10376/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  69%|▋| 10376/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -95337,8 +95192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10378/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10378/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  69%|▋| 10377/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  69%|▋| 10377/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95346,8 +95201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10379/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10379/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10378/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10378/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95355,8 +95210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10380/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10380/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10379/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10379/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -95364,8 +95219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10381/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10381/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  70%|▋| 10380/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  70%|▋| 10380/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -95373,8 +95228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10382/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  70%|▋| 10382/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10381/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  70%|▋| 10381/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95382,8 +95237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10383/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10383/14932 [14:52<06:31, 11.63it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  70%|▋| 10382/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10382/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95391,8 +95246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10384/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  70%|▋| 10384/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10383/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10383/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -95400,8 +95255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10385/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10385/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  70%|▋| 10384/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  70%|▋| 10384/14932 [14:50<06:30, 11.65it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -95409,8 +95264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10386/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  70%|▋| 10386/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  70%|▋| 10385/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  70%|▋| 10385/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95418,8 +95273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10387/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  70%|▋| 10387/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  70%|▋| 10386/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10386/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -95427,8 +95282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10388/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  70%|▋| 10388/14932 [14:52<06:30, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10387/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10387/14932 [14:51<06:30, 11.65it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -95436,8 +95291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10389/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10389/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10388/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  70%|▋| 10388/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95445,8 +95300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10390/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10390/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10389/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10389/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -95454,8 +95309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10391/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10391/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  70%|▋| 10390/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  70%|▋| 10390/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95463,8 +95318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10392/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  70%|▋| 10392/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  70%|▋| 10391/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10391/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -95472,8 +95327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10393/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  70%|▋| 10393/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  70%|▋| 10392/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10392/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95481,8 +95336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10394/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  70%|▋| 10394/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  70%|▋| 10393/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10393/14932 [14:51<06:29, 11.65it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -95490,8 +95345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10395/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  70%|▋| 10395/14932 [14:53<06:30, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10394/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  70%|▋| 10394/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95499,8 +95354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10396/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10396/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  70%|▋| 10395/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10395/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95508,8 +95363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10397/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  70%|▋| 10397/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10396/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10396/14932 [14:51<06:29, 11.66it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -95517,8 +95372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10398/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10398/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10397/14932 [14:52<06:29, 11.66it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  70%|▋| 10397/14932 [14:52<06:29, 11.66it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -95526,8 +95381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10399/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10399/14932 [14:53<06:29, 11.63it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10398/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  70%|▋| 10398/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -95535,8 +95390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10400/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10400/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10399/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10399/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95544,8 +95399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10401/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10401/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10400/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10400/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95553,8 +95408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10402/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10402/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  70%|▋| 10401/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10401/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -95562,8 +95417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10403/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  70%|▋| 10403/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  70%|▋| 10402/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  70%|▋| 10402/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -95571,8 +95426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10404/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  70%|▋| 10404/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10403/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  70%|▋| 10403/14932 [14:52<06:28, 11.65it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95580,8 +95435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10405/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10405/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  70%|▋| 10404/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10404/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95589,8 +95444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10406/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  70%|▋| 10406/14932 [14:54<06:29, 11.63it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10405/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  70%|▋| 10405/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -95598,8 +95453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10407/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10407/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10406/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10406/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -95607,8 +95462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10408/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10408/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  70%|▋| 10407/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  70%|▋| 10407/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -95616,8 +95471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10409/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  70%|▋| 10409/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10408/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  70%|▋| 10408/14932 [14:52<06:28, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95625,8 +95480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10410/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10410/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  70%|▋| 10409/14932 [14:53<06:28, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10409/14932 [14:53<06:28, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95634,8 +95489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10411/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  70%|▋| 10411/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  70%|▋| 10410/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10410/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -95643,8 +95498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10412/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  70%|▋| 10412/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  70%|▋| 10411/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  70%|▋| 10411/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -95652,8 +95507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10413/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  70%|▋| 10413/14932 [14:54<06:28, 11.63it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  70%|▋| 10412/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  70%|▋| 10412/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95661,8 +95516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10414/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  70%|▋| 10414/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  70%|▋| 10413/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10413/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -95670,8 +95525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10415/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  70%|▋| 10415/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  70%|▋| 10414/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  70%|▋| 10414/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95679,8 +95534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10416/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  70%|▋| 10416/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10415/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10415/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -95688,8 +95543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10417/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10417/14932 [14:55<06:28, 11.64it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  70%|▋| 10416/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  70%|▋| 10416/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95697,8 +95552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10418/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  70%|▋| 10418/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  70%|▋| 10417/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  70%|▋| 10417/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -95706,8 +95561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10419/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  70%|▋| 10419/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  70%|▋| 10418/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10418/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95715,8 +95570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10420/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  70%|▋| 10420/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  70%|▋| 10419/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10419/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95724,8 +95579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10421/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  70%|▋| 10421/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10420/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  70%|▋| 10420/14932 [14:53<06:27, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -95733,8 +95588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10422/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10422/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10421/14932 [14:54<06:27, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  70%|▋| 10421/14932 [14:54<06:27, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95742,8 +95597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10423/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10423/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  70%|▋| 10422/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10422/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95751,8 +95606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10424/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  70%|▋| 10424/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10423/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  70%|▋| 10423/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95760,8 +95615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10425/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10425/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10424/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10424/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -95769,8 +95624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10426/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10426/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10425/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10425/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -95778,8 +95633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10427/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10427/14932 [14:55<06:27, 11.64it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  70%|▋| 10426/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  70%|▋| 10426/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -95787,8 +95642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10428/14932 [14:56<06:27, 11.64it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  70%|▋| 10428/14932 [14:56<06:27, 11.64it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  70%|▋| 10427/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  70%|▋| 10427/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -95796,8 +95651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10429/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  70%|▋| 10429/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10428/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10428/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -95805,8 +95660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10430/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10430/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  70%|▋| 10429/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  70%|▋| 10429/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -95814,8 +95669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10431/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  70%|▋| 10431/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10430/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  70%|▋| 10430/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95823,8 +95678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10432/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10432/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  70%|▋| 10431/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  70%|▋| 10431/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -95832,8 +95687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10433/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  70%|▋| 10433/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10432/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10432/14932 [14:54<06:26, 11.66it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -95841,8 +95696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10434/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10434/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  70%|▋| 10433/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  70%|▋| 10433/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -95850,8 +95705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10435/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  70%|▋| 10435/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  70%|▋| 10434/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  70%|▋| 10434/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -95859,8 +95714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10436/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  70%|▋| 10436/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  70%|▋| 10435/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  70%|▋| 10435/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -95868,8 +95723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10437/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  70%|▋| 10437/14932 [14:56<06:26, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10436/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10436/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -95877,8 +95732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10438/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10438/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10437/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  70%|▋| 10437/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -95886,8 +95741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10439/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10439/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  70%|▋| 10438/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  70%|▋| 10438/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -95895,8 +95750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10440/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  70%|▋| 10440/14932 [14:57<06:26, 11.64it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  70%|▋| 10439/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  70%|▋| 10439/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -95904,8 +95759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10441/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  70%|▋| 10441/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  70%|▋| 10440/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  70%|▋| 10440/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -95913,8 +95768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10442/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  70%|▋| 10442/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  70%|▋| 10441/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  70%|▋| 10441/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -95922,8 +95777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10443/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  70%|▋| 10443/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  70%|▋| 10442/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  70%|▋| 10442/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -95931,8 +95786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10444/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  70%|▋| 10444/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10443/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  70%|▋| 10443/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -95940,8 +95795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10445/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10445/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10444/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  70%|▋| 10444/14932 [14:55<06:25, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -95949,8 +95804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10446/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10446/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10445/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  70%|▋| 10445/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95958,8 +95813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10447/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10447/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10446/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10446/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -95967,8 +95822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10448/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10448/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10447/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10447/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -95976,8 +95831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10449/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10449/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10448/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  70%|▋| 10448/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -95985,8 +95840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10450/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10450/14932 [14:57<06:25, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10449/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  70%|▋| 10449/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -95994,8 +95849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10451/14932 [14:58<06:25, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10451/14932 [14:58<06:25, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10450/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10450/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -96003,8 +95858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10452/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10452/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10451/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10451/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96012,8 +95867,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10453/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10453/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10452/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96021,8 +95875,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10454/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10454/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10452/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96030,8 +95883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10455/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10455/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10453/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10453/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -96039,8 +95892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10456/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10456/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10454/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  70%|▋| 10454/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -96048,8 +95901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10457/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10457/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10455/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10455/14932 [14:56<06:24, 11.66it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -96057,8 +95910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10458/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10458/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10456/14932 [14:56<06:23, 11.66it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  70%|▋| 10456/14932 [14:56<06:23, 11.66it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -96066,8 +95919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10459/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10459/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10457/14932 [14:56<06:23, 11.66it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  70%|▋| 10457/14932 [14:56<06:23, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -96075,8 +95928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10460/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10460/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  70%|▋| 10458/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  70%|▋| 10458/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96084,8 +95937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10461/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  70%|▋| 10461/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  70%|▋| 10459/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10459/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -96093,8 +95946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10462/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  70%|▋| 10462/14932 [14:58<06:24, 11.64it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  70%|▋| 10460/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  70%|▋| 10460/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -96102,8 +95955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10463/14932 [14:58<06:23, 11.64it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  70%|▋| 10463/14932 [14:58<06:23, 11.64it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  70%|▋| 10461/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  70%|▋| 10461/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96111,8 +95964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10464/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  70%|▋| 10464/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10462/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10462/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -96120,8 +95973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10465/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10465/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10463/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  70%|▋| 10463/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -96129,8 +95982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10466/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10466/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10464/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  70%|▋| 10464/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -96138,8 +95991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10467/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10467/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10465/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10465/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96147,8 +96000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10468/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10468/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  70%|▋| 10466/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  70%|▋| 10466/14932 [14:57<06:23, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96156,8 +96009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10469/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  70%|▋| 10469/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  70%|▋| 10467/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  70%|▋| 10467/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -96165,8 +96018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10470/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  70%|▋| 10470/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  70%|▋| 10468/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  70%|▋| 10468/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -96174,8 +96027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10471/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  70%|▋| 10471/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  70%|▋| 10469/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  70%|▋| 10469/14932 [14:57<06:22, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96183,8 +96036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10472/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  70%|▋| 10472/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  70%|▋| 10470/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10470/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=5.6"
      ]
     },
     {
@@ -96192,8 +96045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10473/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  70%|▋| 10473/14932 [14:59<06:23, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10471/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=5.6\r",
+      "Epoch 0:  70%|▋| 10471/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -96201,8 +96054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10474/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10474/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10472/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10472/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96210,8 +96063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10475/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10475/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10473/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10473/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96219,8 +96072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10476/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10476/14932 [14:59<06:22, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10474/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10474/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96228,8 +96081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10477/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10477/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10475/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10475/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -96237,8 +96090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10478/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10478/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10476/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  70%|▋| 10476/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -96246,8 +96099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10479/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10479/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  70%|▋| 10477/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  70%|▋| 10477/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -96255,8 +96108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10480/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  70%|▋| 10480/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  70%|▋| 10478/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  70%|▋| 10478/14932 [14:58<06:22, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -96264,8 +96117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10481/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  70%|▋| 10481/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  70%|▋| 10479/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  70%|▋| 10479/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -96273,8 +96126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10482/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  70%|▋| 10482/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10480/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  70%|▋| 10480/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -96282,8 +96135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10483/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10483/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10481/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  70%|▋| 10481/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -96291,8 +96144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10484/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10484/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10482/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  70%|▋| 10482/14932 [14:58<06:21, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -96300,8 +96153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10485/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10485/14932 [15:00<06:22, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10483/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  70%|▋| 10483/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -96309,8 +96162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10486/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  70%|▋| 10486/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  70%|▋| 10484/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  70%|▋| 10484/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -96318,8 +96171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10487/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  70%|▋| 10487/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  70%|▋| 10485/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  70%|▋| 10485/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -96327,8 +96180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10488/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  70%|▋| 10488/14932 [15:00<06:21, 11.64it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  70%|▋| 10486/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  70%|▋| 10486/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -96336,8 +96189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10489/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  70%|▋| 10489/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10487/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  70%|▋| 10487/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96345,8 +96198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10490/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10490/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  70%|▋| 10488/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10488/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -96354,8 +96207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10491/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  70%|▋| 10491/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  70%|▋| 10489/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  70%|▋| 10489/14932 [14:59<06:21, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -96363,8 +96216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10492/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  70%|▋| 10492/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10490/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  70%|▋| 10490/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -96372,8 +96225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10493/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10493/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10491/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  70%|▋| 10491/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -96381,8 +96234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10494/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10494/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10492/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  70%|▋| 10492/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -96390,8 +96243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10495/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10495/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10493/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  70%|▋| 10493/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -96399,8 +96252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10496/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10496/14932 [15:01<06:21, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10494/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  70%|▋| 10494/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -96408,8 +96261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10497/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10497/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10495/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  70%|▋| 10495/14932 [14:59<06:20, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -96417,8 +96270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10498/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10498/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  70%|▋| 10496/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10496/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -96426,8 +96279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10499/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  70%|▋| 10499/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10497/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  70%|▋| 10497/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -96435,7 +96288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10500/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  70%|▋| 10498/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10498/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96443,7 +96297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10500/14932 [15:01<06:20, 11.64it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10499/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  70%|▋| 10499/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -96451,8 +96306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10501/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10501/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  70%|▋| 10500/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10500/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96460,8 +96315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10502/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  70%|▋| 10502/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10501/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  70%|▋| 10501/14932 [15:00<06:20, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96469,8 +96324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10503/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10503/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10502/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  70%|▋| 10502/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -96478,8 +96333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10504/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10504/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  70%|▋| 10503/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10503/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -96487,8 +96342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10505/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  70%|▋| 10505/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  70%|▋| 10504/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  70%|▋| 10504/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -96496,8 +96351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10506/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  70%|▋| 10506/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  70%|▋| 10505/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  70%|▋| 10505/14932 [15:00<06:19, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -96505,8 +96360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10507/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  70%|▋| 10507/14932 [15:02<06:20, 11.64it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10506/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  70%|▋| 10506/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -96514,8 +96369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10508/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10508/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  70%|▋| 10507/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  70%|▋| 10507/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -96523,8 +96378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10509/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  70%|▋| 10509/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  70%|▋| 10508/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  70%|▋| 10508/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96532,8 +96387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10510/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  70%|▋| 10510/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  70%|▋| 10509/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10509/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -96541,8 +96396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10511/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  70%|▋| 10511/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  70%|▋| 10510/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  70%|▋| 10510/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -96550,8 +96405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10512/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  70%|▋| 10512/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10511/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  70%|▋| 10511/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -96559,8 +96414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10513/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10513/14932 [15:02<06:19, 11.64it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  70%|▋| 10512/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  70%|▋| 10512/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -96568,8 +96423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10514/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  70%|▋| 10514/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  70%|▋| 10513/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  70%|▋| 10513/14932 [15:01<06:19, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -96577,8 +96432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10515/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  70%|▋| 10515/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  70%|▋| 10514/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  70%|▋| 10514/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -96586,8 +96441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10516/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  70%|▋| 10516/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  70%|▋| 10515/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  70%|▋| 10515/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -96595,8 +96450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10517/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  70%|▋| 10517/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10516/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  70%|▋| 10516/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96604,8 +96459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10518/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10518/14932 [15:03<06:19, 11.64it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  70%|▋| 10517/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  70%|▋| 10517/14932 [15:01<06:18, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -96613,8 +96468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10519/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  70%|▋| 10519/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  70%|▋| 10518/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  70%|▋| 10518/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -96622,8 +96477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10520/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  70%|▋| 10520/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  70%|▋| 10519/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  70%|▋| 10519/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -96631,8 +96486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10521/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  70%|▋| 10521/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10520/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  70%|▋| 10520/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96640,8 +96495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10522/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  70%|▋| 10522/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  70%|▋| 10521/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  70%|▋| 10521/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -96649,8 +96504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10523/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  70%|▋| 10523/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  70%|▋| 10522/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  70%|▋| 10522/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -96658,8 +96513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10524/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  70%|▋| 10524/14932 [15:03<06:18, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  70%|▋| 10523/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  70%|▋| 10523/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -96667,8 +96522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10525/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  70%|▋| 10525/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  70%|▋| 10524/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  70%|▋| 10524/14932 [15:02<06:18, 11.66it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -96676,8 +96531,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10526/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  70%|▋| 10526/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  70%|▋| 10525/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -96685,8 +96539,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  70%|▋| 10527/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  70%|▋| 10527/14932 [15:03<06:18, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  70%|▋| 10525/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96694,8 +96547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10528/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  71%|▋| 10528/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  70%|▋| 10526/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  70%|▋| 10526/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96703,8 +96556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10529/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10529/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  70%|▋| 10527/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  70%|▋| 10527/14932 [15:02<06:17, 11.66it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -96712,8 +96565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10530/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10530/14932 [15:04<06:18, 11.64it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  71%|▋| 10528/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  71%|▋| 10528/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -96721,8 +96574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10531/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  71%|▋| 10531/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10529/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10529/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -96730,8 +96583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10532/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10532/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10530/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  71%|▋| 10530/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -96739,8 +96592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10533/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10533/14932 [15:04<06:17, 11.64it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  71%|▋| 10531/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  71%|▋| 10531/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -96748,8 +96601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10534/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  71%|▋| 10534/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10532/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10532/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96757,8 +96610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10535/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10535/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  71%|▋| 10533/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10533/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -96766,8 +96619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10536/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  71%|▋| 10536/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10534/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10534/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -96775,7 +96628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10537/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10535/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10535/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -96783,7 +96637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10537/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10536/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10536/14932 [15:03<06:17, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -96791,8 +96646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10538/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10538/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  71%|▋| 10537/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  71%|▋| 10537/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -96800,8 +96655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10539/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  71%|▋| 10539/14932 [15:04<06:17, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10538/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  71%|▋| 10538/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -96809,8 +96664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10540/14932 [15:05<06:17, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10540/14932 [15:05<06:17, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10539/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  71%|▋| 10539/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -96818,8 +96673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10541/14932 [15:05<06:17, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10541/14932 [15:05<06:17, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  71%|▋| 10540/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10540/14932 [15:03<06:16, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -96827,8 +96682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10542/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  71%|▋| 10542/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10541/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  71%|▋| 10541/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -96836,8 +96691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10543/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10543/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10542/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10542/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96845,8 +96700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10544/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10544/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10543/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10543/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96854,8 +96709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10545/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10545/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10544/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10544/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -96863,8 +96718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10546/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10546/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  71%|▋| 10545/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  71%|▋| 10545/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96872,8 +96727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10547/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  71%|▋| 10547/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10546/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10546/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -96881,8 +96736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10548/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10548/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10547/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10547/14932 [15:04<06:16, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -96890,8 +96745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10549/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10549/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10548/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  71%|▋| 10548/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -96899,8 +96754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10550/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10550/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10549/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10549/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -96908,8 +96763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10551/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10551/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  71%|▋| 10550/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  71%|▋| 10550/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -96917,8 +96772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10552/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  71%|▋| 10552/14932 [15:05<06:16, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10551/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  71%|▋| 10551/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96926,8 +96781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10553/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10553/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  71%|▋| 10552/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10552/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96935,8 +96790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10554/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  71%|▋| 10554/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10553/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10553/14932 [15:04<06:15, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -96944,8 +96799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10555/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10555/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10554/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10554/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -96953,8 +96808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10556/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10556/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10555/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10555/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -96962,8 +96817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10557/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10557/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10556/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10556/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -96971,8 +96826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10558/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10558/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10557/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10557/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -96980,8 +96835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10559/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10559/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10558/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10558/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -96989,8 +96844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10560/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10560/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10559/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  71%|▋| 10559/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -96998,8 +96853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10561/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10561/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10560/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10560/14932 [15:05<06:15, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97007,8 +96862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10562/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10562/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10561/14932 [15:05<06:14, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10561/14932 [15:05<06:14, 11.66it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -97016,8 +96871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10563/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10563/14932 [15:06<06:15, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  71%|▋| 10562/14932 [15:05<06:14, 11.66it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  71%|▋| 10562/14932 [15:05<06:14, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -97025,8 +96880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10564/14932 [15:07<06:15, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  71%|▋| 10564/14932 [15:07<06:15, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10563/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10563/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97034,8 +96889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10565/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10565/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10564/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10564/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -97043,8 +96898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10566/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10566/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10565/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10565/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97052,8 +96907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10567/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10567/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10566/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10566/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -97061,8 +96916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10568/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10568/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  71%|▋| 10567/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10567/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97070,8 +96925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10569/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  71%|▋| 10569/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10568/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10568/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -97079,8 +96934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10570/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10570/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10569/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10569/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -97088,8 +96943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10571/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10571/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10570/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  71%|▋| 10570/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -97097,8 +96952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10572/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10572/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10571/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10571/14932 [15:06<06:14, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -97106,8 +96961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10573/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10573/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10572/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10572/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -97115,8 +96970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10574/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10574/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  71%|▋| 10573/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10573/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -97124,8 +96979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10575/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  71%|▋| 10575/14932 [15:07<06:14, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10574/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  71%|▋| 10574/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97133,8 +96988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10576/14932 [15:07<06:13, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10576/14932 [15:07<06:13, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10575/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10575/14932 [15:06<06:13, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97142,8 +96997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10577/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10577/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10576/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10576/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97151,8 +97006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10578/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10578/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  71%|▋| 10577/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10577/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -97160,8 +97015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10579/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  71%|▋| 10579/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  71%|▋| 10578/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10578/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -97169,8 +97024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10580/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  71%|▋| 10580/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10579/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  71%|▋| 10579/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -97178,8 +97033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10581/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10581/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10580/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10580/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -97187,8 +97042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10582/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10582/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10581/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10581/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -97196,8 +97051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10583/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10583/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10582/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10582/14932 [15:07<06:13, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -97205,8 +97060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10584/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10584/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10583/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  71%|▋| 10583/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -97214,8 +97069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10585/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10585/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10584/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  71%|▋| 10584/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -97223,8 +97078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10586/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10586/14932 [15:08<06:13, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  71%|▋| 10585/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  71%|▋| 10585/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -97232,8 +97087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10587/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  71%|▋| 10587/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10586/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  71%|▋| 10586/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -97241,8 +97096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10588/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10588/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10587/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  71%|▋| 10587/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -97250,8 +97105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10589/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10589/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  71%|▋| 10588/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  71%|▋| 10588/14932 [15:07<06:12, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97259,8 +97114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10590/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  71%|▋| 10590/14932 [15:08<06:12, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  71%|▋| 10589/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10589/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -97268,8 +97123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10591/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  71%|▋| 10591/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10590/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  71%|▋| 10590/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -97277,8 +97132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10592/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10592/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10591/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10591/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -97286,8 +97141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10593/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10593/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  71%|▋| 10592/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  71%|▋| 10592/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -97295,8 +97150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10594/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  71%|▋| 10594/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10593/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  71%|▋| 10593/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97304,8 +97159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10595/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10595/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10594/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10594/14932 [15:08<06:12, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97313,8 +97168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10596/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10596/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  71%|▋| 10595/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10595/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -97322,8 +97177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10597/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  71%|▋| 10597/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  71%|▋| 10596/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  71%|▋| 10596/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97331,8 +97186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10598/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  71%|▋| 10598/14932 [15:09<06:12, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10597/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10597/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97340,8 +97195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10599/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10599/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10598/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10598/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97349,8 +97204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10600/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10600/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10599/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10599/14932 [15:08<06:11, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -97358,7 +97213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10601/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10600/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10600/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97366,7 +97222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10601/14932 [15:09<06:11, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  71%|▋| 10601/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10601/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97374,8 +97231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10602/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  71%|▋| 10602/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10602/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10602/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -97383,8 +97240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10603/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10603/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10603/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10603/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -97392,8 +97249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10604/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10604/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  71%|▋| 10604/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  71%|▋| 10604/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97401,8 +97258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10605/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  71%|▋| 10605/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10605/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10605/14932 [15:09<06:11, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97410,8 +97267,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10606/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10606/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10606/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97419,8 +97275,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10607/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10607/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10606/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -97428,8 +97283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10608/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10608/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10607/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10607/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97437,8 +97292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10609/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10609/14932 [15:10<06:11, 11.65it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  71%|▋| 10608/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10608/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -97446,8 +97301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10610/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  71%|▋| 10610/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10609/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  71%|▋| 10609/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97455,8 +97310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10611/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10611/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10610/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10610/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97464,8 +97319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10612/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10612/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10611/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10611/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97473,8 +97328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10613/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10613/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  71%|▋| 10612/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10612/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97482,8 +97337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10614/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  71%|▋| 10614/14932 [15:10<06:10, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10613/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10613/14932 [15:09<06:10, 11.66it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97491,8 +97346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10615/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10615/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10614/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10614/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97500,8 +97355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10616/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10616/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  71%|▋| 10615/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10615/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -97509,8 +97364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10617/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  71%|▋| 10617/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10616/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  71%|▋| 10616/14932 [15:10<06:10, 11.66it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -97518,8 +97373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10618/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10618/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10617/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  71%|▋| 10617/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -97527,8 +97382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10619/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10619/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10618/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  71%|▋| 10618/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -97536,8 +97391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10620/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10620/14932 [15:11<06:10, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10619/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10619/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -97545,8 +97400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10621/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10621/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10620/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  71%|▋| 10620/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -97554,8 +97409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10622/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10622/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10621/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  71%|▋| 10621/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97563,8 +97418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10623/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10623/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10622/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10622/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -97572,7 +97427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10624/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10623/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  71%|▋| 10623/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -97580,7 +97436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10624/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  71%|▋| 10624/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  71%|▋| 10624/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -97588,8 +97445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10625/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  71%|▋| 10625/14932 [15:11<06:09, 11.65it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  71%|▋| 10625/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10625/14932 [15:10<06:09, 11.66it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -97597,8 +97454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10626/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  71%|▋| 10626/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10626/14932 [15:11<06:09, 11.66it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  71%|▋| 10626/14932 [15:11<06:09, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -97606,8 +97463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10627/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10627/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10627/14932 [15:11<06:09, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10627/14932 [15:11<06:09, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -97615,8 +97472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10628/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10628/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10628/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10628/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -97624,8 +97481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10629/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10629/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10629/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  71%|▋| 10629/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97633,8 +97490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10630/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10630/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10630/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10630/14932 [15:11<06:08, 11.66it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -97642,8 +97499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10631/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10631/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10631/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  71%|▋| 10631/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -97651,8 +97508,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10632/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10632/14932 [15:12<06:09, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10632/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -97660,8 +97516,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10633/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10633/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  71%|▋| 10632/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -97669,8 +97524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10634/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  71%|▋| 10634/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10633/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  71%|▋| 10633/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97678,8 +97533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10635/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10635/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  71%|▋| 10634/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10634/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97687,8 +97542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10636/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  71%|▋| 10636/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10635/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10635/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97696,8 +97551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10637/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10637/14932 [15:12<06:08, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10636/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10636/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -97705,8 +97560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10638/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10638/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10637/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10637/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97714,8 +97569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10639/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10639/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  71%|▋| 10638/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10638/14932 [15:11<06:08, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -97723,8 +97578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10640/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  71%|▋| 10640/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10639/14932 [15:11<06:07, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  71%|▋| 10639/14932 [15:11<06:07, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97732,8 +97587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10641/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10641/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10640/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10640/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -97741,8 +97596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10642/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10642/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10641/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10641/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -97750,8 +97605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10643/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10643/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10642/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10642/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97759,8 +97614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10644/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10644/14932 [15:13<06:08, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10643/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10643/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -97768,8 +97623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10645/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10645/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  71%|▋| 10644/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10644/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -97777,8 +97632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10646/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  71%|▋| 10646/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10645/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  71%|▋| 10645/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97786,8 +97641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10647/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10647/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  71%|▋| 10646/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10646/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -97795,8 +97650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10648/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  71%|▋| 10648/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  71%|▋| 10647/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  71%|▋| 10647/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -97804,8 +97659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10649/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  71%|▋| 10649/14932 [15:13<06:07, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  71%|▋| 10648/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  71%|▋| 10648/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -97813,8 +97668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10650/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  71%|▋| 10650/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10649/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  71%|▋| 10649/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -97822,8 +97677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10651/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10651/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10650/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  71%|▋| 10650/14932 [15:12<06:07, 11.67it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -97831,8 +97686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10652/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10652/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  71%|▋| 10651/14932 [15:12<06:06, 11.67it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  71%|▋| 10651/14932 [15:12<06:06, 11.67it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -97840,8 +97695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10653/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  71%|▋| 10653/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  71%|▋| 10652/14932 [15:12<06:06, 11.67it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  71%|▋| 10652/14932 [15:12<06:06, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -97849,8 +97704,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10654/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  71%|▋| 10654/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10653/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -97858,8 +97712,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10655/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10655/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10653/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -97867,8 +97720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10656/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10656/14932 [15:14<06:07, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  71%|▋| 10654/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  71%|▋| 10654/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97876,8 +97729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10657/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  71%|▋| 10657/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10655/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10655/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -97885,8 +97738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10658/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10658/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  71%|▋| 10656/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  71%|▋| 10656/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -97894,8 +97747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10659/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  71%|▋| 10659/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10657/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  71%|▋| 10657/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97903,8 +97756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10660/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10660/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  71%|▋| 10658/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10658/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -97912,8 +97765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10661/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  71%|▋| 10661/14932 [15:14<06:06, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10659/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  71%|▋| 10659/14932 [15:13<06:06, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -97921,8 +97774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10662/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  71%|▋| 10662/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  71%|▋| 10660/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  71%|▋| 10660/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -97930,8 +97783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10663/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  71%|▋| 10663/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10661/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  71%|▋| 10661/14932 [15:13<06:06, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -97939,8 +97792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10664/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10664/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  71%|▋| 10662/14932 [15:14<06:06, 11.66it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  71%|▋| 10662/14932 [15:14<06:06, 11.66it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -97948,8 +97801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10665/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  71%|▋| 10665/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  71%|▋| 10663/14932 [15:14<06:05, 11.66it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  71%|▋| 10663/14932 [15:14<06:05, 11.66it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -97957,8 +97810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10666/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  71%|▋| 10666/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10664/14932 [15:14<06:05, 11.66it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  71%|▋| 10664/14932 [15:14<06:05, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -97966,7 +97819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10667/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  71%|▋| 10665/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10665/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -97974,7 +97828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10667/14932 [15:15<06:06, 11.65it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  71%|▋| 10666/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  71%|▋| 10666/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -97982,8 +97837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10668/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  71%|▋| 10668/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  71%|▋| 10667/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  71%|▋| 10667/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -97991,8 +97846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10669/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  71%|▋| 10669/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  71%|▋| 10668/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  71%|▋| 10668/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -98000,8 +97855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10670/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  71%|▋| 10670/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  71%|▋| 10669/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10669/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -98009,8 +97864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10671/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  71%|▋| 10671/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  71%|▋| 10670/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  71%|▋| 10670/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -98018,8 +97873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10672/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  71%|▋| 10672/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10671/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  71%|▋| 10671/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -98027,8 +97882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10673/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  71%|▋| 10673/14932 [15:15<06:05, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  71%|▋| 10672/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  71%|▋| 10672/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -98036,8 +97891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10674/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  71%|▋| 10674/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  71%|▋| 10673/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  71%|▋| 10673/14932 [15:14<06:05, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -98045,8 +97900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10675/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  71%|▋| 10675/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  71%|▋| 10674/14932 [15:14<06:04, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  71%|▋| 10674/14932 [15:14<06:04, 11.67it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -98054,8 +97909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  71%|▋| 10676/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  71%|▋| 10676/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  71%|▋| 10675/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  71%|▋| 10675/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98063,8 +97918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10677/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  72%|▋| 10677/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  71%|▋| 10676/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  71%|▋| 10676/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -98072,8 +97927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10678/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10678/14932 [15:16<06:05, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10677/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  72%|▋| 10677/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98081,8 +97936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10679/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10679/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10678/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10678/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -98090,8 +97945,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10680/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10680/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  72%|▋| 10679/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -98099,8 +97953,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10681/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  72%|▋| 10681/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10679/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -98108,8 +97961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10682/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10682/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  72%|▋| 10680/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  72%|▋| 10680/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98117,8 +97970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10683/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  72%|▋| 10683/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10681/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10681/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98126,8 +97979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10684/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10684/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10682/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10682/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -98135,8 +97988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10685/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10685/14932 [15:16<06:04, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  72%|▋| 10683/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  72%|▋| 10683/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -98144,8 +97997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10686/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  72%|▋| 10686/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10684/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  72%|▋| 10684/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98153,8 +98006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10687/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10687/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10685/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10685/14932 [15:15<06:04, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -98162,8 +98015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10688/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10688/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10686/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10686/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -98171,8 +98024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10689/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10689/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  72%|▋| 10687/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  72%|▋| 10687/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -98180,8 +98033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10690/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  72%|▋| 10690/14932 [15:17<06:04, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10688/14932 [15:16<06:03, 11.66it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  72%|▋| 10688/14932 [15:16<06:03, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -98189,8 +98042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10691/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10691/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  72%|▋| 10689/14932 [15:16<06:03, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  72%|▋| 10689/14932 [15:16<06:03, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98198,8 +98051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10692/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  72%|▋| 10692/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10690/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10690/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -98207,8 +98060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10693/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10693/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10691/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  72%|▋| 10691/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98216,8 +98069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10694/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10694/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  72%|▋| 10692/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10692/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -98225,8 +98078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10695/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  72%|▋| 10695/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  72%|▋| 10693/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  72%|▋| 10693/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98234,8 +98087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10696/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  72%|▋| 10696/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  72%|▋| 10694/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10694/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -98243,8 +98096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10697/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  72%|▋| 10697/14932 [15:17<06:03, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  72%|▋| 10695/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  72%|▋| 10695/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -98252,8 +98105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10698/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  72%|▋| 10698/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  72%|▋| 10696/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  72%|▋| 10696/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -98261,8 +98114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10699/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  72%|▋| 10699/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10697/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10697/14932 [15:16<06:03, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -98270,8 +98123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10700/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10700/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10698/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  72%|▋| 10698/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -98279,8 +98132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10701/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10701/14932 [15:18<06:03, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10699/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  72%|▋| 10699/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -98288,8 +98141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10702/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  72%|▋| 10702/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  72%|▋| 10700/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  72%|▋| 10700/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -98297,8 +98150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10703/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  72%|▋| 10703/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  72%|▋| 10701/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  72%|▋| 10701/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98306,8 +98159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10704/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  72%|▋| 10704/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  72%|▋| 10702/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10702/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -98315,8 +98168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10705/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  72%|▋| 10705/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10703/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10703/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -98324,8 +98177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10706/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10706/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  72%|▋| 10704/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  72%|▋| 10704/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98333,8 +98186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10707/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  72%|▋| 10707/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  72%|▋| 10705/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10705/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98342,8 +98195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10708/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  72%|▋| 10708/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10706/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10706/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98351,8 +98204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10709/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10709/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  72%|▋| 10707/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10707/14932 [15:17<06:02, 11.66it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98360,8 +98213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10710/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  72%|▋| 10710/14932 [15:18<06:02, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10708/14932 [15:17<06:02, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10708/14932 [15:17<06:02, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98369,8 +98222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10711/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10711/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10709/14932 [15:18<06:02, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10709/14932 [15:18<06:02, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -98378,8 +98231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10712/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10712/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10710/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10710/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98387,8 +98240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10713/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10713/14932 [15:19<06:02, 11.65it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  72%|▋| 10711/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10711/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -98396,8 +98249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10714/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  72%|▋| 10714/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  72%|▋| 10712/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  72%|▋| 10712/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98405,8 +98258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10715/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  72%|▋| 10715/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  72%|▋| 10713/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10713/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -98414,8 +98267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10716/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  72%|▋| 10716/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  72%|▋| 10714/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  72%|▋| 10714/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -98423,8 +98276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10717/14932 [15:19<06:01, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  72%|▋| 10717/14932 [15:19<06:01, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  72%|▋| 10715/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  72%|▋| 10715/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -98432,8 +98285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10718/14932 [15:19<06:01, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  72%|▋| 10718/14932 [15:19<06:01, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10716/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  72%|▋| 10716/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -98441,8 +98294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10719/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10719/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  72%|▋| 10717/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  72%|▋| 10717/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -98450,8 +98303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10720/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  72%|▋| 10720/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  72%|▋| 10718/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  72%|▋| 10718/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -98459,8 +98312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10721/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  72%|▋| 10721/14932 [15:19<06:01, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10719/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10719/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -98468,8 +98321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10722/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10722/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  72%|▋| 10720/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  72%|▋| 10720/14932 [15:18<06:01, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -98477,8 +98330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10723/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  72%|▋| 10723/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10721/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  72%|▋| 10721/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -98486,8 +98339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10724/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10724/14932 [15:20<06:01, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10722/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  72%|▋| 10722/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -98495,8 +98348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10725/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10725/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  72%|▋| 10723/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10723/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -98504,8 +98357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10726/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  72%|▋| 10726/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=4.8"
+      "Epoch 0:  72%|▋| 10724/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  72%|▋| 10724/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98513,8 +98366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10727/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=4.8\r",
-      "Epoch 0:  72%|▋| 10727/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10725/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10725/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -98522,8 +98375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10728/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10728/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  72%|▋| 10726/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  72%|▋| 10726/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -98531,8 +98384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10729/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  72%|▋| 10729/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10727/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  72%|▋| 10727/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -98540,8 +98393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10730/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10730/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  72%|▋| 10728/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  72%|▋| 10728/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -98549,8 +98402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10731/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  72%|▋| 10731/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  72%|▋| 10729/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  72%|▋| 10729/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -98558,8 +98411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10732/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  72%|▋| 10732/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10730/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  72%|▋| 10730/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -98567,7 +98420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10733/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10731/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10731/14932 [15:19<06:00, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -98575,7 +98429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10733/14932 [15:20<06:00, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  72%|▋| 10732/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  72%|▋| 10732/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -98583,8 +98438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10734/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  72%|▋| 10734/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10733/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10733/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -98592,8 +98447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10735/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10735/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  72%|▋| 10734/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  72%|▋| 10734/14932 [15:19<05:59, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -98601,8 +98456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10736/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  72%|▋| 10736/14932 [15:21<06:00, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  72%|▋| 10735/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  72%|▋| 10735/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -98610,8 +98465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10737/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  72%|▋| 10737/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10736/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  72%|▋| 10736/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -98619,8 +98474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10738/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10738/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10737/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10737/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -98628,8 +98483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10739/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10739/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10738/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  72%|▋| 10738/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -98637,8 +98492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10740/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10740/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  72%|▋| 10739/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10739/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -98646,8 +98501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10741/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  72%|▋| 10741/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  72%|▋| 10740/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10740/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98655,8 +98510,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10742/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  72%|▋| 10742/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10741/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98664,8 +98518,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10743/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10743/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10741/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -98673,8 +98526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10744/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10744/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10742/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  72%|▋| 10742/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98682,8 +98535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10745/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10745/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10743/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10743/14932 [15:20<05:59, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98691,8 +98544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10746/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10746/14932 [15:21<05:59, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  72%|▋| 10744/14932 [15:20<05:58, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10744/14932 [15:20<05:58, 11.67it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -98700,8 +98553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10747/14932 [15:22<05:59, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  72%|▋| 10747/14932 [15:22<05:59, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  72%|▋| 10745/14932 [15:20<05:58, 11.67it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  72%|▋| 10745/14932 [15:20<05:58, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98709,8 +98562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10748/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  72%|▋| 10748/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10746/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10746/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -98718,8 +98571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10749/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10749/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10747/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  72%|▋| 10747/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -98727,8 +98580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10750/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10750/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  72%|▋| 10748/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  72%|▋| 10748/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98736,8 +98589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10751/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  72%|▋| 10751/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10749/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10749/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -98745,8 +98598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10752/14932 [15:22<05:58, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10752/14932 [15:22<05:58, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10750/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  72%|▋| 10750/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -98754,8 +98607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10753/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10753/14932 [15:22<05:58, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10751/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  72%|▋| 10751/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -98763,8 +98616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10754/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10754/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10752/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  72%|▋| 10752/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -98772,8 +98625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10755/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10755/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  72%|▋| 10753/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  72%|▋| 10753/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -98781,8 +98634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10756/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  72%|▋| 10756/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  72%|▋| 10754/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  72%|▋| 10754/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -98790,8 +98643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10757/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  72%|▋| 10757/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  72%|▋| 10755/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10755/14932 [15:21<05:58, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -98799,8 +98652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10758/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  72%|▋| 10758/14932 [15:22<05:58, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  72%|▋| 10756/14932 [15:21<05:57, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  72%|▋| 10756/14932 [15:21<05:57, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -98808,8 +98661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10759/14932 [15:23<05:58, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  72%|▋| 10759/14932 [15:23<05:58, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10757/14932 [15:21<05:57, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10757/14932 [15:21<05:57, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98817,8 +98670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10760/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  72%|▋| 10760/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  72%|▋| 10758/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10758/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -98826,8 +98679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10761/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  72%|▋| 10761/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10759/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  72%|▋| 10759/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -98835,8 +98688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10762/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10762/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  72%|▋| 10760/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  72%|▋| 10760/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -98844,8 +98697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10763/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  72%|▋| 10763/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  72%|▋| 10761/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10761/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -98853,8 +98706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10764/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  72%|▋| 10764/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  72%|▋| 10762/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  72%|▋| 10762/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -98862,8 +98715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10765/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  72%|▋| 10765/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  72%|▋| 10763/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  72%|▋| 10763/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -98871,8 +98724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10766/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  72%|▋| 10766/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10764/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10764/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -98880,8 +98733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10767/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  72%|▋| 10767/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  72%|▋| 10765/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10765/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -98889,8 +98742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10768/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  72%|▋| 10768/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  72%|▋| 10766/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10766/14932 [15:22<05:57, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -98898,8 +98751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10769/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  72%|▋| 10769/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10767/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  72%|▋| 10767/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -98907,8 +98760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10770/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10770/14932 [15:23<05:57, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10768/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  72%|▋| 10768/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -98916,8 +98769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10771/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10771/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10769/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10769/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -98925,8 +98778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10772/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10772/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  72%|▋| 10770/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10770/14932 [15:22<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -98934,8 +98787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10773/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  72%|▋| 10773/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  72%|▋| 10771/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10771/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -98943,8 +98796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10774/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  72%|▋| 10774/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  72%|▋| 10772/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10772/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -98952,8 +98805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10775/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  72%|▋| 10775/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10773/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10773/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -98961,8 +98814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10776/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10776/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  72%|▋| 10774/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10774/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -98970,8 +98823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10777/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  72%|▋| 10777/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10775/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  72%|▋| 10775/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -98979,8 +98832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10778/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10778/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  72%|▋| 10776/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10776/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -98988,8 +98841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10779/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  72%|▋| 10779/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  72%|▋| 10777/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10777/14932 [15:23<05:56, 11.67it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -98997,8 +98850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10780/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  72%|▋| 10780/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10778/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  72%|▋| 10778/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99006,8 +98859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10781/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  72%|▋| 10781/14932 [15:24<05:56, 11.66it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  72%|▋| 10779/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10779/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -99015,8 +98868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10782/14932 [15:24<05:55, 11.66it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  72%|▋| 10782/14932 [15:24<05:55, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10780/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  72%|▋| 10780/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99024,8 +98877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10783/14932 [15:24<05:55, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10783/14932 [15:24<05:55, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10781/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  72%|▋| 10781/14932 [15:23<05:55, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99033,8 +98886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10784/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10784/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  72%|▋| 10782/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10782/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -99042,8 +98895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10785/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  72%|▋| 10785/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  72%|▋| 10783/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10783/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -99051,8 +98904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10786/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  72%|▋| 10786/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10784/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  72%|▋| 10784/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -99060,8 +98913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10787/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10787/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10785/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10785/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99069,8 +98922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10788/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10788/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10786/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10786/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -99078,8 +98931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10789/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10789/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10787/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  72%|▋| 10787/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -99087,8 +98940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10790/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10790/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  72%|▋| 10788/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  72%|▋| 10788/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -99096,8 +98949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10791/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  72%|▋| 10791/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  72%|▋| 10789/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  72%|▋| 10789/14932 [15:24<05:55, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -99105,8 +98958,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10792/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  72%|▋| 10792/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  72%|▋| 10790/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -99114,8 +98966,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10793/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  72%|▋| 10793/14932 [15:25<05:55, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  72%|▋| 10790/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -99123,8 +98974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10794/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  72%|▋| 10794/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  72%|▋| 10791/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  72%|▋| 10791/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -99132,8 +98983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10795/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  72%|▋| 10795/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  72%|▋| 10792/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10792/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99141,8 +98992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10796/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  72%|▋| 10796/14932 [15:25<05:54, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10793/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10793/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -99150,8 +99001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10797/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10797/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  72%|▋| 10794/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10794/14932 [15:24<05:54, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -99159,8 +99010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10798/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  72%|▋| 10798/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  72%|▋| 10795/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  72%|▋| 10795/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -99168,8 +99019,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10799/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  72%|▋| 10799/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  72%|▋| 10796/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -99177,8 +99027,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10800/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  72%|▋| 10800/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  72%|▋| 10796/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99186,8 +99035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10801/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  72%|▋| 10801/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  72%|▋| 10797/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  72%|▋| 10797/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -99195,8 +99044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10802/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  72%|▋| 10802/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10798/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10798/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99204,8 +99053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10803/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10803/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  72%|▋| 10799/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10799/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -99213,8 +99062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10804/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  72%|▋| 10804/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  72%|▋| 10800/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  72%|▋| 10800/14932 [15:25<05:54, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -99222,8 +99071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10805/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  72%|▋| 10805/14932 [15:26<05:54, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|���| 10801/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  72%|▋| 10801/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -99231,8 +99080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10806/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10806/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10802/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10802/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -99240,8 +99089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10807/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10807/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  72%|▋| 10803/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  72%|▋| 10803/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99249,8 +99098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10808/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  72%|▋| 10808/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  72%|▋| 10804/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10804/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99258,8 +99107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10809/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  72%|▋| 10809/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  72%|▋| 10805/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  72%|▋| 10805/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -99267,8 +99116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10810/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  72%|▋| 10810/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10806/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10806/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -99276,8 +99125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10811/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10811/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  72%|▋| 10807/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  72%|▋| 10807/14932 [15:25<05:53, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99285,8 +99134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10812/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  72%|▋| 10812/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  72%|▋| 10808/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  72%|▋| 10808/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -99294,8 +99143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10813/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  72%|▋| 10813/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  72%|▋| 10809/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  72%|▋| 10809/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -99303,8 +99152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10814/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  72%|▋| 10814/14932 [15:27<05:53, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  72%|▋| 10810/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  72%|▋| 10810/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -99312,8 +99161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10815/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  72%|▋| 10815/14932 [15:27<05:53, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  72%|▋| 10811/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  72%|▋| 10811/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99321,8 +99170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10816/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  72%|▋| 10816/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  72%|▋| 10812/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10812/14932 [15:26<05:53, 11.67it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -99330,8 +99179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10817/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  72%|▋| 10817/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10813/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  72%|▋| 10813/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -99339,8 +99188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10818/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10818/14932 [15:28<05:53, 11.65it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  72%|▋| 10814/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  72%|▋| 10814/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -99348,8 +99197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10819/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  72%|▋| 10819/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10815/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  72%|▋| 10815/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99357,8 +99206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10820/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10820/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  72%|▋| 10816/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  72%|▋| 10816/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99366,8 +99215,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10821/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  72%|▋| 10821/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  72%|▋| 10817/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99375,8 +99223,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10822/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  72%|▋| 10822/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  72%|▋| 10817/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -99384,8 +99231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10823/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  72%|▋| 10823/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  72%|▋| 10818/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  72%|▋| 10818/14932 [15:26<05:52, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -99393,8 +99240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10824/14932 [15:28<05:52, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  72%|▋| 10824/14932 [15:28<05:52, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  72%|▋| 10819/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  72%|▋| 10819/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -99402,8 +99249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  72%|▋| 10825/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  72%|▋| 10825/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  72%|▋| 10820/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  72%|▋| 10820/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99411,8 +99258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10826/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10826/14932 [15:28<05:52, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  72%|▋| 10821/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10821/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -99420,8 +99267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10827/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10827/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  72%|▋| 10822/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  72%|▋| 10822/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99429,8 +99276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10828/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10828/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  72%|▋| 10823/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  72%|▋| 10823/14932 [15:27<05:52, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99438,8 +99285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10829/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  73%|▋| 10829/14932 [15:29<05:52, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  72%|▋| 10824/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  72%|▋| 10824/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99447,8 +99294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10830/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  73%|▋| 10830/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  72%|▋| 10825/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  72%|▋| 10825/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99456,8 +99303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10831/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  73%|▋| 10831/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10826/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10826/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99465,8 +99312,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10832/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10832/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  73%|▋| 10827/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99474,8 +99320,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10833/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  73%|▋| 10833/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10827/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99483,8 +99328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10834/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10834/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10828/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10828/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -99492,8 +99337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10835/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10835/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10829/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  73%|▋| 10829/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99501,8 +99346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10836/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10836/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10830/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10830/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -99510,8 +99355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10837/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10837/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10831/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  73%|▋| 10831/14932 [15:27<05:51, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99519,8 +99364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10838/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  73%|▋| 10838/14932 [15:29<05:51, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10832/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10832/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -99528,8 +99373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10839/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10839/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10833/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  73%|▋| 10833/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -99537,8 +99382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10840/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10840/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  73%|▋| 10834/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  73%|▋| 10834/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -99546,8 +99391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10841/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  73%|▋| 10841/14932 [15:30<05:51, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10835/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10835/14932 [15:28<05:51, 11.67it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -99555,8 +99400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10842/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10842/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10836/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10836/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -99564,8 +99409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10843/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10843/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10837/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10837/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -99573,8 +99418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10844/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10844/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10838/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  73%|▋| 10838/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99582,8 +99427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10845/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10845/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10839/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10839/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99591,8 +99436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10846/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10846/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10840/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10840/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -99600,8 +99445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10847/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10847/14932 [15:30<05:50, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10841/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10841/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -99609,8 +99454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10848/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10848/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10842/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  73%|▋| 10842/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -99618,8 +99463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10849/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10849/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10843/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  73%|▋| 10843/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -99627,8 +99472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10850/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10850/14932 [15:30<05:50, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  73%|▋| 10844/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  73%|▋| 10844/14932 [15:28<05:50, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99636,8 +99481,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10851/14932 [15:31<05:50, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  73%|▋| 10851/14932 [15:31<05:50, 11.65it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  73%|▋| 10845/14932 [15:29<05:50, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99645,8 +99489,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10852/14932 [15:31<05:50, 11.65it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  73%|▋| 10852/14932 [15:31<05:50, 11.65it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  73%|▋| 10845/14932 [15:29<05:50, 11.67it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -99654,8 +99497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10853/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  73%|▋| 10853/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  73%|▋| 10846/14932 [15:29<05:50, 11.67it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  73%|▋| 10846/14932 [15:29<05:50, 11.67it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -99663,8 +99506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10854/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  73%|▋| 10854/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  73%|▋| 10847/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  73%|▋| 10847/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -99672,8 +99515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10855/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  73%|▋| 10855/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10848/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  73%|▋| 10848/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -99681,8 +99524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10856/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10856/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  73%|▋| 10849/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10849/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -99690,8 +99533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10857/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  73%|▋| 10857/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  73%|▋| 10850/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10850/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99699,8 +99542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10858/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  73%|▋| 10858/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  73%|▋| 10851/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  73%|▋| 10851/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99708,8 +99551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10859/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  73%|▋| 10859/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10852/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10852/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99717,8 +99560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10860/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10860/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10853/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10853/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -99726,8 +99569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10861/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10861/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  73%|▋| 10854/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  73%|▋| 10854/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -99735,8 +99578,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10862/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  73%|▋| 10862/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  73%|▋| 10855/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -99744,8 +99586,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10863/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  73%|▋| 10863/14932 [15:31<05:49, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10855/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -99753,7 +99594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10864/14932 [15:32<05:49, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10856/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  73%|▋| 10856/14932 [15:29<05:49, 11.67it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -99761,7 +99603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10864/14932 [15:32<05:49, 11.66it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  73%|▋| 10857/14932 [15:30<05:49, 11.67it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10857/14932 [15:30<05:49, 11.67it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -99769,8 +99612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10865/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  73%|▋| 10865/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10858/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  73%|▋| 10858/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -99778,8 +99621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10866/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10866/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10859/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10859/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -99787,8 +99630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10867/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10867/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10860/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10860/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99796,8 +99639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10868/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10868/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10861/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10861/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -99805,8 +99648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10869/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10869/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  73%|▋| 10862/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10862/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -99814,8 +99657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10870/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  73%|▋| 10870/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10863/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  73%|▋| 10863/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -99823,8 +99666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10871/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10871/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10864/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  73%|▋| 10864/14932 [15:30<05:48, 11.67it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -99832,8 +99675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10872/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10872/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  73%|▋| 10865/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  73%|▋| 10865/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -99841,8 +99684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10873/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  73%|▋| 10873/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10866/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  73%|▋| 10866/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -99850,8 +99693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10874/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10874/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  73%|▋| 10867/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10867/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99859,8 +99702,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10875/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  73%|▋| 10875/14932 [15:32<05:48, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10868/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -99868,8 +99710,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10876/14932 [15:32<05:47, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10876/14932 [15:32<05:47, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10868/14932 [15:30<05:48, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99877,8 +99718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10877/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10877/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10869/14932 [15:30<05:47, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10869/14932 [15:30<05:47, 11.68it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -99886,8 +99727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10878/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10878/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10870/14932 [15:30<05:47, 11.68it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10870/14932 [15:30<05:47, 11.68it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -99895,8 +99736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10879/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10879/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10871/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10871/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -99904,8 +99745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10880/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10880/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10872/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  73%|▋| 10872/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99913,8 +99754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10881/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10881/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10873/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10873/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -99922,8 +99763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10882/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  73%|▋| 10882/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  73%|▋| 10874/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  73%|▋| 10874/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -99931,8 +99772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10883/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  73%|▋| 10883/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  73%|▋| 10875/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10875/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -99940,8 +99781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10884/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  73%|▋| 10884/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  73%|▋| 10876/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  73%|▋| 10876/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -99949,8 +99790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10885/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  73%|▋| 10885/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  73%|▋| 10877/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  73%|▋| 10877/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -99958,8 +99799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10886/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  73%|▋| 10886/14932 [15:33<05:47, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10878/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  73%|▋| 10878/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -99967,8 +99808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10887/14932 [15:33<05:46, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10887/14932 [15:33<05:46, 11.66it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  73%|▋| 10879/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  73%|▋| 10879/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -99976,8 +99817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10888/14932 [15:33<05:46, 11.66it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  73%|▋| 10888/14932 [15:33<05:46, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10880/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10880/14932 [15:31<05:47, 11.68it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -99985,8 +99826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10889/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10889/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  73%|▋| 10881/14932 [15:31<05:46, 11.68it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10881/14932 [15:31<05:46, 11.68it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -99994,8 +99835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10890/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  73%|▋| 10890/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10882/14932 [15:31<05:46, 11.68it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  73%|▋| 10882/14932 [15:31<05:46, 11.68it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -100003,8 +99844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10891/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10891/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  73%|▋| 10883/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  73%|▋| 10883/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -100012,8 +99853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10892/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  73%|▋| 10892/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10884/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10884/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -100021,8 +99862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10893/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  73%|▋| 10893/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  73%|▋| 10885/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10885/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -100030,8 +99871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10894/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  73%|▋| 10894/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10886/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10886/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100039,8 +99880,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10895/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10895/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10887/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100048,8 +99888,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10896/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10896/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  73%|▋| 10887/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -100057,8 +99896,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10897/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  73%|▋| 10897/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  73%|▋| 10888/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  73%|▋| 10888/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -100066,8 +99905,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10898/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  73%|▋| 10898/14932 [15:34<05:46, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10889/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10889/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -100075,8 +99914,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10899/14932 [15:34<05:45, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10899/14932 [15:34<05:45, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10890/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10890/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -100084,8 +99923,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10900/14932 [15:34<05:45, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10900/14932 [15:34<05:45, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10891/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  73%|▋| 10891/14932 [15:32<05:46, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -100093,8 +99932,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10901/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10901/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10892/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10892/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -100102,8 +99941,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10902/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10902/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10893/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10893/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -100111,8 +99950,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10903/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10903/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  73%|▋| 10894/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10894/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -100120,8 +99959,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10904/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  73%|▋| 10904/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10895/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  73%|▋| 10895/14932 [15:32<05:45, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -100129,8 +99968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10905/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10905/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  73%|▋| 10896/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10896/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -100138,8 +99977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10906/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  73%|▋| 10906/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10897/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10897/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -100147,8 +99986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10907/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10907/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10898/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  73%|▋| 10898/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -100156,8 +99995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10908/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10908/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10899/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  73%|▋| 10899/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -100165,8 +100004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10909/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10909/14932 [15:35<05:45, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10900/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  73%|▋| 10900/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -100174,8 +100013,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10910/14932 [15:35<05:44, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10910/14932 [15:35<05:44, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10901/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  73%|▋| 10901/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -100183,8 +100022,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10911/14932 [15:35<05:44, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10911/14932 [15:35<05:44, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10902/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  73%|▋| 10902/14932 [15:33<05:45, 11.68it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -100192,8 +100031,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10912/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10912/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  73%|▋| 10903/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  73%|▋| 10903/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -100201,8 +100040,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10913/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  73%|▋| 10913/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  73%|▋| 10904/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  73%|▋| 10904/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100210,8 +100049,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10914/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  73%|▋| 10914/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  73%|▋| 10905/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10905/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100219,8 +100058,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10915/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  73%|▋| 10915/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10906/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10906/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -100228,8 +100067,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10916/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10916/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  73%|▋| 10907/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  73%|▋| 10907/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -100237,8 +100076,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10917/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  73%|▋| 10917/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  73%|▋| 10908/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10908/14932 [15:33<05:44, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100246,8 +100085,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10918/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  73%|▋| 10918/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  73%|▋| 10909/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10909/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -100255,8 +100094,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10919/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  73%|▋| 10919/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10910/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10910/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -100264,8 +100103,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10920/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10920/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10911/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  73%|▋| 10911/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -100273,8 +100112,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10921/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10921/14932 [15:36<05:44, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10912/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  73%|▋| 10912/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -100282,8 +100121,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10922/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10922/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10913/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10913/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -100291,8 +100130,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10923/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10923/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10914/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10914/14932 [15:34<05:44, 11.68it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -100300,8 +100139,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10924/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10924/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10915/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10915/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -100309,8 +100148,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10925/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10925/14932 [15:36<05:43, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10916/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  73%|▋| 10916/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100318,8 +100157,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10926/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10926/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10917/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10917/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -100327,8 +100166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10927/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10927/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10918/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10918/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100336,8 +100175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10928/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10928/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10919/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10919/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -100345,8 +100184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10929/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10929/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  73%|▋| 10920/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10920/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100354,8 +100193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10930/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  73%|▋| 10930/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  73%|▋| 10921/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10921/14932 [15:34<05:43, 11.68it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -100363,8 +100202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10931/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  73%|▋| 10931/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10922/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  73%|▋| 10922/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100372,8 +100211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10932/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10932/14932 [15:37<05:43, 11.66it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  73%|▋| 10923/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10923/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100381,8 +100220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10933/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  73%|▋| 10933/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  73%|▋| 10924/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  73%|▋| 10924/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -100390,8 +100229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10934/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  73%|▋| 10934/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10925/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  73%|▋| 10925/14932 [15:35<05:43, 11.68it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -100399,8 +100238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10935/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10935/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10926/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  73%|▋| 10926/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100408,7 +100247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10936/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10927/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10927/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -100416,7 +100256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10936/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  73%|▋| 10928/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10928/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -100424,8 +100265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10937/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  73%|▋| 10937/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10929/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  73%|▋| 10929/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -100433,8 +100274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10938/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  73%|▋| 10938/14932 [15:37<05:42, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10930/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  73%|▋| 10930/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -100442,8 +100283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10939/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10939/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  73%|▋| 10931/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  73%|▋| 10931/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -100451,8 +100292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10940/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  73%|▋| 10940/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10932/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10932/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -100460,8 +100301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10941/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  73%|▋| 10941/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10933/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  73%|▋| 10933/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -100469,8 +100310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10942/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10942/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10934/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  73%|▋| 10934/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -100478,8 +100319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10943/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10943/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10935/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  73%|▋| 10935/14932 [15:35<05:42, 11.68it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100487,8 +100328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10944/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10944/14932 [15:38<05:42, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  73%|▋| 10936/14932 [15:36<05:42, 11.68it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10936/14932 [15:36<05:42, 11.68it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -100496,8 +100337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10945/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  73%|▋| 10945/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10937/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  73%|▋| 10937/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100505,8 +100346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10946/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10946/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10938/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10938/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -100514,8 +100355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10947/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10947/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  73%|▋| 10939/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10939/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -100523,8 +100364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10948/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  73%|▋| 10948/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  73%|▋| 10940/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  73%|▋| 10940/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100532,8 +100373,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10949/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  73%|▋| 10949/14932 [15:38<05:41, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10941/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100541,8 +100381,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10950/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10950/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10941/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -100550,8 +100389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10951/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10951/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10942/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10942/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -100559,8 +100398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10952/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  73%|▋| 10952/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10943/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10943/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -100568,8 +100407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10953/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10953/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  73%|▋| 10944/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  73%|▋| 10944/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100577,8 +100416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10954/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  73%|▋| 10954/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  73%|▋| 10945/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10945/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -100586,8 +100425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10955/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  73%|▋| 10955/14932 [15:39<05:41, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  73%|▋| 10946/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  73%|▋| 10946/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -100595,8 +100434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10956/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  73%|▋| 10956/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10947/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  73%|▋| 10947/14932 [15:36<05:41, 11.68it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100604,8 +100443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10957/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10957/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10948/14932 [15:36<05:40, 11.68it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10948/14932 [15:36<05:40, 11.68it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -100613,8 +100452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10958/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  73%|▋| 10958/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10949/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10949/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -100622,8 +100461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10959/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  73%|▋| 10959/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10950/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  73%|▋| 10950/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -100631,8 +100470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10960/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  73%|▋| 10960/14932 [15:39<05:40, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  73%|▋| 10951/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  73%|▋| 10951/14932 [15:37<05:40, 11.68it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -100640,8 +100479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10961/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  73%|▋| 10961/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10952/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  73%|▋| 10952/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -100649,8 +100488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10962/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10962/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  73%|▋| 10953/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  73%|▋| 10953/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100658,8 +100497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10963/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  73%|▋| 10963/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  73%|▋| 10954/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10954/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -100667,8 +100506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10964/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  73%|▋| 10964/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  73%|▋| 10955/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  73%|▋| 10955/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -100676,8 +100515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10965/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  73%|▋| 10965/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  73%|▋| 10956/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  73%|▋| 10956/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100685,8 +100524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10966/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  73%|▋| 10966/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  73%|▋| 10957/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10957/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -100694,8 +100533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10967/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  73%|▋| 10967/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  73%|▋| 10958/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  73%|▋| 10958/14932 [15:37<05:40, 11.69it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -100703,8 +100542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10968/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  73%|▋| 10968/14932 [15:40<05:40, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10959/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  73%|▋| 10959/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -100712,7 +100551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10969/14932 [15:40<05:39, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10960/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  73%|▋| 10960/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -100720,7 +100560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10969/14932 [15:40<05:39, 11.66it/s, v_num=o30c, train/loss=4.8"
+      "Epoch 0:  73%|▋| 10961/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  73%|▋| 10961/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100728,8 +100569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10970/14932 [15:40<05:39, 11.66it/s, v_num=o30c, train/loss=4.8\r",
-      "Epoch 0:  73%|▋| 10970/14932 [15:40<05:39, 11.66it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  73%|▋| 10962/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  73%|▋| 10962/14932 [15:37<05:39, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100737,8 +100578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10971/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  73%|▋| 10971/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  73%|▋| 10963/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10963/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100746,8 +100587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10972/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  73%|▋| 10972/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  73%|▋| 10964/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  73%|▋| 10964/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -100755,8 +100596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10973/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  73%|▋| 10973/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  73%|▋| 10965/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  73%|▋| 10965/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100764,8 +100605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10974/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  73%|▋| 10974/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  73%|▋| 10966/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10966/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -100773,8 +100614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  73%|▋| 10975/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  73%|▋| 10975/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10967/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  73%|▋| 10967/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100782,8 +100623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10976/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 10976/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  73%|▋| 10968/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10968/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -100791,8 +100632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10977/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 10977/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  73%|▋| 10969/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  73%|▋| 10969/14932 [15:38<05:39, 11.69it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -100800,8 +100641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10978/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 10978/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  73%|▋| 10970/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  73%|▋| 10970/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100809,8 +100650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10979/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 10979/14932 [15:41<05:39, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  73%|▋| 10971/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  73%|▋| 10971/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -100818,8 +100659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10980/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 10980/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10972/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  73%|▋| 10972/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -100827,8 +100668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10981/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 10981/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  73%|▋| 10973/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  73%|▋| 10973/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -100836,8 +100677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10982/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 10982/14932 [15:41<05:38, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  73%|▋| 10974/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  73%|▋| 10974/14932 [15:38<05:38, 11.69it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -100845,8 +100686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10983/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  74%|▋| 10983/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  73%|▋| 10975/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  73%|▋| 10975/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -100854,8 +100695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10984/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  74%|▋| 10984/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 10976/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  74%|▋| 10976/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -100863,8 +100704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10985/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 10985/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  74%|▋| 10977/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 10977/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -100872,8 +100713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10986/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  74%|▋| 10986/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  74%|▋| 10978/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  74%|▋| 10978/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -100881,8 +100722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10987/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 10987/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 10979/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  74%|▋| 10979/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -100890,8 +100731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10988/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 10988/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  74%|▋| 10980/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 10980/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -100899,8 +100740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10989/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  74%|▋| 10989/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 10981/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  74%|▋| 10981/14932 [15:39<05:38, 11.69it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -100908,8 +100749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10990/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 10990/14932 [15:42<05:38, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 10982/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 10982/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -100917,8 +100758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10991/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 10991/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  74%|▋| 10983/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  74%|▋| 10983/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -100926,8 +100767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10992/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  74%|▋| 10992/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  74%|▋| 10984/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  74%|▋| 10984/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100935,8 +100776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10993/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  74%|▋| 10993/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 10985/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 10985/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -100944,8 +100785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10994/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 10994/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  74%|▋| 10986/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  74%|▋| 10986/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100953,8 +100794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10995/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  74%|▋| 10995/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 10987/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 10987/14932 [15:39<05:37, 11.69it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -100962,8 +100803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10996/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 10996/14932 [15:42<05:37, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 10988/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  74%|▋| 10988/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -100971,8 +100812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10997/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 10997/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 10989/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 10989/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -100980,8 +100821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10998/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 10998/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 10990/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 10990/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -100989,8 +100830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 10999/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 10999/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 10991/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  74%|▋| 10991/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -100998,8 +100839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11000/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 11000/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 10992/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  74%|▋| 10992/14932 [15:40<05:37, 11.69it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -101007,8 +100848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11001/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11001/14932 [15:43<05:37, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 10993/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  74%|▋| 10993/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -101016,8 +100857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11002/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11002/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 10994/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 10994/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101025,8 +100866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11003/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11003/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=4.8"
+      "Epoch 0:  74%|▋| 10995/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 10995/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -101034,8 +100875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11004/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=4.8\r",
-      "Epoch 0:  74%|▋| 11004/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  74%|▋| 10996/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  74%|▋| 10996/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101043,8 +100884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11005/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 11005/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  74%|▋| 10997/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 10997/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101052,8 +100893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11006/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  74%|▋| 11006/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  74%|▋| 10998/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 10998/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=4.7"
      ]
     },
     {
@@ -101061,8 +100902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11007/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  74%|▋| 11007/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  74%|▋| 10999/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=4.7\r",
+      "Epoch 0:  74%|▋| 10999/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -101070,8 +100911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11008/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  74%|▋| 11008/14932 [15:43<05:36, 11.66it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  74%|▋| 11000/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  74%|▋| 11000/14932 [15:40<05:36, 11.69it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -101079,8 +100920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11009/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  74%|▋| 11009/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  74%|▋| 11001/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  74%|▋| 11001/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -101088,8 +100929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11010/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  74%|▋| 11010/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11002/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  74%|▋| 11002/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -101097,8 +100938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11011/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11011/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11003/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  74%|▋| 11003/14932 [15:41<05:36, 11.69it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -101106,8 +100947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11012/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 11012/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  74%|▋| 11004/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  74%|▋| 11004/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -101115,8 +100956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11013/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 11013/14932 [15:44<05:36, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  74%|▋| 11005/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  74%|▋| 11005/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101124,8 +100965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11014/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  74%|▋| 11014/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11006/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11006/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101133,7 +100974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11015/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11007/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11007/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -101141,7 +100983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11015/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  74%|▋| 11008/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 11008/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -101149,8 +100992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11016/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 11016/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  74%|▋| 11009/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  74%|▋| 11009/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -101158,8 +101001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11017/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  74%|▋| 11017/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  74%|▋| 11010/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  74%|▋| 11010/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101167,8 +101010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11018/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 11018/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  74%|▋| 11011/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11011/14932 [15:41<05:35, 11.69it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -101176,8 +101019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11019/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 11019/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  74%|▋| 11012/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  74%|▋| 11012/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -101185,8 +101028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11020/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  74%|▋| 11020/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  74%|▋| 11013/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  74%|▋| 11013/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -101194,8 +101037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11021/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  74%|▋| 11021/14932 [15:44<05:35, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11014/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  74%|▋| 11014/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -101203,7 +101046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11022/14932 [15:45<05:35, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11015/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  74%|▋| 11015/14932 [15:42<05:35, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101211,7 +101055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11022/14932 [15:45<05:35, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  74%|▋| 11016/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11016/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -101219,8 +101064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11023/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  74%|▋| 11023/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11017/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  74%|▋| 11017/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -101228,8 +101073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11024/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11024/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11018/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  74%|▋| 11018/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -101237,8 +101082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11025/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 11025/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11019/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  74%|▋| 11019/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -101246,8 +101091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11026/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11026/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  74%|▋| 11020/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  74%|▋| 11020/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -101255,8 +101100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11027/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  74%|▋| 11027/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  74%|▋| 11021/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  74%|▋| 11021/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -101264,8 +101109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11028/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  74%|▋| 11028/14932 [15:46<05:35, 11.65it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  74%|▋| 11022/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  74%|▋| 11022/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -101273,8 +101118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11029/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  74%|▋| 11029/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11023/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  74%|▋| 11023/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101282,8 +101127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11030/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11030/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11024/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11024/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -101291,8 +101136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11031/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11031/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  74%|▋| 11025/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  74%|▋| 11025/14932 [15:42<05:34, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -101300,8 +101145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11032/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 11032/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 11026/14932 [15:43<05:34, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  74%|▋| 11026/14932 [15:43<05:34, 11.69it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -101309,8 +101154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11033/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 11033/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  74%|▋| 11027/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  74%|▋| 11027/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101318,8 +101163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11034/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  74%|▋| 11034/14932 [15:46<05:34, 11.65it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 11028/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11028/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -101327,8 +101172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11035/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 11035/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  74%|▋| 11029/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  74%|▋| 11029/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -101336,8 +101181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11036/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  74%|▋| 11036/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  74%|▋| 11030/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  74%|▋| 11030/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -101345,8 +101190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11037/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  74%|▋| 11037/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11031/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  74%|▋| 11031/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101354,8 +101199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11038/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11038/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  74%|▋| 11032/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11032/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101363,8 +101208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11039/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 11039/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11033/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11033/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -101372,8 +101217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11040/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11040/14932 [15:47<05:34, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  74%|▋| 11034/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  74%|▋| 11034/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -101381,8 +101226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11041/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  74%|▋| 11041/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  74%|▋| 11035/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  74%|▋| 11035/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -101390,8 +101235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11042/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 11042/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  74%|▋| 11036/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  74%|▋| 11036/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -101399,8 +101244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11043/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  74%|▋| 11043/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  74%|▋| 11037/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  74%|▋| 11037/14932 [15:43<05:33, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101408,8 +101253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11044/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  74%|▋| 11044/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  74%|▋| 11038/14932 [15:43<05:32, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11038/14932 [15:43<05:32, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -101417,8 +101262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11045/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 11045/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11039/14932 [15:43<05:32, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  74%|▋| 11039/14932 [15:43<05:32, 11.69it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -101426,8 +101271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11046/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 11046/14932 [15:47<05:33, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  74%|▋| 11040/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  74%|▋| 11040/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -101435,8 +101280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11047/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  74%|▋| 11047/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  74%|▋| 11041/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  74%|▋| 11041/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -101444,8 +101289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11048/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  74%|▋| 11048/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  74%|▋| 11042/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  74%|▋| 11042/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -101453,8 +101298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11049/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  74%|▋| 11049/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  74%|▋| 11043/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 11043/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -101462,8 +101307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11050/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  74%|▋| 11050/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11044/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  74%|▋| 11044/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -101471,8 +101316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11051/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11051/14932 [15:48<05:33, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11045/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  74%|▋| 11045/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101480,8 +101325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11052/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11052/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  74%|▋| 11046/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11046/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101489,8 +101334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11053/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  74%|▋| 11053/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11047/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11047/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -101498,8 +101343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11054/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11054/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  74%|▋| 11048/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  74%|▋| 11048/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -101507,8 +101352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11055/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  74%|▋| 11055/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11049/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  74%|▋| 11049/14932 [15:44<05:32, 11.69it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101516,8 +101361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11056/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11056/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11050/14932 [15:45<05:32, 11.69it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11050/14932 [15:45<05:32, 11.69it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -101525,8 +101370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11057/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11057/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11051/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  74%|▋| 11051/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101534,8 +101379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11058/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11058/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  74%|▋| 11052/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11052/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -101543,8 +101388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11059/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  74%|▋| 11059/14932 [15:48<05:32, 11.65it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  74%|▋| 11053/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  74%|▋| 11053/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101552,8 +101397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11060/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  74%|▋| 11060/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11054/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 11054/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101561,8 +101406,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11061/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11061/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  74%|▋| 11055/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101570,8 +101414,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11062/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  74%|▋| 11062/14932 [15:49<05:32, 11.65it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11055/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -101579,8 +101422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11063/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11063/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  74%|▋| 11056/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  74%|▋| 11056/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -101588,8 +101431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11064/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  74%|▋| 11064/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  74%|▋| 11057/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 11057/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -101597,8 +101440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11065/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  74%|▋| 11065/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  74%|▋| 11058/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  74%|▋| 11058/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -101606,8 +101449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11066/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  74%|▋| 11066/14932 [15:49<05:31, 11.65it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11059/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  74%|▋| 11059/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -101615,8 +101458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11067/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 11067/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  74%|▋| 11060/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  74%|▋| 11060/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101624,8 +101467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11068/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  74%|▋| 11068/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  74%|▋| 11061/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11061/14932 [15:45<05:31, 11.69it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -101633,8 +101476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11069/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  74%|▋| 11069/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 11062/14932 [15:45<05:30, 11.69it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  74%|▋| 11062/14932 [15:45<05:30, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101642,8 +101485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11070/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 11070/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  74%|▋| 11063/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11063/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -101651,8 +101494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11071/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  74%|▋| 11071/14932 [15:49<05:31, 11.66it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  74%|▋| 11064/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  74%|▋| 11064/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101660,8 +101503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11072/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  74%|▋| 11072/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11065/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11065/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -101669,8 +101512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11073/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11073/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  74%|▋| 11066/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  74%|▋| 11066/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -101678,8 +101521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11074/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  74%|▋| 11074/14932 [15:50<05:31, 11.65it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11067/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  74%|▋| 11067/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -101687,8 +101530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11075/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11075/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  74%|▋| 11068/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  74%|▋| 11068/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -101696,8 +101539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11076/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  74%|▋| 11076/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  74%|▋| 11069/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  74%|▋| 11069/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -101705,8 +101548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11077/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  74%|▋| 11077/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  74%|▋| 11070/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  74%|▋| 11070/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -101714,8 +101557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11078/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  74%|▋| 11078/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  74%|▋| 11071/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  74%|▋| 11071/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101723,8 +101566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11079/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 11079/14932 [15:50<05:30, 11.65it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11072/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11072/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101732,8 +101575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11080/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11080/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  74%|▋| 11073/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11073/14932 [15:46<05:30, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -101741,8 +101584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11081/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  74%|▋| 11081/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11074/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 11074/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -101750,8 +101593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11082/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11082/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  74%|▋| 11075/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 11075/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -101759,8 +101602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11083/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  74%|▋| 11083/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  74%|▋| 11076/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  74%|▋| 11076/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -101768,7 +101611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11084/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  74%|▋| 11077/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  74%|▋| 11077/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101776,7 +101620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11084/14932 [15:50<05:30, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11078/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11078/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -101784,8 +101629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11085/14932 [15:51<05:30, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11085/14932 [15:51<05:30, 11.66it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  74%|▋| 11079/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  74%|▋| 11079/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101793,8 +101638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11086/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  74%|▋| 11086/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  74%|▋| 11080/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11080/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101802,8 +101647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11087/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  74%|▋| 11087/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  74%|▋| 11081/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11081/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -101811,8 +101656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11088/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  74%|▋| 11088/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11082/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  74%|▋| 11082/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -101820,8 +101665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11089/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11089/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  74%|▋| 11083/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  74%|▋| 11083/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -101829,8 +101674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11090/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  74%|▋| 11090/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  74%|▋| 11084/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  74%|▋| 11084/14932 [15:47<05:29, 11.69it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -101838,8 +101683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11091/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  74%|▋| 11091/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  74%|▋| 11085/14932 [15:47<05:28, 11.69it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  74%|▋| 11085/14932 [15:47<05:28, 11.69it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -101847,8 +101692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11092/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  74%|▋| 11092/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 11086/14932 [15:47<05:28, 11.69it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  74%|▋| 11086/14932 [15:47<05:28, 11.69it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -101856,8 +101701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11093/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 11093/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  74%|▋| 11087/14932 [15:48<05:28, 11.69it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  74%|▋| 11087/14932 [15:48<05:28, 11.69it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101865,8 +101710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11094/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  74%|▋| 11094/14932 [15:51<05:29, 11.65it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11088/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11088/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -101874,8 +101719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11095/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11095/14932 [15:51<05:29, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11089/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  74%|▋| 11089/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101883,8 +101728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11096/14932 [15:52<05:29, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11096/14932 [15:52<05:29, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  74%|▋| 11090/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 11090/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101892,8 +101737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11097/14932 [15:52<05:29, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  74%|▋| 11097/14932 [15:52<05:29, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  74%|▋| 11091/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 11091/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -101901,8 +101746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11098/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  74%|▋| 11098/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  74%|▋| 11092/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  74%|▋| 11092/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -101910,8 +101755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11099/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  74%|▋| 11099/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  74%|▋| 11093/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  74%|▋| 11093/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -101919,8 +101764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11100/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  74%|▋| 11100/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  74%|▋| 11094/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  74%|▋| 11094/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -101928,8 +101773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11101/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  74%|▋| 11101/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11095/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  74%|▋| 11095/14932 [15:48<05:28, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -101937,8 +101782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11102/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11102/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  74%|▋| 11096/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  74%|▋| 11096/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -101946,8 +101791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11103/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  74%|▋| 11103/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 11097/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  74%|▋| 11097/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -101955,8 +101800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11104/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 11104/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11098/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11098/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -101964,8 +101809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11105/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  74%|▋| 11105/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  74%|▋| 11099/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  74%|▋| 11099/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -101973,8 +101818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11106/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  74%|▋| 11106/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  74%|▋| 11100/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  74%|▋| 11100/14932 [15:48<05:27, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -101982,8 +101827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11107/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  74%|▋| 11107/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  74%|▋| 11101/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 11101/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -101991,8 +101836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11108/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  74%|▋| 11108/14932 [15:52<05:28, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  74%|▋| 11102/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11102/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102000,8 +101845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11109/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  74%|▋| 11109/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 11103/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  74%|▋| 11103/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -102009,8 +101854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11110/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  74%|▋| 11110/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  74%|▋| 11104/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  74%|▋| 11104/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -102018,8 +101863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11111/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  74%|▋| 11111/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11105/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  74%|▋| 11105/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102027,8 +101872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11112/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11112/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  74%|▋| 11106/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 11106/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -102036,8 +101881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11113/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  74%|▋| 11113/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  74%|▋| 11107/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  74%|▋| 11107/14932 [15:49<05:27, 11.70it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -102045,8 +101890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11114/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  74%|▋| 11114/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  74%|▋| 11108/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  74%|▋| 11108/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -102054,8 +101899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11115/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  74%|▋| 11115/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11109/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  74%|▋| 11109/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102063,8 +101908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11116/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11116/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  74%|▋| 11110/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  74%|▋| 11110/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -102072,8 +101917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11117/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  74%|▋| 11117/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  74%|▋| 11111/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  74%|▋| 11111/14932 [15:49<05:26, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102081,8 +101926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11118/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  74%|▋| 11118/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  74%|▋| 11112/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  74%|▋| 11112/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -102090,8 +101935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11119/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  74%|▋| 11119/14932 [15:53<05:27, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  74%|▋| 11113/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  74%|▋| 11113/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -102099,8 +101944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11120/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  74%|▋| 11120/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  74%|▋| 11114/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  74%|▋| 11114/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -102108,8 +101953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11121/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  74%|▋| 11121/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  74%|▋| 11115/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  74%|▋| 11115/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -102117,8 +101962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11122/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  74%|▋| 11122/14932 [15:53<05:26, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  74%|▋| 11116/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  74%|▋| 11116/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -102126,8 +101971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11123/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  74%|▋| 11123/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  74%|▋| 11117/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  74%|▋| 11117/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -102135,8 +101980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  74%|▋| 11124/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  74%|▋| 11124/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  74%|▋| 11118/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  74%|▋| 11118/14932 [15:50<05:26, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -102144,8 +101989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11125/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  75%|▋| 11125/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  74%|▋| 11119/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  74%|▋| 11119/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -102153,8 +101998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11126/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11126/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  74%|▋| 11120/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  74%|▋| 11120/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -102162,8 +102007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11127/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  75%|▋| 11127/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  74%|▋| 11121/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  74%|▋| 11121/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -102171,8 +102016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11128/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▋| 11128/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  74%|▋| 11122/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  74%|▋| 11122/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102180,8 +102025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11129/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11129/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  74%|▋| 11123/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  74%|▋| 11123/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -102189,8 +102034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11130/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▋| 11130/14932 [15:54<05:26, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  74%|▋| 11124/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  74%|▋| 11124/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -102198,8 +102043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11131/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▋| 11131/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▋| 11125/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  75%|▋| 11125/14932 [15:50<05:25, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102207,8 +102052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11132/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▋| 11132/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▋| 11126/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▋| 11126/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -102216,8 +102061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11133/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▋| 11133/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11127/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  75%|▋| 11127/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -102225,8 +102070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11134/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11134/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  75%|▋| 11128/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  75%|▋| 11128/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -102234,8 +102079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11135/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  75%|▋| 11135/14932 [15:54<05:25, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▋| 11129/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▋| 11129/14932 [15:51<05:25, 11.70it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -102243,8 +102088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11136/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  75%|▋| 11136/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  75%|▋| 11130/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  75%|▋| 11130/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -102252,8 +102097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11137/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  75%|▋| 11137/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  75%|▋| 11131/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  75%|▋| 11131/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -102261,8 +102106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11138/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  75%|▋| 11138/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  75%|▋| 11132/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  75%|▋| 11132/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -102270,8 +102115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11139/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  75%|▋| 11139/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▋| 11133/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  75%|▋| 11133/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -102279,8 +102124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11140/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  75%|▋| 11140/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▋| 11134/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▋| 11134/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102288,8 +102133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11141/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▋| 11141/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▋| 11135/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▋| 11135/14932 [15:51<05:24, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -102297,8 +102142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11142/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▋| 11142/14932 [15:55<05:25, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  75%|▋| 11136/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▋| 11136/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -102306,8 +102151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11143/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▋| 11143/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  75%|▋| 11137/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  75%|▋| 11137/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102315,8 +102160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11144/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  75%|▋| 11144/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▋| 11138/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▋| 11138/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -102324,8 +102169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11145/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▋| 11145/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▋| 11139/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  75%|▋| 11139/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102333,8 +102178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11146/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▋| 11146/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  75%|▋| 11140/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11140/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -102342,8 +102187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11147/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  75%|▋| 11147/14932 [15:55<05:24, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▋| 11141/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  75%|▋| 11141/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -102351,8 +102196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11148/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▋| 11148/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  75%|▋| 11142/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  75%|▋| 11142/14932 [15:52<05:24, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102360,8 +102205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11149/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  75%|▋| 11149/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▋| 11143/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11143/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -102369,8 +102214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11150/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▋| 11150/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▋| 11144/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▋| 11144/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -102378,8 +102223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11151/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▋| 11151/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  75%|▋| 11145/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▋| 11145/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -102387,8 +102232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11152/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  75%|▋| 11152/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  75%|▋| 11146/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▋| 11146/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -102396,8 +102241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11153/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  75%|▋| 11153/14932 [15:56<05:24, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  75%|▋| 11147/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▋| 11147/14932 [15:52<05:23, 11.70it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -102405,8 +102250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11154/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  75%|▋| 11154/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▋| 11148/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  75%|▋| 11148/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102414,8 +102259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11155/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▋| 11155/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  75%|▋| 11149/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▋| 11149/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -102423,8 +102268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11156/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  75%|▋| 11156/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  75%|▋| 11150/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  75%|▋| 11150/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -102432,8 +102277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11157/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  75%|▋| 11157/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▋| 11151/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▋| 11151/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -102441,8 +102286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11158/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▋| 11158/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▋| 11152/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  75%|▋| 11152/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -102450,8 +102295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11159/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▋| 11159/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  75%|▋| 11153/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  75%|▋| 11153/14932 [15:53<05:23, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102459,8 +102304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11160/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  75%|▋| 11160/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  75%|▋| 11154/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11154/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102468,8 +102313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11161/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  75%|▋| 11161/14932 [15:56<05:23, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11155/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11155/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -102477,8 +102322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11162/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11162/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  75%|▋| 11156/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  75%|▋| 11156/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -102486,8 +102331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11163/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  75%|▋| 11163/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▋| 11157/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  75%|▋| 11157/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -102495,8 +102340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11164/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▋| 11164/14932 [15:57<05:23, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  75%|▋| 11158/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▋| 11158/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102504,8 +102349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11165/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  75%|▋| 11165/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▋| 11159/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▋| 11159/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102513,8 +102358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11166/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▋| 11166/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▋| 11160/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▋| 11160/14932 [15:53<05:22, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -102522,8 +102367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11167/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▋| 11167/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▋| 11161/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▋| 11161/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -102531,8 +102376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11168/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▋| 11168/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  75%|▋| 11162/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  75%|▋| 11162/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102540,8 +102385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11169/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  75%|▋| 11169/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11163/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▋| 11163/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -102549,8 +102394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11170/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11170/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▋| 11164/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  75%|▋| 11164/14932 [15:54<05:22, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -102558,8 +102403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11171/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▋| 11171/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▋| 11165/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  75%|▋| 11165/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -102567,8 +102412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11172/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▋| 11172/14932 [15:57<05:22, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▋| 11166/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▋| 11166/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -102576,8 +102421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11173/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▋| 11173/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▋| 11167/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  75%|▋| 11167/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -102585,8 +102430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11174/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▋| 11174/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  75%|▋| 11168/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  75%|▋| 11168/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -102594,8 +102439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11175/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▋| 11175/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▋| 11169/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▋| 11169/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -102603,8 +102448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11176/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▋| 11176/14932 [15:58<05:22, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11170/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▋| 11170/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102612,8 +102457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11177/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11177/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▋| 11171/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11171/14932 [15:54<05:21, 11.70it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -102621,8 +102466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11178/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▋| 11178/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  75%|▋| 11172/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  75%|▋| 11172/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102630,8 +102475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11179/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  75%|▋| 11179/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▋| 11173/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11173/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102639,8 +102484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11180/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▋| 11180/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11174/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▋| 11174/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102648,8 +102493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11181/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11181/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▋| 11175/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11175/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -102657,8 +102502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11182/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▋| 11182/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  75%|▋| 11176/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  75%|▋| 11176/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -102666,8 +102511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11183/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  75%|▋| 11183/14932 [15:58<05:21, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▋| 11177/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  75%|▋| 11177/14932 [15:55<05:21, 11.70it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -102675,8 +102520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11184/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  75%|▋| 11184/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▋| 11178/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  75%|▋| 11178/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -102684,8 +102529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11185/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▋| 11185/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  75%|▋| 11179/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  75%|▋| 11179/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -102693,8 +102538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11186/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  75%|▋| 11186/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  75%|▋| 11180/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  75%|▋| 11180/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -102702,8 +102547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11187/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  75%|▋| 11187/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▋| 11181/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  75%|▋| 11181/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102711,8 +102556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11188/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▋| 11188/14932 [15:59<05:21, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▋| 11182/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11182/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -102720,8 +102565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11189/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▋| 11189/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▋| 11183/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▋| 11183/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -102729,8 +102574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11190/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▋| 11190/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▋| 11184/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▋| 11184/14932 [15:55<05:20, 11.70it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -102738,8 +102583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11191/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▋| 11191/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  75%|▋| 11185/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  75%|▋| 11185/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102747,8 +102592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11192/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  75%|▋| 11192/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  75%|▋| 11186/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▋| 11186/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102756,8 +102601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11193/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  75%|▋| 11193/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▋| 11187/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▋| 11187/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -102765,8 +102610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11194/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▋| 11194/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  75%|▋| 11188/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  75%|▋| 11188/14932 [15:56<05:20, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102774,8 +102619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11195/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  75%|▋| 11195/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▋| 11189/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11189/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102783,8 +102628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11196/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▋| 11196/14932 [15:59<05:20, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  75%|▋| 11190/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11190/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -102792,8 +102637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11197/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  75%|▋| 11197/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11191/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  75%|▋| 11191/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102801,8 +102646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▋| 11198/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▋| 11198/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  75%|▋| 11192/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▋| 11192/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -102810,8 +102655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11199/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  75%|▊| 11199/14932 [16:00<05:20, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11193/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  75%|▋| 11193/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -102819,7 +102664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11200/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▋| 11194/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  75%|▋| 11194/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -102827,7 +102673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11200/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  75%|▋| 11195/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  75%|▋| 11195/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102835,8 +102682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11201/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  75%|▊| 11201/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  75%|▋| 11196/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▋| 11196/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -102844,7 +102691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11202/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  75%|▋| 11197/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▋| 11197/14932 [15:56<05:19, 11.70it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -102852,7 +102700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11202/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  75%|▋| 11198/14932 [15:57<05:19, 11.70it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  75%|▋| 11198/14932 [15:57<05:19, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -102860,8 +102709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11203/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  75%|▊| 11203/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  75%|▊| 11199/14932 [15:57<05:19, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  75%|▊| 11199/14932 [15:57<05:19, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102869,8 +102718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11204/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  75%|▊| 11204/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  75%|▊| 11200/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11200/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -102878,8 +102727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11205/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  75%|▊| 11205/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  75%|▊| 11201/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  75%|▊| 11201/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -102887,8 +102736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11206/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  75%|▊| 11206/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▊| 11202/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  75%|▊| 11202/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -102896,8 +102745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11207/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▊| 11207/14932 [16:00<05:19, 11.66it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▊| 11203/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  75%|▊| 11203/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -102905,8 +102754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11208/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  75%|▊| 11208/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  75%|▊| 11204/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  75%|▊| 11204/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -102914,8 +102763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11209/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  75%|▊| 11209/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▊| 11205/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  75%|▊| 11205/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -102923,8 +102772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11210/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▊| 11210/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  75%|▊| 11206/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  75%|▊| 11206/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -102932,8 +102781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11211/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  75%|▊| 11211/14932 [16:01<05:19, 11.66it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▊| 11207/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  75%|▊| 11207/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -102941,8 +102790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11212/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▊| 11212/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  75%|▊| 11208/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▊| 11208/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102950,8 +102799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11213/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  75%|▊| 11213/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▊| 11209/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11209/14932 [15:57<05:18, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -102959,8 +102808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11214/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▊| 11214/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▊| 11210/14932 [15:58<05:18, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11210/14932 [15:58<05:18, 11.70it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -102968,8 +102817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11215/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▊| 11215/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▊| 11211/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  75%|▊| 11211/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -102977,8 +102826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11216/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▊| 11216/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▊| 11212/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  75%|▊| 11212/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -102986,8 +102835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11217/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▊| 11217/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  75%|▊| 11213/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  75%|▊| 11213/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -102995,8 +102844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11218/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  75%|▊| 11218/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▊| 11214/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▊| 11214/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -103004,8 +102853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11219/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▊| 11219/14932 [16:01<05:18, 11.66it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  75%|▊| 11215/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  75%|▊| 11215/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103013,8 +102862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11220/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  75%|▊| 11220/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  75%|▊| 11216/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▊| 11216/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -103022,8 +102871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11221/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  75%|▊| 11221/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▊| 11217/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  75%|▊| 11217/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103031,8 +102880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11222/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▊| 11222/14932 [16:02<05:18, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▊| 11218/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▊| 11218/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103040,8 +102889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11223/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▊| 11223/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  75%|▊| 11219/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  75%|▊| 11219/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -103049,8 +102898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11224/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  75%|▊| 11224/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▊| 11220/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  75%|▊| 11220/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -103058,8 +102907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11225/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  75%|▊| 11225/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▊| 11221/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11221/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103067,8 +102916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11226/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▊| 11226/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▊| 11222/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▊| 11222/14932 [15:58<05:17, 11.70it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -103076,8 +102925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11227/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▊| 11227/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  75%|▊| 11223/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  75%|▊| 11223/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -103085,7 +102934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11228/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  75%|▊| 11224/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▊| 11224/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103093,7 +102943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11228/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  75%|▊| 11225/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▊| 11225/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103101,8 +102952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11229/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  75%|▊| 11229/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  75%|▊| 11226/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▊| 11226/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -103110,8 +102961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11230/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  75%|▊| 11230/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  75%|▊| 11227/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  75%|▊| 11227/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103119,8 +102970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11231/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  75%|▊| 11231/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▊| 11228/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  75%|▊| 11228/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103128,8 +102979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11232/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▊| 11232/14932 [16:02<05:17, 11.66it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  75%|▊| 11229/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▊| 11229/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103137,8 +102988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11233/14932 [16:03<05:17, 11.66it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  75%|▊| 11233/14932 [16:03<05:17, 11.66it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  75%|▊| 11230/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▊| 11230/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -103146,8 +102997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11234/14932 [16:03<05:17, 11.66it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  75%|▊| 11234/14932 [16:03<05:17, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▊| 11231/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  75%|▊| 11231/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -103155,8 +103006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11235/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▊| 11235/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  75%|▊| 11232/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  75%|▊| 11232/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103164,8 +103015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11236/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  75%|▊| 11236/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  75%|▊| 11233/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  75%|▊| 11233/14932 [15:59<05:16, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103173,8 +103024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11237/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  75%|▊| 11237/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  75%|▊| 11234/14932 [16:00<05:16, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  75%|▊| 11234/14932 [16:00<05:16, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103182,8 +103033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11238/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  75%|▊| 11238/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▊| 11235/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▊| 11235/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103191,8 +103042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11239/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▊| 11239/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  75%|▊| 11236/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▊| 11236/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -103200,8 +103051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11240/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  75%|▊| 11240/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  75%|▊| 11237/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  75%|▊| 11237/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -103209,8 +103060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11241/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  75%|▊| 11241/14932 [16:03<05:16, 11.66it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▊| 11238/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11238/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103218,8 +103069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11242/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▊| 11242/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▊| 11239/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▊| 11239/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -103227,8 +103078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11243/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▊| 11243/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  75%|▊| 11240/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▊| 11240/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -103236,8 +103087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11244/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  75%|▊| 11244/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  75%|▊| 11241/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  75%|▊| 11241/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -103245,8 +103096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11245/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  75%|▊| 11245/14932 [16:03<05:16, 11.67it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  75%|▊| 11242/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  75%|▊| 11242/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -103254,8 +103105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11246/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  75%|▊| 11246/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▊| 11243/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  75%|▊| 11243/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -103263,8 +103114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11247/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▊| 11247/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  75%|▊| 11244/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  75%|▊| 11244/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -103272,8 +103123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11248/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  75%|▊| 11248/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▊| 11245/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  75%|▊| 11245/14932 [16:00<05:15, 11.70it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -103281,8 +103132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11249/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▊| 11249/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  75%|▊| 11246/14932 [16:00<05:14, 11.70it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  75%|▊| 11246/14932 [16:00<05:14, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -103290,8 +103141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11250/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  75%|▊| 11250/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  75%|▊| 11247/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▊| 11247/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -103299,8 +103150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11251/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▊| 11251/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▊| 11248/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  75%|▊| 11248/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103308,8 +103159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11252/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▊| 11252/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=0.5"
+      "Epoch 0:  75%|▊| 11249/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▊| 11249/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -103317,8 +103168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11253/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=0.5\r",
-      "Epoch 0:  75%|▊| 11253/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  75%|▊| 11250/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  75%|▊| 11250/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -103326,8 +103177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11254/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  75%|▊| 11254/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  75%|▊| 11251/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  75%|▊| 11251/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -103335,8 +103186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11255/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  75%|▊| 11255/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▊| 11252/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  75%|▊| 11252/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103344,8 +103195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11256/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▊| 11256/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  75%|▊| 11253/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▊| 11253/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -103353,8 +103204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11257/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  75%|▊| 11257/14932 [16:04<05:15, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▊| 11254/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  75%|▊| 11254/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -103362,8 +103213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11258/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  75%|▊| 11258/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  75%|▊| 11255/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  75%|▊| 11255/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -103371,8 +103222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11259/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  75%|▊| 11259/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  75%|▊| 11256/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  75%|▊| 11256/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -103380,8 +103231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11260/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  75%|▊| 11260/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  75%|▊| 11257/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  75%|▊| 11257/14932 [16:01<05:14, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103389,8 +103240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11261/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  75%|▊| 11261/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  75%|▊| 11258/14932 [16:01<05:13, 11.70it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  75%|▊| 11258/14932 [16:01<05:13, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -103398,8 +103249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11262/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  75%|▊| 11262/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  75%|▊| 11259/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  75%|▊| 11259/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -103407,8 +103258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11263/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  75%|▊| 11263/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  75%|▊| 11260/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  75%|▊| 11260/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -103416,8 +103267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11264/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  75%|▊| 11264/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  75%|▊| 11261/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  75%|▊| 11261/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -103425,8 +103276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11265/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▊| 11265/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▊| 11262/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  75%|▊| 11262/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -103434,8 +103285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11266/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▊| 11266/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  75%|▊| 11263/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  75%|▊| 11263/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103443,8 +103294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11267/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  75%|▊| 11267/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  75%|▊| 11264/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  75%|▊| 11264/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103452,8 +103303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11268/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  75%|▊| 11268/14932 [16:05<05:14, 11.67it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  75%|▊| 11265/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  75%|▊| 11265/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103461,8 +103312,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11269/14932 [16:05<05:13, 11.67it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  75%|▊| 11269/14932 [16:05<05:13, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  75%|▊| 11266/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103470,8 +103320,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11270/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  75%|▊| 11270/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  75%|▊| 11266/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103479,8 +103328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11271/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  75%|▊| 11271/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  75%|▊| 11267/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▊| 11267/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -103488,8 +103337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11272/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  75%|▊| 11272/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  75%|▊| 11268/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  75%|▊| 11268/14932 [16:02<05:13, 11.70it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103497,8 +103346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  75%|▊| 11273/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  75%|▊| 11273/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  75%|▊| 11269/14932 [16:02<05:12, 11.70it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  75%|▊| 11269/14932 [16:02<05:12, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -103506,8 +103355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11274/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  76%|▊| 11274/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  75%|▊| 11270/14932 [16:02<05:12, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  75%|▊| 11270/14932 [16:02<05:12, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103515,8 +103364,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11275/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11275/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  75%|▊| 11271/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103524,8 +103372,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11276/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11276/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  75%|▊| 11271/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103533,8 +103380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11277/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  76%|▊| 11277/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  75%|▊| 11272/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  75%|▊| 11272/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -103542,8 +103389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11278/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  76%|▊| 11278/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  75%|▊| 11273/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  75%|▊| 11273/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -103551,8 +103398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11279/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11279/14932 [16:06<05:13, 11.67it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  76%|▊| 11274/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  76%|▊| 11274/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -103560,8 +103407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11280/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  76%|▊| 11280/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  76%|▊| 11275/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  76%|▊| 11275/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -103569,8 +103416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11281/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  76%|▊| 11281/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11276/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  76%|▊| 11276/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -103578,8 +103425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11282/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11282/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11277/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11277/14932 [16:03<05:12, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103587,8 +103434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11283/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11283/14932 [16:06<05:12, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11278/14932 [16:03<05:12, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11278/14932 [16:03<05:12, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103596,8 +103443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11284/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11284/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11279/14932 [16:03<05:12, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11279/14932 [16:03<05:12, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -103605,8 +103452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11285/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11285/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  76%|▊| 11280/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  76%|▊| 11280/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -103614,8 +103461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11286/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  76%|▊| 11286/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  76%|▊| 11281/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  76%|▊| 11281/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -103623,7 +103470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11287/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  76%|▊| 11282/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11282/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -103631,7 +103479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11287/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11283/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  76%|▊| 11283/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103639,8 +103488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11288/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11288/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  76%|▊| 11284/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11284/14932 [16:03<05:11, 11.71it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -103648,8 +103497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11289/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  76%|▊| 11289/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11285/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  76%|▊| 11285/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -103657,8 +103506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11290/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11290/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11286/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11286/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103666,7 +103515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11291/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11287/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  76%|▊| 11287/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103674,7 +103524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11291/14932 [16:07<05:12, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  76%|▊| 11288/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11288/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -103682,8 +103533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11292/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  76%|▊| 11292/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11289/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  76%|▊| 11289/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -103691,8 +103542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11293/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11293/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11290/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  76%|▊| 11290/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -103700,8 +103551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11294/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11294/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11291/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  76%|▊| 11291/14932 [16:04<05:11, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103709,8 +103560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11295/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11295/14932 [16:07<05:11, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  76%|▊| 11292/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11292/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -103718,8 +103569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11296/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  76%|▊| 11296/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  76%|▊| 11293/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  76%|▊| 11293/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -103727,8 +103578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11297/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  76%|▊| 11297/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11294/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  76%|▊| 11294/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103736,8 +103587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11298/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11298/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11295/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11295/14932 [16:04<05:10, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -103745,8 +103596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11299/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11299/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11296/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  76%|▊| 11296/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -103754,8 +103605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11300/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11300/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  76%|▊| 11297/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  76%|▊| 11297/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -103763,8 +103614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11301/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  76%|▊| 11301/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  76%|▊| 11298/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  76%|▊| 11298/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103772,8 +103623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11302/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  76%|▊| 11302/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11299/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  76%|▊| 11299/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103781,8 +103632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11303/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11303/14932 [16:08<05:11, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  76%|▊| 11300/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11300/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103790,8 +103641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11304/14932 [16:08<05:10, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  76%|▊| 11304/14932 [16:08<05:10, 11.67it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  76%|▊| 11301/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  76%|▊| 11301/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103799,8 +103650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11305/14932 [16:08<05:10, 11.67it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  76%|▊| 11305/14932 [16:08<05:10, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11302/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11302/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -103808,8 +103659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11306/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11306/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11303/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  76%|▊| 11303/14932 [16:05<05:10, 11.70it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -103817,8 +103668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11307/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11307/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11304/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11304/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -103826,8 +103677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11308/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11308/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11305/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  76%|▊| 11305/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -103835,8 +103686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11309/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11309/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11306/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  76%|▊| 11306/14932 [16:05<05:09, 11.70it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103844,8 +103695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11310/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11310/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  76%|▊| 11307/14932 [16:05<05:09, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11307/14932 [16:05<05:09, 11.71it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -103853,8 +103704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11311/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  76%|▊| 11311/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  76%|▊| 11308/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  76%|▊| 11308/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -103862,8 +103713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11312/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  76%|▊| 11312/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11309/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11309/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -103871,7 +103722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11313/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11310/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  76%|▊| 11310/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -103879,7 +103731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11313/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11311/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  76%|▊| 11311/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -103887,8 +103740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11314/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11314/14932 [16:09<05:10, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11312/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  76%|▊| 11312/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -103896,8 +103749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11315/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11315/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11313/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  76%|▊| 11313/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -103905,8 +103758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11316/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11316/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11314/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11314/14932 [16:06<05:09, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -103914,8 +103767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11317/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11317/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11315/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11315/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -103923,8 +103776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11318/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11318/14932 [16:09<05:09, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  76%|▊| 11316/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  76%|▊| 11316/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -103932,8 +103785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11319/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  76%|▊| 11319/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11317/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  76%|▊| 11317/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -103941,8 +103794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11320/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11320/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11318/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11318/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -103950,8 +103803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11321/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11321/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  76%|▊| 11319/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  76%|▊| 11319/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -103959,8 +103812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11322/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  76%|▊| 11322/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  76%|▊| 11320/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11320/14932 [16:06<05:08, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -103968,8 +103821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11323/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  76%|▊| 11323/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11321/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  76%|▊| 11321/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -103977,8 +103830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11324/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11324/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  76%|▊| 11322/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  76%|▊| 11322/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -103986,8 +103839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11325/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  76%|▊| 11325/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  76%|▊| 11323/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  76%|▊| 11323/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -103995,8 +103848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11326/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  76%|▊| 11326/14932 [16:10<05:09, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11324/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  76%|▊| 11324/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104004,8 +103857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11327/14932 [16:10<05:08, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11327/14932 [16:10<05:08, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  76%|▊| 11325/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11325/14932 [16:07<05:08, 11.71it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -104013,8 +103866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11328/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  76%|▊| 11328/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  76%|▊| 11326/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  76%|▊| 11326/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -104022,8 +103875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11329/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  76%|▊| 11329/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11327/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  76%|▊| 11327/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -104031,8 +103884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11330/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11330/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  76%|▊| 11328/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  76%|▊| 11328/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104040,8 +103893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11331/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  76%|▊| 11331/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11329/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11329/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104049,8 +103902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11332/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11332/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11330/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11330/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -104058,8 +103911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11333/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11333/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11331/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  76%|▊| 11331/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -104067,8 +103920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11334/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11334/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11332/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  76%|▊| 11332/14932 [16:07<05:07, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104076,8 +103929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11335/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11335/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11333/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11333/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -104085,8 +103938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11336/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11336/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11334/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  76%|▊| 11334/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -104094,8 +103947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11337/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11337/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11335/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  76%|▊| 11335/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104103,8 +103956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11338/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11338/14932 [16:11<05:08, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11336/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11336/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104112,8 +103965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11339/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11339/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  76%|▊| 11337/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11337/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -104121,8 +103974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11340/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  76%|▊| 11340/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11338/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  76%|▊| 11338/14932 [16:08<05:07, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104130,8 +103983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11341/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11341/14932 [16:11<05:07, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11339/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11339/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -104139,8 +103992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11342/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11342/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11340/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11340/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104148,8 +104001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11343/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11343/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11341/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11341/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -104157,8 +104010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11344/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11344/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  76%|▊| 11342/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  76%|▊| 11342/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -104166,8 +104019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11345/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  76%|▊| 11345/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11343/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  76%|▊| 11343/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -104175,8 +104028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11346/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11346/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11344/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  76%|▊| 11344/14932 [16:08<05:06, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -104184,8 +104037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11347/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11347/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11345/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  76%|▊| 11345/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -104193,8 +104046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11348/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11348/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  76%|▊| 11346/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  76%|▊| 11346/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -104202,8 +104055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11349/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  76%|▊| 11349/14932 [16:12<05:07, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11347/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  76%|▊| 11347/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -104211,8 +104064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11350/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11350/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  76%|▊| 11348/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  76%|▊| 11348/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104220,8 +104073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11351/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  76%|▊| 11351/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  76%|▊| 11349/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11349/14932 [16:09<05:06, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -104229,8 +104082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11352/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  76%|▊| 11352/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11350/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  76%|▊| 11350/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -104238,8 +104091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11353/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11353/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  76%|▊| 11351/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  76%|▊| 11351/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104247,8 +104100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11354/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  76%|▊| 11354/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11352/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11352/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104256,8 +104109,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11355/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  76%|▊| 11355/14932 [16:12<05:06, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11353/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104265,8 +104117,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11356/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11356/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11353/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104274,8 +104125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11357/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11357/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11354/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11354/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -104283,8 +104134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11358/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11358/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11355/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  76%|▊| 11355/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104292,8 +104143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11359/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11359/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11356/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11356/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104301,8 +104152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11360/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11360/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11357/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11357/14932 [16:09<05:05, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -104310,8 +104161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11361/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11361/14932 [16:13<05:06, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11358/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  76%|▊| 11358/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -104319,8 +104170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11362/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11362/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  76%|▊| 11359/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  76%|▊| 11359/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -104328,8 +104179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11363/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  76%|▊| 11363/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  76%|▊| 11360/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  76%|▊| 11360/14932 [16:10<05:05, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -104337,8 +104188,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11364/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  76%|▊| 11364/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11361/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  76%|▊| 11361/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -104346,8 +104197,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11365/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11365/14932 [16:13<05:05, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11362/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  76%|▊| 11362/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -104355,8 +104206,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11366/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11366/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11363/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  76%|▊| 11363/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -104364,8 +104215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11367/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11367/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11364/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11364/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -104373,8 +104224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11368/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11368/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  76%|▊| 11365/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  76%|▊| 11365/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -104382,8 +104233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11369/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  76%|▊| 11369/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11366/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  76%|▊| 11366/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -104391,8 +104242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11370/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11370/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11367/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  76%|▊| 11367/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104400,8 +104251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11371/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11371/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  76%|▊| 11368/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11368/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -104409,8 +104260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11372/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  76%|▊| 11372/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  76%|▊| 11369/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11369/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -104418,8 +104269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11373/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  76%|▊| 11373/14932 [16:14<05:05, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11370/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11370/14932 [16:10<05:04, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -104427,8 +104278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11374/14932 [16:14<05:04, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11374/14932 [16:14<05:04, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  76%|▊| 11371/14932 [16:11<05:04, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  76%|▊| 11371/14932 [16:11<05:04, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104436,8 +104287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11375/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  76%|▊| 11375/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  76%|▊| 11372/14932 [16:11<05:04, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11372/14932 [16:11<05:04, 11.71it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -104445,8 +104296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11376/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  76%|▊| 11376/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11373/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  76%|▊| 11373/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -104454,8 +104305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11377/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11377/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  76%|▊| 11374/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11374/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -104463,8 +104314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11378/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  76%|▊| 11378/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11375/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  76%|▊| 11375/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104472,8 +104323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11379/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11379/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11376/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11376/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104481,8 +104332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11380/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11380/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  76%|▊| 11377/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11377/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -104490,8 +104341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11381/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  76%|▊| 11381/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11378/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  76%|▊| 11378/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104499,8 +104350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11382/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11382/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  76%|▊| 11379/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11379/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -104508,8 +104359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11383/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  76%|▊| 11383/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11380/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  76%|▊| 11380/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104517,8 +104368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11384/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  76%|▊| 11384/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11381/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11381/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -104526,8 +104377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11385/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11385/14932 [16:15<05:04, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  76%|▊| 11382/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  76%|▊| 11382/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104535,8 +104386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11386/14932 [16:15<05:03, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  76%|▊| 11386/14932 [16:15<05:03, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  76%|▊| 11383/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11383/14932 [16:11<05:03, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104544,8 +104395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11387/14932 [16:15<05:03, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  76%|▊| 11387/14932 [16:15<05:03, 11.67it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  76%|▊| 11384/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11384/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -104553,8 +104404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11388/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  76%|▊| 11388/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  76%|▊| 11385/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  76%|▊| 11385/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -104562,8 +104413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11389/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  76%|▊| 11389/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11386/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  76%|▊| 11386/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -104571,8 +104422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11390/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11390/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  76%|▊| 11387/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  76%|▊| 11387/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -104580,8 +104431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11391/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  76%|▊| 11391/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11388/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  76%|▊| 11388/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104589,8 +104440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11392/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11392/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  76%|▊| 11389/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11389/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -104598,8 +104449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11393/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  76%|▊| 11393/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11390/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  76%|▊| 11390/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -104607,8 +104458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11394/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11394/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11391/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  76%|▊| 11391/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -104616,8 +104467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11395/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11395/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11392/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11392/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -104625,8 +104476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11396/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11396/14932 [16:16<05:03, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  76%|▊| 11393/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  76%|▊| 11393/14932 [16:12<05:02, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -104634,8 +104485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11397/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  76%|▊| 11397/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  76%|▊| 11394/14932 [16:13<05:02, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  76%|▊| 11394/14932 [16:13<05:02, 11.71it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -104643,8 +104494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11398/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  76%|▊| 11398/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11395/14932 [16:13<05:02, 11.71it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  76%|▊| 11395/14932 [16:13<05:02, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104652,8 +104503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11399/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11399/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11396/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11396/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -104661,8 +104512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11400/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  76%|▊| 11400/14932 [16:16<05:02, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  76%|▊| 11397/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  76%|▊| 11397/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -104670,8 +104521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11401/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  76%|▊| 11401/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11398/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  76%|▊| 11398/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -104679,8 +104530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11402/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  76%|▊| 11402/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  76%|▊| 11399/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  76%|▊| 11399/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -104688,8 +104539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11403/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  76%|▊| 11403/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11400/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  76%|▊| 11400/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -104697,8 +104548,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11404/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11404/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11401/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -104706,8 +104556,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11405/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11405/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11401/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -104715,8 +104564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11406/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11406/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  76%|▊| 11402/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  76%|▊| 11402/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104724,8 +104573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11407/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  76%|▊| 11407/14932 [16:17<05:02, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11403/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  76%|▊| 11403/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -104733,8 +104582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11408/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11408/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11404/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  76%|▊| 11404/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104742,8 +104591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11409/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11409/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11405/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11405/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -104751,8 +104600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11410/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11410/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11406/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  76%|▊| 11406/14932 [16:13<05:01, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104760,8 +104609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11411/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11411/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  76%|▊| 11407/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11407/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -104769,8 +104618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11412/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  76%|▊| 11412/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  76%|▊| 11408/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  76%|▊| 11408/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -104778,8 +104627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11413/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  76%|▊| 11413/14932 [16:17<05:01, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  76%|▊| 11409/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  76%|▊| 11409/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=5.3"
      ]
     },
     {
@@ -104787,8 +104636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11414/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  76%|▊| 11414/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  76%|▊| 11410/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=5.3\r",
+      "Epoch 0:  76%|▊| 11410/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -104796,8 +104645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11415/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  76%|▊| 11415/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  76%|▊| 11411/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11411/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104805,8 +104654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11416/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  76%|▊| 11416/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  76%|▊| 11412/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  76%|▊| 11412/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -104814,8 +104663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11417/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  76%|▊| 11417/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11413/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  76%|▊| 11413/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -104823,8 +104672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11418/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  76%|▊| 11418/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  76%|▊| 11414/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  76%|▊| 11414/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104832,8 +104681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11419/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  76%|▊| 11419/14932 [16:18<05:01, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  76%|▊| 11415/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11415/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104841,8 +104690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11420/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  76%|▊| 11420/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  76%|▊| 11416/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  76%|▊| 11416/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -104850,8 +104699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11421/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  76%|▊| 11421/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  76%|▊| 11417/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  76%|▊| 11417/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -104859,8 +104708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  76%|▊| 11422/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  76%|▊| 11422/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  76%|▊| 11418/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  76%|▊| 11418/14932 [16:14<05:00, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -104868,8 +104717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11423/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  77%|▊| 11423/14932 [16:18<05:00, 11.67it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  76%|▊| 11419/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  76%|▊| 11419/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -104877,8 +104726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11424/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  77%|▊| 11424/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  76%|▊| 11420/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  76%|▊| 11420/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104886,8 +104735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11425/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  77%|▊| 11425/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  76%|▊| 11421/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  76%|▊| 11421/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104895,8 +104744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11426/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  77%|▊| 11426/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  76%|▊| 11422/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  76%|▊| 11422/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -104904,8 +104753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11427/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11427/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11423/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  77%|▊| 11423/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -104913,8 +104762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11428/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11428/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11424/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11424/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -104922,8 +104771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11429/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11429/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11425/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11425/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -104931,8 +104780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11430/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11430/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  77%|▊| 11426/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11426/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -104940,8 +104789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11431/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  77%|▊| 11431/14932 [16:19<05:00, 11.67it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  77%|▊| 11427/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11427/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -104949,8 +104798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11432/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  77%|▊| 11432/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11428/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11428/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -104958,8 +104807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11433/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  77%|▊| 11433/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  77%|▊| 11429/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11429/14932 [16:15<04:59, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -104967,8 +104816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11434/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11434/14932 [16:19<04:59, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11430/14932 [16:16<04:59, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11430/14932 [16:16<04:59, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -104976,8 +104825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11435/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11435/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11431/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  77%|▊| 11431/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -104985,8 +104834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11436/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11436/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11432/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11432/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -104994,8 +104843,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11437/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11437/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11433/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -105003,8 +104851,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11438/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11438/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  77%|▊| 11433/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -105012,8 +104859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11439/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11439/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11434/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  77%|▊| 11434/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105021,8 +104868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11440/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11440/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  77%|▊| 11435/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11435/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -105030,8 +104877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11441/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  77%|▊| 11441/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11436/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  77%|▊| 11436/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -105039,8 +104886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11442/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11442/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  77%|▊| 11437/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11437/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105048,8 +104895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11443/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  77%|▊| 11443/14932 [16:20<04:59, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  77%|▊| 11438/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11438/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105057,8 +104904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11444/14932 [16:20<04:58, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  77%|▊| 11444/14932 [16:20<04:58, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11439/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11439/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -105066,8 +104913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11445/14932 [16:20<04:58, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11445/14932 [16:20<04:58, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  77%|▊| 11440/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  77%|▊| 11440/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105075,8 +104922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11446/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  77%|▊| 11446/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  77%|▊| 11441/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11441/14932 [16:16<04:58, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105084,8 +104931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11447/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11447/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  77%|▊| 11442/14932 [16:16<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11442/14932 [16:16<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105093,8 +104940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11448/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  77%|▊| 11448/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11443/14932 [16:16<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11443/14932 [16:16<04:57, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105102,8 +104949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11449/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11449/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  77%|▊| 11444/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11444/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105111,8 +104958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11450/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  77%|▊| 11450/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  77%|▊| 11445/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11445/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -105120,7 +104967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11451/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  77%|▊| 11446/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  77%|▊| 11446/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -105128,7 +104976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11451/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11447/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11447/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105136,8 +104985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11452/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  77%|▊| 11452/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  77%|▊| 11448/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11448/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105145,8 +104994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11453/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  77%|▊| 11453/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11449/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11449/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105154,8 +105003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11454/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11454/14932 [16:21<04:58, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  77%|▊| 11450/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11450/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105163,8 +105012,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11455/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  77%|▊| 11455/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11451/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105172,8 +105020,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11456/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11456/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11451/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105181,8 +105028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11457/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11457/14932 [16:21<04:57, 11.67it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  77%|▊| 11452/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11452/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105190,8 +105037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11458/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  77%|▊| 11458/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  77%|▊| 11453/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11453/14932 [16:17<04:57, 11.71it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -105199,8 +105046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11459/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  77%|▊| 11459/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  77%|▊| 11454/14932 [16:17<04:56, 11.71it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  77%|▊| 11454/14932 [16:17<04:56, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105208,8 +105055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11460/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  77%|▊| 11460/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  77%|▊| 11455/14932 [16:17<04:56, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11455/14932 [16:17<04:56, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105217,8 +105064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11461/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  77%|▊| 11461/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11456/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11456/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -105226,8 +105073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11462/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  77%|▊| 11462/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11457/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11457/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105235,8 +105082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11463/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11463/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  77%|▊| 11458/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11458/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -105244,8 +105091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11464/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  77%|▊| 11464/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11459/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11459/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -105253,8 +105100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11465/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11465/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11460/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11460/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -105262,8 +105109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11466/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  77%|▊| 11466/14932 [16:22<04:57, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11461/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11461/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -105271,8 +105118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11467/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11467/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  77%|▊| 11462/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  77%|▊| 11462/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105280,8 +105127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11468/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  77%|▊| 11468/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11463/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11463/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -105289,8 +105136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11469/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11469/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11464/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11464/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -105298,8 +105145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11470/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11470/14932 [16:22<04:56, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  77%|▊| 11465/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11465/14932 [16:18<04:56, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -105307,8 +105154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11471/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  77%|▊| 11471/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  77%|▊| 11466/14932 [16:18<04:55, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11466/14932 [16:18<04:55, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105316,8 +105163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11472/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  77%|▊| 11472/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11467/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11467/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -105325,8 +105172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11473/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11473/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11468/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  77%|▊| 11468/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -105334,8 +105181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11474/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11474/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11469/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  77%|▊| 11469/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -105343,8 +105190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11475/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11475/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11470/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  77%|▊| 11470/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105352,8 +105199,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11476/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  77%|▊| 11476/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  77%|▊| 11471/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105361,8 +105207,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11477/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  77%|▊| 11477/14932 [16:23<04:56, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11471/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -105370,8 +105215,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11478/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11478/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  77%|▊| 11472/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  77%|▊| 11472/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105379,8 +105224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11479/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  77%|▊| 11479/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11473/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11473/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -105388,8 +105233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11480/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11480/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  77%|▊| 11474/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  77%|▊| 11474/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105397,8 +105242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11481/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  77%|▊| 11481/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11475/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11475/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105406,8 +105251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11482/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  77%|▊| 11482/14932 [16:23<04:55, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  77%|▊| 11476/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11476/14932 [16:19<04:55, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105415,8 +105260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11483/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  77%|▊| 11483/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  77%|▊| 11477/14932 [16:19<04:54, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11477/14932 [16:19<04:54, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105424,8 +105269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11484/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  77%|▊| 11484/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11478/14932 [16:19<04:54, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11478/14932 [16:19<04:54, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105433,8 +105278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11485/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11485/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11479/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11479/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -105442,7 +105287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11486/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11480/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  77%|▊| 11480/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -105450,7 +105296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11486/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11481/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  77%|▊| 11481/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -105458,8 +105305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11487/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11487/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11482/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  77%|▊| 11482/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105467,8 +105314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11488/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  77%|▊| 11488/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11483/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11483/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105476,8 +105323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11489/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11489/14932 [16:24<04:55, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11484/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11484/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105485,8 +105332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11490/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11490/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11485/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11485/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -105494,8 +105341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11491/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11491/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11486/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  77%|▊| 11486/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -105503,8 +105350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11492/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11492/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  77%|▊| 11487/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  77%|▊| 11487/14932 [16:20<04:54, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -105512,8 +105359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11493/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  77%|▊| 11493/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11488/14932 [16:21<04:54, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  77%|▊| 11488/14932 [16:21<04:54, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -105521,8 +105368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11494/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11494/14932 [16:24<04:54, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  77%|▊| 11489/14932 [16:21<04:54, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  77%|▊| 11489/14932 [16:21<04:54, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -105530,8 +105377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11495/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  77%|▊| 11495/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  77%|▊| 11490/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  77%|▊| 11490/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -105539,8 +105386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11496/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  77%|▊| 11496/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11491/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  77%|▊| 11491/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -105548,8 +105395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11497/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11497/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  77%|▊| 11492/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11492/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105557,8 +105404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11498/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  77%|▊| 11498/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11493/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11493/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -105566,8 +105413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11499/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11499/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11494/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  77%|▊| 11494/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -105575,8 +105422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11500/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11500/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11495/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  77%|▊| 11495/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -105584,7 +105431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11501/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11496/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11496/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -105592,7 +105440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11501/14932 [16:25<04:54, 11.67it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  77%|▊| 11497/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11497/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105600,8 +105449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11502/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  77%|▊| 11502/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  77%|▊| 11498/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11498/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105609,8 +105458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11503/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11503/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  77%|▊| 11499/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11499/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -105618,8 +105467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11504/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  77%|▊| 11504/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11500/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  77%|▊| 11500/14932 [16:21<04:53, 11.71it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -105627,8 +105476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11505/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11505/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  77%|▊| 11501/14932 [16:21<04:52, 11.71it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  77%|▊| 11501/14932 [16:21<04:52, 11.71it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -105636,8 +105485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11506/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  77%|▊| 11506/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11502/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  77%|▊| 11502/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105645,8 +105494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11507/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11507/14932 [16:25<04:53, 11.67it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  77%|▊| 11503/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11503/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -105654,8 +105503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11508/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  77%|▊| 11508/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11504/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  77%|▊| 11504/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -105663,8 +105512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11509/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11509/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  77%|▊| 11505/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  77%|▊| 11505/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105672,8 +105521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11510/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  77%|▊| 11510/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11506/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11506/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105681,8 +105530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11511/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11511/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11507/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11507/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -105690,8 +105539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11512/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11512/14932 [16:26<04:53, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11508/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  77%|▊| 11508/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -105699,8 +105548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11513/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11513/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  77%|▊| 11509/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11509/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105708,8 +105557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11514/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  77%|▊| 11514/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11510/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11510/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -105717,8 +105566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11515/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11515/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11511/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11511/14932 [16:22<04:52, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -105726,8 +105575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11516/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  77%|▊| 11516/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  77%|▊| 11512/14932 [16:22<04:51, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  77%|▊| 11512/14932 [16:22<04:51, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105735,8 +105584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11517/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  77%|▊| 11517/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  77%|▊| 11513/14932 [16:22<04:51, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11513/14932 [16:22<04:51, 11.71it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -105744,8 +105593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11518/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  77%|▊| 11518/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  77%|▊| 11514/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  77%|▊| 11514/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -105753,8 +105602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11519/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  77%|▊| 11519/14932 [16:26<04:52, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  77%|▊| 11515/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  77%|▊| 11515/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -105762,8 +105611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11520/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  77%|▊| 11520/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11516/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  77%|▊| 11516/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -105771,8 +105620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11521/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11521/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11517/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  77%|▊| 11517/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -105780,8 +105629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11522/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11522/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  77%|▊| 11518/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  77%|▊| 11518/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105789,8 +105638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11523/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  77%|▊| 11523/14932 [16:27<04:52, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11519/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11519/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -105798,8 +105647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11524/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11524/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11520/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11520/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -105807,8 +105656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11525/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11525/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  77%|▊| 11521/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  77%|▊| 11521/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -105816,8 +105665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11526/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  77%|▊| 11526/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11522/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  77%|▊| 11522/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -105825,8 +105674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11527/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11527/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11523/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  77%|▊| 11523/14932 [16:23<04:51, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -105834,8 +105683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11528/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  77%|▊| 11528/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  77%|▊| 11524/14932 [16:24<04:51, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  77%|▊| 11524/14932 [16:24<04:51, 11.71it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -105843,8 +105692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11529/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  77%|▊| 11529/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11525/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  77%|▊| 11525/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105852,8 +105701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11530/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11530/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  77%|▊| 11526/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11526/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -105861,8 +105710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11531/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  77%|▊| 11531/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11527/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11527/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105870,8 +105719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11532/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11532/14932 [16:27<04:51, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11528/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11528/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -105879,8 +105728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11533/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11533/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  77%|▊| 11529/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  77%|▊| 11529/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -105888,8 +105737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11534/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  77%|▊| 11534/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  77%|▊| 11530/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11530/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -105897,8 +105746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11535/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  77%|▊| 11535/14932 [16:28<04:51, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  77%|▊| 11531/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11531/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -105906,8 +105755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11536/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  77%|▊| 11536/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11532/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  77%|▊| 11532/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -105915,8 +105764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11537/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11537/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  77%|▊| 11533/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  77%|▊| 11533/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -105924,8 +105773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11538/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  77%|▊| 11538/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11534/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11534/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105933,8 +105782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11539/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11539/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  77%|▊| 11535/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11535/14932 [16:24<04:50, 11.71it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -105942,8 +105791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11540/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  77%|▊| 11540/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=5.9"
+      "Epoch 0:  77%|▊| 11536/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  77%|▊| 11536/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -105951,8 +105800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11541/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=5.9\r",
-      "Epoch 0:  77%|▊| 11541/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  77%|▊| 11537/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11537/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -105960,8 +105809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11542/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  77%|▊| 11542/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11538/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11538/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105969,8 +105818,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11543/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11543/14932 [16:28<04:50, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11539/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -105978,8 +105826,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11544/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11544/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  77%|▊| 11539/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -105987,8 +105834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11545/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  77%|▊| 11545/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  77%|▊| 11540/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11540/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -105996,8 +105843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11546/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  77%|▊| 11546/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11541/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  77%|▊| 11541/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106005,8 +105852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11547/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11547/14932 [16:29<04:50, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11542/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11542/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106014,8 +105861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11548/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11548/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11543/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  77%|▊| 11543/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -106023,8 +105870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11549/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11549/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11544/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  77%|▊| 11544/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -106032,8 +105879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11550/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  77%|▊| 11550/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  77%|▊| 11545/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  77%|▊| 11545/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -106041,8 +105888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11551/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  77%|▊| 11551/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11546/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  77%|▊| 11546/14932 [16:25<04:49, 11.71it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -106050,8 +105897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11552/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11552/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11547/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  77%|▊| 11547/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106059,8 +105906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11553/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11553/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  77%|▊| 11548/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11548/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -106068,8 +105915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11554/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  77%|▊| 11554/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  77%|▊| 11549/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  77%|▊| 11549/14932 [16:25<04:48, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106077,8 +105924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11555/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  77%|▊| 11555/14932 [16:29<04:49, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  77%|▊| 11550/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  77%|▊| 11550/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -106086,8 +105933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11556/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  77%|▊| 11556/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  77%|▊| 11551/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  77%|▊| 11551/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106095,8 +105942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11557/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  77%|▊| 11557/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11552/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  77%|▊| 11552/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106104,8 +105951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11558/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11558/14932 [16:30<04:49, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  77%|▊| 11553/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11553/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -106113,8 +105960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11559/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  77%|▊| 11559/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  77%|▊| 11554/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  77%|▊| 11554/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -106122,8 +105969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11560/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  77%|▊| 11560/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11555/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  77%|▊| 11555/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106131,8 +105978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11561/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11561/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  77%|▊| 11556/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11556/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -106140,8 +105987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11562/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  77%|▊| 11562/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11557/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  77%|▊| 11557/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106149,8 +105996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11563/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11563/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  77%|▊| 11558/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  77%|▊| 11558/14932 [16:26<04:48, 11.71it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -106158,8 +106005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11564/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  77%|▊| 11564/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  77%|▊| 11559/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  77%|▊| 11559/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -106167,8 +106014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11565/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  77%|▊| 11565/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  77%|▊| 11560/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  77%|▊| 11560/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -106176,8 +106023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11566/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  77%|▊| 11566/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  77%|▊| 11561/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  77%|▊| 11561/14932 [16:26<04:47, 11.71it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106185,8 +106032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11567/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  77%|▊| 11567/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  77%|▊| 11562/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  77%|▊| 11562/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -106194,8 +106041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11568/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  77%|▊| 11568/14932 [16:30<04:48, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  77%|▊| 11563/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  77%|▊| 11563/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106203,8 +106050,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11569/14932 [16:31<04:48, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  77%|▊| 11569/14932 [16:31<04:48, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  77%|▊| 11564/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106212,8 +106058,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11570/14932 [16:31<04:48, 11.67it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  77%|▊| 11570/14932 [16:31<04:48, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  77%|▊| 11564/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106221,8 +106066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11571/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  77%|▊| 11571/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  77%|▊| 11565/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11565/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -106230,8 +106075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  77%|▊| 11572/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  77%|▊| 11572/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  77%|▊| 11566/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  77%|▊| 11566/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106239,8 +106084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11573/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11573/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  77%|▊| 11567/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  77%|▊| 11567/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -106248,8 +106093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11574/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  78%|▊| 11574/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11568/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  77%|▊| 11568/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -106257,8 +106102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11575/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11575/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  77%|▊| 11569/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  77%|▊| 11569/14932 [16:27<04:47, 11.71it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -106266,8 +106111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11576/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11576/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  77%|▊| 11570/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  77%|▊| 11570/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -106275,8 +106120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11577/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|��| 11577/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  77%|▊| 11571/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  77%|▊| 11571/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -106284,8 +106129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11578/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11578/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  77%|▊| 11572/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  77%|▊| 11572/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -106293,8 +106138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11579/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11579/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11573/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11573/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106302,8 +106147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11580/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11580/14932 [16:31<04:47, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11574/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11574/14932 [16:27<04:46, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106311,8 +106156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11581/14932 [16:31<04:47, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11581/14932 [16:31<04:47, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11575/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11575/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106320,8 +106165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11582/14932 [16:32<04:46, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11582/14932 [16:32<04:46, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11576/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11576/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -106329,8 +106174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11583/14932 [16:32<04:46, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11583/14932 [16:32<04:46, 11.68it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  78%|▊| 11577/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11577/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106338,8 +106183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11584/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11584/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11578/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11578/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106347,8 +106192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11585/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11585/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11579/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11579/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106356,8 +106201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11586/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11586/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11580/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11580/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -106365,8 +106210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11587/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  78%|▊| 11587/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  78%|▊| 11581/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11581/14932 [16:28<04:46, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106374,8 +106219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11588/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  78%|▊| 11588/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  78%|▊| 11582/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11582/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -106383,8 +106228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11589/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  78%|▊| 11589/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11583/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  78%|▊| 11583/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -106392,8 +106237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11590/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11590/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11584/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11584/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -106401,8 +106246,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11591/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11591/14932 [16:32<04:46, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11585/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -106410,8 +106254,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11592/14932 [16:33<04:46, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11592/14932 [16:33<04:46, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11585/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -106419,7 +106262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11593/14932 [16:33<04:46, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11586/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11586/14932 [16:28<04:45, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106427,7 +106271,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11593/14932 [16:33<04:46, 11.67it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  78%|▊| 11587/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106435,8 +106279,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11594/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  78%|▊| 11594/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11587/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -106444,8 +106287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11595/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11595/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11588/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11588/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -106453,8 +106296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11596/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  78%|▊| 11596/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  78%|▊| 11589/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11589/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -106462,8 +106305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11597/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  78%|▊| 11597/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11590/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11590/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106471,8 +106314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11598/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11598/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11591/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  78%|▊| 11591/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -106480,8 +106323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11599/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  78%|▊| 11599/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11592/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  78%|▊| 11592/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -106489,8 +106332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11600/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11600/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11593/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  78%|▊| 11593/14932 [16:29<04:45, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -106498,8 +106341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11601/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11601/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11594/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11594/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -106507,8 +106350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11602/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11602/14932 [16:33<04:45, 11.67it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  78%|▊| 11595/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  78%|▊| 11595/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -106516,8 +106359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11603/14932 [16:33<04:45, 11.68it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  78%|▊| 11603/14932 [16:33<04:45, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  78%|▊| 11596/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  78%|▊| 11596/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -106525,8 +106368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11604/14932 [16:33<04:45, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  78%|▊| 11604/14932 [16:33<04:45, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11597/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  78%|▊| 11597/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -106534,8 +106377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11605/14932 [16:33<04:44, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11605/14932 [16:33<04:44, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11598/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11598/14932 [16:29<04:44, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106543,8 +106386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11606/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11606/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11599/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11599/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106552,8 +106395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11607/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  78%|▊| 11607/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11600/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11600/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106561,8 +106404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11608/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11608/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  78%|▊| 11601/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  78%|▊| 11601/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -106570,8 +106413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11609/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  78%|▊| 11609/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11602/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  78%|▊| 11602/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106579,8 +106422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11610/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11610/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11603/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11603/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -106588,7 +106431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11611/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11604/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11604/14932 [16:30<04:44, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -106596,7 +106440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11611/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11605/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  78%|▊| 11605/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106604,8 +106449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11612/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11612/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11606/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11606/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106613,8 +106458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11613/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11613/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11607/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11607/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -106622,8 +106467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11614/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11614/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11608/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  78%|▊| 11608/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -106631,8 +106476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11615/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  78%|▊| 11615/14932 [16:34<04:44, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11609/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  78%|▊| 11609/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -106640,8 +106485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11616/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  78%|▊| 11616/14932 [16:34<04:44, 11.67it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11610/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  78%|▊| 11610/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106649,8 +106494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11617/14932 [16:35<04:43, 11.67it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  78%|▊| 11617/14932 [16:35<04:43, 11.67it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11611/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11611/14932 [16:30<04:43, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -106658,8 +106503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11618/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11618/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11612/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  78%|▊| 11612/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106667,8 +106512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11619/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11619/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  78%|▊| 11613/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11613/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106676,8 +106521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11620/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  78%|▊| 11620/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  78%|▊| 11614/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11614/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -106685,8 +106530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11621/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  78%|▊| 11621/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11615/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  78%|▊| 11615/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -106694,8 +106539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11622/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11622/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  78%|▊| 11616/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11616/14932 [16:31<04:43, 11.72it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -106703,8 +106548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11623/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  78%|▊| 11623/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  78%|▊| 11617/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  78%|▊| 11617/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -106712,8 +106557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11624/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  78%|▊| 11624/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  78%|▊| 11618/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  78%|▊| 11618/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106721,8 +106566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11625/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11625/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11619/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11619/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106730,8 +106575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11626/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11626/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11620/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11620/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -106739,8 +106584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11627/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11627/14932 [16:35<04:43, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11621/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  78%|▊| 11621/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106748,8 +106593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11628/14932 [16:35<04:42, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11628/14932 [16:35<04:42, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11622/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11622/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -106757,8 +106602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11629/14932 [16:35<04:42, 11.68it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  78%|▊| 11629/14932 [16:35<04:42, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11623/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11623/14932 [16:31<04:42, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106766,8 +106611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11630/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11630/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  78%|▊| 11624/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11624/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -106775,8 +106620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11631/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  78%|▊| 11631/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  78%|▊| 11625/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  78%|▊| 11625/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106784,8 +106629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11632/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  78%|▊| 11632/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  78%|▊| 11626/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11626/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106793,8 +106638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11633/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  78%|▊| 11633/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  78%|▊| 11627/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11627/14932 [16:32<04:42, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -106802,8 +106647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11634/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  78%|▊| 11634/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  78%|▊| 11628/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  78%|▊| 11628/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106811,8 +106656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11635/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  78%|▊| 11635/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  78%|▊| 11629/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11629/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -106820,8 +106665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11636/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  78%|▊| 11636/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11630/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  78%|▊| 11630/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106829,8 +106674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11637/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11637/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11631/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11631/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -106838,8 +106683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11638/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11638/14932 [16:36<04:42, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  78%|▊| 11632/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  78%|▊| 11632/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106847,8 +106692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11639/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  78%|▊| 11639/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11633/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11633/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106856,8 +106701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11640/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11640/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11634/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11634/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -106865,8 +106710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11641/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  78%|▊| 11641/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11635/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  78%|▊| 11635/14932 [16:32<04:41, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -106874,8 +106719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11642/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11642/14932 [16:36<04:41, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11636/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11636/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -106883,8 +106728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11643/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  78%|▊| 11643/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11637/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11637/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -106892,8 +106737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11644/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11644/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11638/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11638/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -106901,8 +106746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11645/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11645/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11639/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11639/14932 [16:33<04:41, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -106910,8 +106755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11646/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11646/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  78%|▊| 11640/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11640/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -106919,8 +106764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11647/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  78%|▊| 11647/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11641/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  78%|▊| 11641/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -106928,8 +106773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11648/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11648/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11642/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  78%|▊| 11642/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -106937,8 +106782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11649/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11649/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  78%|▊| 11643/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  78%|▊| 11643/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -106946,8 +106791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11650/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  78%|▊| 11650/14932 [16:37<04:41, 11.68it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  78%|▊| 11644/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11644/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -106955,8 +106800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11651/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  78%|▊| 11651/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  78%|▊| 11645/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  78%|▊| 11645/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -106964,8 +106809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11652/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  78%|▊| 11652/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11646/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  78%|▊| 11646/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -106973,8 +106818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11653/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11653/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11647/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  78%|▊| 11647/14932 [16:33<04:40, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -106982,8 +106827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11654/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11654/14932 [16:37<04:40, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11648/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11648/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -106991,8 +106836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11655/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11655/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  78%|▊| 11649/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11649/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107000,8 +106845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11656/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  78%|▊| 11656/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  78%|▊| 11650/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11650/14932 [16:34<04:40, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -107009,8 +106854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11657/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  78%|▊| 11657/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11651/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11651/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107018,7 +106863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11658/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11652/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11652/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -107026,7 +106872,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11658/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11653/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -107034,8 +106880,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11659/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11659/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11653/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -107043,8 +106888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11660/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11660/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11654/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11654/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -107052,8 +106897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11661/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11661/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11655/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  78%|▊| 11655/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107061,8 +106906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11662/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11662/14932 [16:38<04:40, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11656/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11656/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -107070,8 +106915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11663/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11663/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11657/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11657/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107079,8 +106924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11664/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11664/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11658/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11658/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -107088,8 +106933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11665/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  78%|▊| 11665/14932 [16:38<04:39, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  78%|▊| 11659/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11659/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107097,8 +106942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11666/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  78%|▊| 11666/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  78%|▊| 11660/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11660/14932 [16:34<04:39, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -107106,8 +106951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11667/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  78%|▊| 11667/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11661/14932 [16:35<04:39, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  78%|▊| 11661/14932 [16:35<04:39, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -107115,8 +106960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11668/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  78%|▊| 11668/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  78%|▊| 11662/14932 [16:35<04:39, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  78%|▊| 11662/14932 [16:35<04:39, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -107124,8 +106969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11669/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11669/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  78%|▊| 11663/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  78%|▊| 11663/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -107133,8 +106978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11670/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  78%|▊| 11670/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  78%|▊| 11664/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11664/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -107142,8 +106987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11671/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  78%|▊| 11671/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  78%|▊| 11665/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  78%|▊| 11665/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -107151,8 +106996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11672/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  78%|▊| 11672/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11666/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  78%|▊| 11666/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -107160,8 +107005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11673/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11673/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  78%|▊| 11667/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  78%|▊| 11667/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -107169,8 +107014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11674/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  78%|▊| 11674/14932 [16:39<04:39, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11668/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  78%|▊| 11668/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107178,8 +107023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11675/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11675/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11669/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11669/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107187,8 +107032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11676/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11676/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11670/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11670/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107196,8 +107041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11677/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11677/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11671/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11671/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -107205,8 +107050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11678/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11678/14932 [16:39<04:38, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11672/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  78%|▊| 11672/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -107214,8 +107059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11679/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11679/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  78%|▊| 11673/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11673/14932 [16:35<04:38, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -107223,8 +107068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11680/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  78%|▊| 11680/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  78%|▊| 11674/14932 [16:35<04:37, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  78%|▊| 11674/14932 [16:35<04:37, 11.72it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -107232,8 +107077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11681/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  78%|▊| 11681/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  78%|▊| 11675/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  78%|▊| 11675/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107241,8 +107086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11682/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11682/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  78%|▊| 11676/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11676/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107250,8 +107095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11683/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  78%|▊| 11683/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11677/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  78%|▊| 11677/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107259,8 +107104,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11684/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11684/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11678/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11678/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -107268,8 +107113,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11685/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11685/14932 [16:40<04:38, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11679/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  78%|▊| 11679/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -107277,8 +107122,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11686/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11686/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  78%|▊| 11680/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  78%|▊| 11680/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -107286,8 +107131,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11687/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  78%|▊| 11687/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  78%|▊| 11681/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11681/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107295,8 +107140,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11688/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  78%|▊| 11688/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  78%|▊| 11682/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11682/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -107304,8 +107149,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11689/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  78%|▊| 11689/14932 [16:40<04:37, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  78%|▊| 11683/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11683/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -107313,8 +107158,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11690/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  78%|▊| 11690/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  78%|▊| 11684/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11684/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -107322,8 +107167,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11691/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  78%|▊| 11691/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  78%|▊| 11685/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11685/14932 [16:36<04:37, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -107331,7 +107176,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11692/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  78%|▊| 11686/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  78%|▊| 11686/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -107339,7 +107185,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11692/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  78%|▊| 11687/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11687/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -107347,8 +107194,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11693/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  78%|▊| 11693/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  78%|▊| 11688/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11688/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -107356,8 +107203,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11694/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  78%|▊| 11694/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  78%|▊| 11689/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  78%|▊| 11689/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -107365,8 +107212,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11695/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  78%|▊| 11695/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  78%|▊| 11690/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  78%|▊| 11690/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -107374,8 +107221,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11696/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  78%|▊| 11696/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  78%|▊| 11691/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  78%|▊| 11691/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107383,8 +107230,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11697/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  78%|▊| 11697/14932 [16:41<04:37, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11692/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11692/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -107392,8 +107239,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11698/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  78%|▊| 11698/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  78%|▊| 11693/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11693/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -107401,8 +107248,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11699/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  78%|▊| 11699/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  78%|▊| 11694/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  78%|▊| 11694/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -107410,8 +107257,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11700/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  78%|▊| 11700/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  78%|▊| 11695/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  78%|▊| 11695/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -107419,8 +107266,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11701/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  78%|▊| 11701/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  78%|▊| 11696/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  78%|▊| 11696/14932 [16:37<04:36, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -107428,8 +107275,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11702/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  78%|▊| 11702/14932 [16:41<04:36, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11697/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  78%|▊| 11697/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107437,8 +107284,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11703/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11703/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  78%|▊| 11698/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11698/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -107446,8 +107293,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11704/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  78%|▊| 11704/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11699/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11699/14932 [16:37<04:35, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -107455,8 +107302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11705/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11705/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  78%|▊| 11700/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  78%|▊| 11700/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -107464,8 +107311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11706/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  78%|▊| 11706/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  78%|▊| 11701/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  78%|▊| 11701/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107473,8 +107320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11707/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  78%|▊| 11707/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  78%|▊| 11702/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  78%|▊| 11702/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -107482,8 +107329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11708/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  78%|▊| 11708/14932 [16:42<04:36, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  78%|▊| 11703/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  78%|▊| 11703/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -107491,8 +107338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11709/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  78%|▊| 11709/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  78%|▊| 11704/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11704/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -107500,8 +107347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11710/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  78%|▊| 11710/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11705/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11705/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -107509,8 +107356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11711/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11711/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11706/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  78%|▊| 11706/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107518,8 +107365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11712/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11712/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  78%|▊| 11707/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11707/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107527,8 +107374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11713/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  78%|▊| 11713/14932 [16:42<04:35, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11708/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11708/14932 [16:38<04:35, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107536,8 +107383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11714/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11714/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  78%|▊| 11709/14932 [16:38<04:34, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11709/14932 [16:38<04:34, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107545,8 +107392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11715/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  78%|▊| 11715/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  78%|▊| 11710/14932 [16:38<04:34, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  78%|▊| 11710/14932 [16:38<04:34, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107554,8 +107401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11716/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  78%|▊| 11716/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  78%|▊| 11711/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  78%|▊| 11711/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -107563,8 +107410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11717/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  78%|▊| 11717/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  78%|▊| 11712/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  78%|▊| 11712/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107572,8 +107419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11718/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  78%|▊| 11718/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  78%|▊| 11713/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  78%|▊| 11713/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107581,8 +107428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11719/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  78%|▊| 11719/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  78%|▊| 11714/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  78%|▊| 11714/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -107590,8 +107437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11720/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  78%|▊| 11720/14932 [16:43<04:35, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11715/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11715/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -107599,8 +107446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  78%|▊| 11721/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  78%|▊| 11721/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  78%|▊| 11716/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  78%|▊| 11716/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -107608,8 +107455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11722/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  79%|▊| 11722/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  78%|▊| 11717/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  78%|▊| 11717/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107617,8 +107464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11723/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  79%|▊| 11723/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  78%|▊| 11718/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  78%|▊| 11718/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -107626,8 +107473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11724/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11724/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11719/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  78%|▊| 11719/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -107635,8 +107482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11725/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  79%|▊| 11725/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  78%|▊| 11720/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  78%|▊| 11720/14932 [16:39<04:34, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -107644,8 +107491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11726/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11726/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  78%|▊| 11721/14932 [16:39<04:33, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  78%|▊| 11721/14932 [16:39<04:33, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -107653,8 +107500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11727/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  79%|▊| 11727/14932 [16:43<04:34, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11722/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  79%|▊| 11722/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -107662,8 +107509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11728/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11728/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11723/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  79%|▊| 11723/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107671,8 +107518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11729/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11729/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11724/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  79%|▊| 11724/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -107680,8 +107527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11730/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11730/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11725/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  79%|▊| 11725/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -107689,8 +107536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11731/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11731/14932 [16:44<04:34, 11.68it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  79%|▊| 11726/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11726/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -107698,8 +107545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11732/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  79%|▊| 11732/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11727/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  79%|▊| 11727/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107707,8 +107554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11733/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  79%|▊| 11733/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  79%|▊| 11728/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11728/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107716,8 +107563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11734/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  79%|▊| 11734/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  79%|▊| 11729/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  79%|▊| 11729/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -107725,8 +107572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11735/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  79%|▊| 11735/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11730/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  79%|▊| 11730/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -107734,8 +107581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11736/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11736/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11731/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11731/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -107743,8 +107590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11737/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11737/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11732/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  79%|▊| 11732/14932 [16:40<04:33, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -107752,8 +107599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11738/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11738/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  79%|▊| 11733/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11733/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107761,8 +107608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11739/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  79%|▊| 11739/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  79%|▊| 11734/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11734/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -107770,8 +107617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11740/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  79%|▊| 11740/14932 [16:44<04:33, 11.68it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  79%|▊| 11735/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11735/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -107779,8 +107626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11741/14932 [16:45<04:33, 11.68it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  79%|▊| 11741/14932 [16:45<04:33, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11736/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  79%|▊| 11736/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -107788,8 +107635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11742/14932 [16:45<04:33, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11742/14932 [16:45<04:33, 11.68it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  79%|▊| 11737/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  79%|▊| 11737/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -107797,8 +107644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11743/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  79%|▊| 11743/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11738/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11738/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -107806,8 +107653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11744/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11744/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11739/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11739/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -107815,8 +107662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11745/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11745/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11740/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  79%|▊| 11740/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -107824,8 +107671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11746/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11746/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  79%|▊| 11741/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11741/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=0.5"
      ]
     },
     {
@@ -107833,8 +107680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11747/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  79%|▊| 11747/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  79%|▊| 11742/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=0.5\r",
+      "Epoch 0:  79%|▊| 11742/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107842,8 +107689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11748/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  79%|▊| 11748/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11743/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11743/14932 [16:41<04:32, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107851,8 +107698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11749/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11749/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11744/14932 [16:42<04:32, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11744/14932 [16:42<04:32, 11.72it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -107860,8 +107707,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11750/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11750/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11745/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -107869,8 +107715,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11751/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11751/14932 [16:45<04:32, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11745/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107878,8 +107723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11752/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11752/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11746/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11746/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107887,8 +107732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11753/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11753/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  79%|▊| 11747/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11747/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107896,8 +107741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11754/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  79%|▊| 11754/14932 [16:46<04:32, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  79%|▊| 11748/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11748/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -107905,8 +107750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11755/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  79%|▊| 11755/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11749/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  79%|▊| 11749/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -107914,8 +107759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11756/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11756/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  79%|▊| 11750/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  79%|▊| 11750/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -107923,8 +107768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11757/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  79%|▊| 11757/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  79%|▊| 11751/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  79%|▊| 11751/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -107932,8 +107777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11758/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  79%|▊| 11758/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  79%|▊| 11752/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11752/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -107941,8 +107786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11759/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  79%|▊| 11759/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11753/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11753/14932 [16:42<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -107950,8 +107795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11760/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11760/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11754/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11754/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -107959,8 +107804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11761/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11761/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11755/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11755/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -107968,8 +107813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11762/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11762/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11756/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11756/14932 [16:43<04:31, 11.72it/s, v_num=ui8w, train/loss=4.7"
      ]
     },
     {
@@ -107977,8 +107822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11763/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11763/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11757/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=4.7\r",
+      "Epoch 0:  79%|▊| 11757/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -107986,8 +107831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11764/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11764/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11758/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11758/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -107995,8 +107840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11765/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11765/14932 [16:46<04:31, 11.68it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  79%|▊| 11759/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  79%|▊| 11759/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108004,8 +107849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11766/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  79%|▊| 11766/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  79%|▊| 11760/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11760/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -108013,8 +107858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11767/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  79%|▊| 11767/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11761/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  79%|▊| 11761/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108022,8 +107867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11768/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11768/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11762/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11762/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108031,8 +107876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11769/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11769/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11763/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11763/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -108040,8 +107885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11770/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11770/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11764/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  79%|▊| 11764/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -108049,8 +107894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11771/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11771/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11765/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11765/14932 [16:43<04:30, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -108058,8 +107903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11772/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11772/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11766/14932 [16:44<04:30, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  79%|▊| 11766/14932 [16:44<04:30, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -108067,8 +107912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11773/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11773/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  79%|▊| 11767/14932 [16:44<04:30, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  79%|▊| 11767/14932 [16:44<04:30, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -108076,8 +107921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11774/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  79%|▊| 11774/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11768/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  79%|▊| 11768/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108085,8 +107930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11775/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11775/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11769/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11769/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108094,8 +107939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11776/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11776/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  79%|▊| 11770/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11770/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108103,8 +107948,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11777/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  79%|▊| 11777/14932 [16:47<04:30, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11771/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108112,8 +107956,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11778/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11778/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  79%|▊| 11771/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -108121,8 +107964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11779/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  79%|▊| 11779/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  79%|▊| 11772/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  79%|▊| 11772/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108130,8 +107973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11780/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  79%|▊| 11780/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  79%|▊| 11773/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11773/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108139,8 +107982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11781/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  79%|▊| 11781/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11774/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11774/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108148,8 +107991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11782/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  79%|▊| 11782/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  79%|▊| 11775/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11775/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108157,8 +108000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11783/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  79%|▊| 11783/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11776/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11776/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -108166,8 +108009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11784/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11784/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  79%|▊| 11777/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  79%|▊| 11777/14932 [16:44<04:29, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108175,8 +108018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11785/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  79%|▊| 11785/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  79%|▊| 11778/14932 [16:45<04:29, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11778/14932 [16:45<04:29, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108184,8 +108027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11786/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  79%|▊| 11786/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11779/14932 [16:45<04:29, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11779/14932 [16:45<04:29, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108193,8 +108036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11787/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11787/14932 [16:48<04:29, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  79%|▊| 11780/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11780/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108202,8 +108045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11788/14932 [16:49<04:29, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  79%|▊| 11788/14932 [16:49<04:29, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11781/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11781/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -108211,8 +108054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11789/14932 [16:49<04:29, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11789/14932 [16:49<04:29, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11782/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11782/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -108220,8 +108063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11790/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11790/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  79%|▊| 11783/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  79%|▊| 11783/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -108229,8 +108072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11791/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  79%|▊| 11791/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  79%|▊| 11784/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  79%|▊| 11784/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -108238,8 +108081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11792/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  79%|▊| 11792/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11785/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11785/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -108247,8 +108090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11793/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11793/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  79%|▊| 11786/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  79%|▊| 11786/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=0.5"
      ]
     },
     {
@@ -108256,8 +108099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11794/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  79%|▊| 11794/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11787/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=0.5\r",
+      "Epoch 0:  79%|▊| 11787/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -108265,8 +108108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11795/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11795/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  79%|▊| 11788/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  79%|▊| 11788/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108274,8 +108117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11796/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  79%|▊| 11796/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11789/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11789/14932 [16:45<04:28, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -108283,8 +108126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11797/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11797/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  79%|▊| 11790/14932 [16:46<04:28, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  79%|▊| 11790/14932 [16:46<04:28, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108292,8 +108135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11798/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  79%|▊| 11798/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11791/14932 [16:46<04:28, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11791/14932 [16:46<04:28, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108301,7 +108144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11799/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11792/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11792/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108309,7 +108153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11799/14932 [16:49<04:28, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11793/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11793/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -108317,8 +108162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11800/14932 [16:50<04:28, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11800/14932 [16:50<04:28, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11794/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  79%|▊| 11794/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108326,8 +108171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11801/14932 [16:50<04:28, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11801/14932 [16:50<04:28, 11.68it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  79%|▊| 11795/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11795/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108335,8 +108180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11802/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  79%|▊| 11802/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11796/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11796/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -108344,8 +108189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11803/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  79%|▊| 11803/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11797/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  79%|▊| 11797/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108353,8 +108198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11804/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11804/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  79%|▊| 11798/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11798/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -108362,8 +108207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11805/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  79%|▊| 11805/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  79%|▊| 11799/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  79%|▊| 11799/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=5.5"
      ]
     },
     {
@@ -108371,8 +108216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11806/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  79%|▊| 11806/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  79%|▊| 11800/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=5.5\r",
+      "Epoch 0:  79%|▊| 11800/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -108380,8 +108225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11807/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  79%|▊| 11807/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11801/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11801/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108389,8 +108234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11808/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11808/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  79%|▊| 11802/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11802/14932 [16:46<04:27, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108398,8 +108243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11809/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  79%|▊| 11809/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  79%|▊| 11803/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11803/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -108407,8 +108252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11810/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  79%|▊| 11810/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11804/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11804/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -108416,8 +108261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11811/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11811/14932 [16:50<04:27, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  79%|▊| 11805/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  79%|▊| 11805/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108425,8 +108270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11812/14932 [16:51<04:27, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  79%|▊| 11812/14932 [16:51<04:27, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  79%|▊| 11806/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11806/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -108434,8 +108279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11813/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  79%|▊| 11813/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  79%|▊| 11807/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11807/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108443,8 +108288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11814/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  79%|▊| 11814/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  79%|▊| 11808/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11808/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108452,8 +108297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11815/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  79%|▊| 11815/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  79%|▊| 11809/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11809/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -108461,8 +108306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11816/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  79%|▊| 11816/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  79%|▊| 11810/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  79%|▊| 11810/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -108470,8 +108315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11817/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  79%|▊| 11817/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  79%|▊| 11811/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  79%|▊| 11811/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108479,8 +108324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11818/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  79%|▊| 11818/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  79%|▊| 11812/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11812/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -108488,8 +108333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11819/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  79%|▊| 11819/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  79%|▊| 11813/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  79%|▊| 11813/14932 [16:47<04:26, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108497,8 +108342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11820/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  79%|▊| 11820/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  79%|▊| 11814/14932 [16:48<04:26, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11814/14932 [16:48<04:26, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108506,8 +108351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11821/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  79%|▊| 11821/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  79%|▊| 11815/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11815/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -108515,8 +108360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11822/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  79%|▊| 11822/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11816/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  79%|▊| 11816/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108524,8 +108369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11823/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11823/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  79%|▊| 11817/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11817/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108533,8 +108378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11824/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  79%|▊| 11824/14932 [16:51<04:26, 11.68it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  79%|▊| 11818/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11818/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108542,8 +108387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11825/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  79%|▊| 11825/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  79%|▊| 11819/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11819/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108551,8 +108396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11826/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  79%|▊| 11826/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  79%|▊| 11820/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11820/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108560,8 +108405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11827/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  79%|▊| 11827/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  79%|▊| 11821/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11821/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -108569,8 +108414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11828/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  79%|▊| 11828/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  79%|▊| 11822/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11822/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -108578,8 +108423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11829/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  79%|▊| 11829/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  79%|▊| 11823/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  79%|▊| 11823/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -108587,8 +108432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11830/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  79%|▊| 11830/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  79%|▊| 11824/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11824/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -108596,8 +108441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11831/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  79%|▊| 11831/14932 [16:52<04:25, 11.68it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11825/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  79%|▊| 11825/14932 [16:48<04:25, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -108605,8 +108450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11832/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11832/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  79%|▊| 11826/14932 [16:49<04:25, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  79%|▊| 11826/14932 [16:49<04:25, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -108614,8 +108459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11833/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  79%|▊| 11833/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  79%|▊| 11827/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  79%|▊| 11827/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -108623,8 +108468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11834/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  79%|▊| 11834/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11828/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  79%|▊| 11828/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108632,8 +108477,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11835/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11835/14932 [16:52<04:25, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11829/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108641,8 +108485,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11836/14932 [16:52<04:24, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  79%|▊| 11836/14932 [16:52<04:24, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  79%|▊| 11829/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108650,8 +108493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11837/14932 [16:52<04:24, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  79%|▊| 11837/14932 [16:52<04:24, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11830/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11830/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -108659,8 +108502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11838/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11838/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  79%|▊| 11831/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  79%|▊| 11831/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -108668,8 +108511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11839/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  79%|▊| 11839/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  79%|▊| 11832/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  79%|▊| 11832/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108677,8 +108520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11840/14932 [16:53<04:24, 11.68it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  79%|▊| 11840/14932 [16:53<04:24, 11.68it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  79%|▊| 11833/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11833/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108686,8 +108529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11841/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  79%|▊| 11841/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  79%|▊| 11834/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11834/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108695,8 +108538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11842/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  79%|▊| 11842/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  79%|▊| 11835/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11835/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108704,8 +108547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11843/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  79%|▊| 11843/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11836/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11836/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -108713,8 +108556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11844/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  79%|▊| 11844/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11837/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  79%|▊| 11837/14932 [16:49<04:24, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -108722,8 +108565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11845/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11845/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  79%|▊| 11838/14932 [16:49<04:23, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  79%|▊| 11838/14932 [16:49<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108731,8 +108574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11846/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  79%|▊| 11846/14932 [16:53<04:24, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11839/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11839/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108740,8 +108583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11847/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  79%|▊| 11847/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11840/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11840/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108749,8 +108592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11848/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11848/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  79%|▊| 11841/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11841/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -108758,8 +108601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11849/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  79%|▊| 11849/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  79%|▊| 11842/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11842/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -108767,8 +108610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11850/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  79%|▊| 11850/14932 [16:53<04:23, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11843/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  79%|▊| 11843/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -108776,8 +108619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11851/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11851/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11844/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  79%|▊| 11844/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -108785,8 +108628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11852/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  79%|▊| 11852/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  79%|▊| 11845/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  79%|▊| 11845/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -108794,8 +108637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11853/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  79%|▊| 11853/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  79%|▊| 11846/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  79%|▊| 11846/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108803,8 +108646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11854/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  79%|▊| 11854/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  79%|▊| 11847/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11847/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -108812,8 +108655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11855/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  79%|▊| 11855/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  79%|▊| 11848/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  79%|▊| 11848/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -108821,8 +108664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11856/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  79%|▊| 11856/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  79%|▊| 11849/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11849/14932 [16:50<04:23, 11.72it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -108830,8 +108673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11857/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  79%|▊| 11857/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  79%|▊| 11850/14932 [16:50<04:22, 11.72it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  79%|▊| 11850/14932 [16:50<04:22, 11.72it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -108839,8 +108682,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11858/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  79%|▊| 11858/14932 [16:54<04:23, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  79%|▊| 11851/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  79%|▊| 11851/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -108848,8 +108691,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11859/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  79%|▊| 11859/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  79%|▊| 11852/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  79%|▊| 11852/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108857,8 +108700,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11860/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  79%|▊| 11860/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  79%|▊| 11853/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11853/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -108866,8 +108709,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11861/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  79%|▊| 11861/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  79%|▊| 11854/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  79%|▊| 11854/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -108875,8 +108718,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11862/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  79%|▊| 11862/14932 [16:54<04:22, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  79%|▊| 11855/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  79%|▊| 11855/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -108884,8 +108727,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11863/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  79%|▊| 11863/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11856/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  79%|▊| 11856/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -108893,7 +108736,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11864/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  79%|▊| 11857/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  79%|▊| 11857/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -108901,7 +108745,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11864/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  79%|▊| 11858/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  79%|▊| 11858/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -108909,8 +108754,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11865/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  79%|▊| 11865/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  79%|▊| 11859/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  79%|▊| 11859/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108918,8 +108763,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11866/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  79%|▊| 11866/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  79%|▊| 11860/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11860/14932 [16:51<04:22, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -108927,8 +108772,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11867/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  79%|▊| 11867/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  79%|▊| 11861/14932 [16:51<04:21, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  79%|▊| 11861/14932 [16:51<04:21, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -108936,8 +108781,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11868/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  79%|▊| 11868/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  79%|▊| 11862/14932 [16:51<04:21, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11862/14932 [16:51<04:21, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -108945,8 +108790,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11869/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  79%|▊| 11869/14932 [16:55<04:22, 11.69it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  79%|▊| 11863/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  79%|▊| 11863/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -108954,8 +108799,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  79%|▊| 11870/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  79%|▊| 11870/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  79%|▊| 11864/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11864/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -108963,8 +108808,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11871/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  80%|▊| 11871/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  79%|▊| 11865/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  79%|▊| 11865/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -108972,8 +108817,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11872/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11872/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  79%|▊| 11866/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  79%|▊| 11866/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -108981,7 +108826,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11873/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  79%|▊| 11867/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  79%|▊| 11867/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -108989,7 +108835,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11873/14932 [16:55<04:21, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  79%|▊| 11868/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  79%|▊| 11868/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -108997,8 +108844,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11874/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 11874/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  79%|▊| 11869/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  79%|▊| 11869/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109006,8 +108853,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11875/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11875/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  79%|▊| 11870/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  79%|▊| 11870/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109015,8 +108862,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11876/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 11876/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  80%|▊| 11871/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11871/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109024,8 +108871,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11877/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  80%|▊| 11877/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  80%|▊| 11872/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11872/14932 [16:52<04:21, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109033,8 +108880,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11878/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  80%|▊| 11878/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 11873/14932 [16:52<04:20, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11873/14932 [16:52<04:20, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -109042,8 +108889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11879/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 11879/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 11874/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  80%|▊| 11874/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109051,8 +108898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11880/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 11880/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  80%|▊| 11875/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11875/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -109060,8 +108907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11881/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  80%|▊| 11881/14932 [16:56<04:21, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11876/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  80%|▊| 11876/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -109069,8 +108916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11882/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11882/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11877/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  80%|▊| 11877/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -109078,8 +108925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11883/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11883/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  80%|▊| 11878/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11878/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -109087,8 +108934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11884/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  80%|▊| 11884/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  80%|▊| 11879/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11879/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -109096,8 +108943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11885/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  80%|▊| 11885/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11880/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  80%|▊| 11880/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -109105,8 +108952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11886/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11886/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11881/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  80%|▊| 11881/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -109114,8 +108961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11887/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11887/14932 [16:56<04:20, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  80%|▊| 11882/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  80%|▊| 11882/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -109123,8 +108970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11888/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 11888/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  80%|▊| 11883/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  80%|▊| 11883/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109132,8 +108979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11889/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  80%|▊| 11889/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11884/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11884/14932 [16:53<04:20, 11.72it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -109141,8 +108988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11890/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11890/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11885/14932 [16:53<04:19, 11.72it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  80%|▊| 11885/14932 [16:53<04:19, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109150,8 +108997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11891/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11891/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11886/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11886/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -109159,8 +109006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11892/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11892/14932 [16:57<04:20, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11887/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  80%|▊| 11887/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109168,8 +109015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11893/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11893/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  80%|▊| 11888/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11888/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -109177,8 +109024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11894/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11894/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  80%|▊| 11889/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11889/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109186,8 +109033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11895/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  80%|▊| 11895/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  80%|▊| 11890/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11890/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109195,8 +109042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11896/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  80%|▊| 11896/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11891/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11891/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -109204,8 +109051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11897/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11897/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11892/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11892/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -109213,8 +109060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11898/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11898/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11893/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  80%|▊| 11893/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -109222,8 +109069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11899/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11899/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  80%|▊| 11894/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  80%|▊| 11894/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109231,8 +109078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11900/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 11900/14932 [16:57<04:19, 11.69it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  80%|▊| 11895/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11895/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -109240,8 +109087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11901/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  80%|▊| 11901/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  80%|▊| 11896/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  80%|▊| 11896/14932 [16:54<04:19, 11.72it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -109249,8 +109096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11902/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  80%|▊| 11902/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  80%|▊| 11897/14932 [16:54<04:18, 11.72it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  80%|▊| 11897/14932 [16:54<04:18, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109258,8 +109105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11903/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  80%|▊| 11903/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=5.5"
+      "Epoch 0:  80%|▊| 11898/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11898/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -109267,8 +109114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11904/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=5.5\r",
-      "Epoch 0:  80%|▊| 11904/14932 [16:58<04:19, 11.69it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  80%|▊| 11899/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  80%|▊| 11899/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -109276,8 +109123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11905/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  80%|▊| 11905/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11900/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11900/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -109285,8 +109132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11906/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11906/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  80%|▊| 11901/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  80%|▊| 11901/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109294,8 +109141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11907/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  80%|▊| 11907/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 11902/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11902/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109303,8 +109150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11908/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 11908/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11903/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11903/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -109312,8 +109159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11909/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11909/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  80%|▊| 11904/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 11904/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -109321,8 +109168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11910/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  80%|▊| 11910/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11905/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11905/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -109330,8 +109177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11911/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11911/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11906/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  80%|▊| 11906/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -109339,8 +109186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11912/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11912/14932 [16:58<04:18, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11907/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  80%|▊| 11907/14932 [16:55<04:18, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109348,8 +109195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11913/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11913/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  80%|▊| 11908/14932 [16:55<04:17, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11908/14932 [16:55<04:17, 11.72it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -109357,8 +109204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11914/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  80%|▊| 11914/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11909/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  80%|▊| 11909/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109366,8 +109213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11915/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11915/14932 [16:59<04:18, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11910/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11910/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -109375,8 +109222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11916/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11916/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  80%|▊| 11911/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  80%|▊| 11911/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -109384,8 +109231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11917/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  80%|▊| 11917/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11912/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  80%|▊| 11912/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109393,8 +109240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11918/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11918/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11913/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11913/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -109402,8 +109249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11919/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11919/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  80%|▊| 11914/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  80%|▊| 11914/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -109411,8 +109258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11920/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  80%|▊| 11920/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11915/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11915/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109420,8 +109267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11921/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11921/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  80%|▊| 11916/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11916/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -109429,8 +109276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11922/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  80%|▊| 11922/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11917/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  80%|▊| 11917/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -109438,8 +109285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11923/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11923/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 11918/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11918/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109447,8 +109294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11924/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 11924/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  80%|▊| 11919/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11919/14932 [16:56<04:17, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109456,8 +109303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11925/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  80%|▊| 11925/14932 [16:59<04:17, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 11920/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11920/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -109465,8 +109312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11926/14932 [17:00<04:17, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 11926/14932 [17:00<04:17, 11.69it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  80%|▊| 11921/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  80%|▊| 11921/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109474,8 +109321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11927/14932 [17:00<04:17, 11.69it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  80%|▊| 11927/14932 [17:00<04:17, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11922/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11922/14932 [16:56<04:16, 11.72it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -109483,8 +109330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11928/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11928/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  80%|▊| 11923/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  80%|▊| 11923/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -109492,8 +109339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11929/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  80%|▊| 11929/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 11924/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  80%|▊| 11924/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -109501,8 +109348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11930/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 11930/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  80%|▊| 11925/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  80%|▊| 11925/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -109510,8 +109357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11931/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  80%|▊| 11931/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 11926/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 11926/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -109519,8 +109366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11932/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 11932/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  80%|▊| 11927/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  80%|▊| 11927/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -109528,8 +109375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11933/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  80%|▊| 11933/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  80%|▊| 11928/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  80%|▊| 11928/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109537,8 +109384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11934/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  80%|▊| 11934/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  80%|▊| 11929/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11929/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -109546,8 +109393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11935/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  80%|▊| 11935/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11930/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  80%|▊| 11930/14932 [16:57<04:16, 11.72it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -109555,8 +109402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11936/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11936/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  80%|▊| 11931/14932 [16:57<04:15, 11.72it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  80%|▊| 11931/14932 [16:57<04:15, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109564,8 +109411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11937/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11937/14932 [17:00<04:16, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11932/14932 [16:57<04:15, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11932/14932 [16:57<04:15, 11.72it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -109573,8 +109420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11938/14932 [17:01<04:16, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11938/14932 [17:01<04:16, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 11933/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  80%|▊| 11933/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -109582,8 +109429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11939/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 11939/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11934/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11934/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109591,8 +109438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11940/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11940/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11935/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11935/14932 [16:57<04:15, 11.73it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -109600,8 +109447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11941/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11941/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  80%|▊| 11936/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11936/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109609,8 +109456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11942/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  80%|▊| 11942/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  80%|▊| 11937/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11937/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109618,8 +109465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11943/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  80%|▊| 11943/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  80%|▊| 11938/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11938/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -109627,8 +109474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11944/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  80%|▊| 11944/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  80%|▊| 11939/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  80%|▊| 11939/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -109636,8 +109483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11945/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  80%|▊| 11945/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11940/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  80%|▊| 11940/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -109645,8 +109492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11946/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11946/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11941/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  80%|▊| 11941/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109654,8 +109501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11947/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11947/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  80%|▊| 11942/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11942/14932 [16:58<04:15, 11.72it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109663,8 +109510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11948/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11948/14932 [17:01<04:15, 11.69it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  80%|▊| 11943/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11943/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109672,8 +109519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11949/14932 [17:02<04:15, 11.69it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  80%|▊| 11949/14932 [17:02<04:15, 11.69it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11944/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11944/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -109681,8 +109528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11950/14932 [17:02<04:15, 11.69it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11950/14932 [17:02<04:15, 11.69it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  80%|▊| 11945/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  80%|▊| 11945/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -109690,8 +109537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11951/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  80%|▊| 11951/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11946/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11946/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109699,8 +109546,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11952/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11952/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  80%|▊| 11947/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109708,8 +109554,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11953/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  80%|▊| 11953/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  80%|▊| 11947/14932 [16:58<04:14, 11.72it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -109717,8 +109562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11954/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 11954/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  80%|▊| 11948/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11948/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109726,8 +109571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11955/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11955/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  80%|▊| 11949/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11949/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -109735,8 +109580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11956/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  80%|▊| 11956/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  80%|▊| 11950/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 11950/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109744,8 +109589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11957/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 11957/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 11951/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11951/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -109753,8 +109598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11958/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 11958/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  80%|▊| 11952/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  80%|▊| 11952/14932 [16:59<04:14, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -109762,8 +109607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11959/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  80%|▊| 11959/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  80%|▊| 11953/14932 [16:59<04:14, 11.73it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  80%|▊| 11953/14932 [16:59<04:14, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -109771,8 +109616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11960/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  80%|▊| 11960/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11954/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 11954/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -109780,8 +109625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11961/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11961/14932 [17:02<04:14, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11955/14932 [16:59<04:13, 11.72it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  80%|▊| 11955/14932 [16:59<04:13, 11.72it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -109789,8 +109634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11962/14932 [17:03<04:14, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11962/14932 [17:03<04:14, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11956/14932 [16:59<04:13, 11.72it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11956/14932 [16:59<04:13, 11.72it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109798,8 +109643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11963/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11963/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  80%|▊| 11957/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11957/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -109807,8 +109652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11964/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  80%|▊| 11964/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11958/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  80%|▊| 11958/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -109816,8 +109661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11965/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11965/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  80%|▊| 11959/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  80%|▊| 11959/14932 [16:59<04:13, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109825,8 +109670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11966/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  80%|▊| 11966/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  80%|▊| 11960/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11960/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -109834,8 +109679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11967/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  80%|▊| 11967/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 11961/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11961/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -109843,8 +109688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11968/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 11968/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11962/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11962/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -109852,8 +109697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11969/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11969/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 11963/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  80%|▊| 11963/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109861,8 +109706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11970/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 11970/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11964/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11964/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -109870,8 +109715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11971/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11971/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 11965/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  80%|▊| 11965/14932 [17:00<04:13, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -109879,8 +109724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11972/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 11972/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11966/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11966/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -109888,8 +109733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11973/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11973/14932 [17:03<04:13, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  80%|▊| 11967/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 11967/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -109897,8 +109742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11974/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  80%|▊| 11974/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11968/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  80%|▊| 11968/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -109906,8 +109751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11975/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11975/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  80%|▊| 11969/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  80%|▊| 11969/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -109915,8 +109760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11976/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  80%|▊| 11976/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  80%|▊| 11970/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  80%|▊| 11970/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -109924,8 +109769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11977/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  80%|▊| 11977/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  80%|▊| 11971/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  80%|▊| 11971/14932 [17:00<04:12, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -109933,8 +109778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11978/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  80%|▊| 11978/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  80%|▊| 11972/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  80%|▊| 11972/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -109942,8 +109787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11979/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  80%|▊| 11979/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11973/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11973/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -109951,8 +109796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11980/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11980/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11974/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  80%|▊| 11974/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109960,8 +109805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11981/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 11981/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11975/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11975/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109969,8 +109814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11982/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11982/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  80%|▊| 11976/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11976/14932 [17:01<04:12, 11.73it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -109978,8 +109823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11983/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  80%|▊| 11983/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11977/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11977/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -109987,8 +109832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11984/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11984/14932 [17:04<04:12, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11978/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 11978/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -109996,8 +109841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11985/14932 [17:04<04:11, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11985/14932 [17:04<04:11, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 11979/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 11979/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110005,8 +109850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11986/14932 [17:04<04:11, 11.69it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  80%|▊| 11986/14932 [17:04<04:11, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 11980/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11980/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110014,8 +109859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11987/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 11987/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11981/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11981/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -110023,8 +109868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11988/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11988/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  80%|▊| 11982/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 11982/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -110032,8 +109877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11989/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  80%|▊| 11989/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  80%|▊| 11983/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  80%|▊| 11983/14932 [17:01<04:11, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -110041,8 +109886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11990/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  80%|▊| 11990/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11984/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  80%|▊| 11984/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110050,8 +109895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11991/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 11991/14932 [17:05<04:11, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 11985/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 11985/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110059,8 +109904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11992/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 11992/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  80%|▊| 11986/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11986/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -110068,8 +109913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11993/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  80%|▊| 11993/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  80%|▊| 11987/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  80%|▊| 11987/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -110077,8 +109922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11994/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  80%|▊| 11994/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11988/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11988/14932 [17:02<04:11, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110086,8 +109931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11995/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11995/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  80%|▊| 11989/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11989/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110095,8 +109940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11996/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  80%|▊| 11996/14932 [17:05<04:11, 11.70it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  80%|▊| 11990/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 11990/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -110104,8 +109949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11997/14932 [17:05<04:10, 11.70it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  80%|▊| 11997/14932 [17:05<04:10, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 11991/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  80%|▊| 11991/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -110113,8 +109958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11998/14932 [17:05<04:10, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 11998/14932 [17:05<04:10, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  80%|▊| 11992/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  80%|▊| 11992/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110122,8 +109967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 11999/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  80%|▊| 11999/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  80%|▊| 11993/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  80%|▊| 11993/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -110131,8 +109976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12000/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  80%|▊| 12000/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  80%|▊| 11994/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  80%|▊| 11994/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -110140,8 +109985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12001/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  80%|▊| 12001/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  80%|▊| 11995/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  80%|▊| 11995/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -110149,8 +109994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12002/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  80%|▊| 12002/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  80%|▊| 11996/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  80%|▊| 11996/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -110158,8 +110003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12003/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  80%|▊| 12003/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 11997/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  80%|▊| 11997/14932 [17:02<04:10, 11.73it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -110167,8 +110012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12004/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 12004/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  80%|▊| 11998/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  80%|▊| 11998/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110176,8 +110021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12005/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  80%|▊| 12005/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  80%|▊| 11999/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 11999/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -110185,8 +110030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12006/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  80%|▊| 12006/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 12000/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  80%|▊| 12000/14932 [17:03<04:10, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110194,8 +110039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12007/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 12007/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  80%|▊| 12001/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 12001/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -110203,8 +110048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12008/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  80%|▊| 12008/14932 [17:06<04:10, 11.69it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 12002/14932 [17:03<04:09, 11.72it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  80%|▊| 12002/14932 [17:03<04:09, 11.72it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -110212,8 +110057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12009/14932 [17:06<04:09, 11.69it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  80%|▊| 12009/14932 [17:06<04:09, 11.69it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  80%|▊| 12003/14932 [17:03<04:09, 11.72it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  80%|▊| 12003/14932 [17:03<04:09, 11.72it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -110221,8 +110066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12010/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  80%|▊| 12010/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  80%|▊| 12004/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 12004/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110230,8 +110075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12011/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  80%|▊| 12011/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  80%|▊| 12005/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 12005/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -110239,8 +110084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12012/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  80%|▊| 12012/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  80%|▊| 12006/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  80%|▊| 12006/14932 [17:03<04:09, 11.73it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -110248,8 +110093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12013/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  80%|▊| 12013/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  80%|▊| 12007/14932 [17:04<04:09, 11.72it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  80%|▊| 12007/14932 [17:04<04:09, 11.72it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -110257,8 +110102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12014/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  80%|▊| 12014/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  80%|▊| 12008/14932 [17:04<04:09, 11.72it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  80%|▊| 12008/14932 [17:04<04:09, 11.72it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -110266,8 +110111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12015/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  80%|▊| 12015/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 12009/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  80%|▊| 12009/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -110275,7 +110120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12016/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 12010/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  80%|▊| 12010/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -110283,7 +110129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12016/14932 [17:07<04:09, 11.69it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  80%|▊| 12011/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  80%|▊| 12011/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110291,8 +110138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12017/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  80%|▊| 12017/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  80%|▊| 12012/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  80%|▊| 12012/14932 [17:04<04:09, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110300,8 +110147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12018/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  80%|▊| 12018/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  80%|▊| 12013/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  80%|▊| 12013/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -110309,8 +110156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12019/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  80%|▊| 12019/14932 [17:07<04:09, 11.70it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  80%|▊| 12014/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  80%|▊| 12014/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -110318,8 +110165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  80%|▊| 12020/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  80%|▊| 12020/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  80%|▊| 12015/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  80%|▊| 12015/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -110327,8 +110174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12021/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  81%|▊| 12021/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  80%|▊| 12016/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  80%|▊| 12016/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -110336,8 +110183,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12022/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12022/14932 [17:07<04:08, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  80%|▊| 12017/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -110345,8 +110191,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12023/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12023/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  80%|▊| 12017/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110354,8 +110199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12024/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  81%|▊| 12024/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  80%|▊| 12018/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 12018/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110363,8 +110208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12025/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12025/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  80%|▊| 12019/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  80%|▊| 12019/14932 [17:04<04:08, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -110372,8 +110217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12026/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12026/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  80%|▊| 12020/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  80%|▊| 12020/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110381,8 +110226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12027/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  81%|▊| 12027/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12021/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12021/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -110390,8 +110235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12028/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12028/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12022/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12022/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -110399,8 +110244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12029/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12029/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  81%|▊| 12023/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  81%|▊| 12023/14932 [17:05<04:08, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -110408,8 +110253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12030/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  81%|▊| 12030/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  81%|▊| 12024/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  81%|▊| 12024/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -110417,8 +110262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12031/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  81%|▊| 12031/14932 [17:08<04:08, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12025/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12025/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -110426,8 +110271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12032/14932 [17:08<04:07, 11.69it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12032/14932 [17:08<04:07, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  81%|▊| 12026/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12026/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -110435,8 +110280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12033/14932 [17:08<04:07, 11.70it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  81%|▊| 12033/14932 [17:08<04:07, 11.70it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  81%|▊| 12027/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  81%|▊| 12027/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110444,8 +110289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12034/14932 [17:08<04:07, 11.70it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  81%|▊| 12034/14932 [17:08<04:07, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  81%|▊| 12028/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  81%|▊| 12028/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -110453,8 +110298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12035/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  81%|▊| 12035/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12029/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  81%|▊| 12029/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -110462,8 +110307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12036/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12036/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12030/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  81%|▊| 12030/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -110471,8 +110316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12037/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12037/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12031/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12031/14932 [17:05<04:07, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110480,7 +110325,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12038/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12032/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110488,7 +110333,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12038/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12032/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110496,8 +110341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12039/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12039/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  81%|▊| 12033/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  81%|▊| 12033/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -110505,8 +110350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12040/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  81%|▊| 12040/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12034/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12034/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -110514,8 +110359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12041/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12041/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  81%|▊| 12035/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12035/14932 [17:06<04:07, 11.73it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -110523,8 +110368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12042/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  81%|▊| 12042/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  81%|▊| 12036/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  81%|▊| 12036/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -110532,8 +110377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12043/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  81%|▊| 12043/14932 [17:09<04:07, 11.70it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  81%|▊| 12037/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  81%|▊| 12037/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -110541,8 +110386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12044/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  81%|▊| 12044/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  81%|▊| 12038/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  81%|▊| 12038/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110550,8 +110395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12045/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12045/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  81%|▊| 12039/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12039/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -110559,8 +110404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12046/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  81%|▊| 12046/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12040/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12040/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -110568,8 +110413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12047/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12047/14932 [17:09<04:06, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  81%|▊| 12041/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  81%|▊| 12041/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -110577,8 +110422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12048/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  81%|▊| 12048/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12042/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12042/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -110586,8 +110431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12049/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12049/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12043/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12043/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -110595,8 +110440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12050/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12050/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  81%|▊| 12044/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  81%|▊| 12044/14932 [17:06<04:06, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -110604,8 +110449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12051/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  81%|▊| 12051/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  81%|▊| 12045/14932 [17:07<04:06, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  81%|▊| 12045/14932 [17:07<04:06, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110613,8 +110458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12052/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  81%|▊| 12052/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  81%|▊| 12046/14932 [17:07<04:06, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12046/14932 [17:07<04:06, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -110622,7 +110467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12053/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  81%|▊| 12047/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  81%|▊| 12047/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110630,7 +110476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12053/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  81%|▊| 12048/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12048/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110638,8 +110485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12054/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  81%|▊| 12054/14932 [17:10<04:06, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12049/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12049/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -110647,8 +110494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12055/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  81%|▊| 12055/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  81%|▊| 12050/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12050/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -110656,8 +110503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12056/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  81%|▊| 12056/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12051/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  81%|▊| 12051/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -110665,8 +110512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12057/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12057/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  81%|▊| 12052/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12052/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -110674,8 +110521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12058/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  81%|▊| 12058/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12053/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12053/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -110683,8 +110530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12059/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12059/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12054/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12054/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110692,8 +110539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12060/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12060/14932 [17:10<04:05, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12055/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12055/14932 [17:07<04:05, 11.73it/s, v_num=ui8w, train/loss=4.7"
      ]
     },
     {
@@ -110701,8 +110548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12061/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12061/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12056/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=4.7\r",
+      "Epoch 0:  81%|▊| 12056/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110710,8 +110557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12062/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  81%|▊| 12062/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12057/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12057/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110719,8 +110566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12063/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12063/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  81%|▊| 12058/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  81%|▊| 12058/14932 [17:08<04:05, 11.73it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -110728,8 +110575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12064/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  81%|▊| 12064/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12059/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  81%|▊| 12059/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -110737,8 +110584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12065/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12065/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  81%|▊| 12060/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  81%|▊| 12060/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110746,8 +110593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12066/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  81%|▊| 12066/14932 [17:11<04:05, 11.70it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  81%|▊| 12061/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12061/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -110755,8 +110602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12067/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  81%|▊| 12067/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12062/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12062/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -110764,8 +110611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12068/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12068/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  81%|▊| 12063/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  81%|▊| 12063/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -110773,8 +110620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12069/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  81%|▊| 12069/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  81%|▊| 12064/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  81%|▊| 12064/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -110782,8 +110629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12070/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  81%|▊| 12070/14932 [17:11<04:04, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12065/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  81%|▊| 12065/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110791,8 +110638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12071/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12071/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12066/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12066/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -110800,8 +110647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12072/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12072/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  81%|▊| 12067/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  81%|▊| 12067/14932 [17:08<04:04, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -110809,8 +110656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12073/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  81%|▊| 12073/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12068/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12068/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110818,8 +110665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12074/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12074/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  81%|▊| 12069/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12069/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -110827,8 +110674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12075/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  81%|▊| 12075/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12070/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12070/14932 [17:09<04:04, 11.73it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -110836,8 +110683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12076/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12076/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12071/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  81%|▊| 12071/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -110845,8 +110692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12077/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12077/14932 [17:12<04:04, 11.70it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  81%|▊| 12072/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12072/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -110854,8 +110701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12078/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  81%|▊| 12078/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12073/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12073/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110863,8 +110710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12079/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12079/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  81%|▊| 12074/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12074/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -110872,8 +110719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12080/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  81%|▊| 12080/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12075/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12075/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -110881,8 +110728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12081/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12081/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12076/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12076/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -110890,8 +110737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12082/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12082/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12077/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12077/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110899,8 +110746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12083/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12083/14932 [17:12<04:03, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12078/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12078/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -110908,8 +110755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12084/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12084/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12079/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12079/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -110917,8 +110764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12085/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12085/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12080/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12080/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110926,8 +110773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12086/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12086/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  81%|▊| 12081/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12081/14932 [17:09<04:03, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -110935,8 +110782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12087/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  81%|▊| 12087/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12082/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12082/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -110944,8 +110791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12088/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  81%|▊| 12088/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  81%|▊| 12083/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12083/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -110953,8 +110800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12089/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  81%|▊| 12089/14932 [17:13<04:03, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12084/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12084/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -110962,8 +110809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12090/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12090/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12085/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12085/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -110971,8 +110818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12091/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12091/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12086/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12086/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -110980,8 +110827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12092/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12092/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12087/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  81%|▊| 12087/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -110989,8 +110836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12093/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12093/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12088/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  81%|▊| 12088/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -110998,8 +110845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12094/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12094/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  81%|▊| 12089/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  81%|▊| 12089/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -111007,8 +110854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12095/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12095/14932 [17:13<04:02, 11.70it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  81%|▊| 12090/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  81%|▊| 12090/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -111016,8 +110863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12096/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  81%|▊| 12096/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12091/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12091/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -111025,8 +110872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12097/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12097/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  81%|▊| 12092/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12092/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -111034,8 +110881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12098/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  81%|▊| 12098/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12093/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  81%|▊| 12093/14932 [17:10<04:02, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111043,8 +110890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12099/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12099/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12094/14932 [17:10<04:01, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12094/14932 [17:10<04:01, 11.73it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -111052,8 +110899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12100/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12100/14932 [17:14<04:02, 11.70it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  81%|▊| 12095/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  81%|▊| 12095/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -111061,8 +110908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12101/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  81%|▊| 12101/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12096/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12096/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111070,8 +110917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12102/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  81%|▊| 12102/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  81%|▊| 12097/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12097/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -111079,8 +110926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12103/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  81%|▊| 12103/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  81%|▊| 12098/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12098/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -111088,8 +110935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12104/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  81%|▊| 12104/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12099/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12099/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -111097,8 +110944,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12105/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12105/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12100/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  81%|▊| 12100/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -111106,8 +110953,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12106/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12106/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  81%|▊| 12101/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12101/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111115,8 +110962,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12107/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  81%|▊| 12107/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  81%|▊| 12102/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12102/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -111124,8 +110971,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12108/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  81%|▊| 12108/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12103/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12103/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111133,8 +110980,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12109/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12109/14932 [17:14<04:01, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12104/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12104/14932 [17:11<04:01, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111142,8 +110989,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12110/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12110/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  81%|▊| 12105/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12105/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111151,8 +110998,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12111/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  81%|▊| 12111/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  81%|▊| 12106/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12106/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -111160,8 +111007,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12112/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  81%|▊| 12112/14932 [17:15<04:01, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12107/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12107/14932 [17:11<04:00, 11.73it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -111169,8 +111016,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12113/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12113/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12108/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  81%|▊| 12108/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111178,8 +111025,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12114/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12114/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  81%|▊| 12109/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12109/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111187,8 +111034,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12115/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  81%|▊| 12115/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  81%|▊| 12110/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12110/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -111196,8 +111043,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12116/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  81%|▊| 12116/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  81%|▊| 12111/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12111/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -111205,8 +111052,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12117/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  81%|▊| 12117/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  81%|▊| 12112/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  81%|▊| 12112/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -111214,8 +111061,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12118/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12118/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  81%|▊| 12113/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  81%|▊| 12113/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -111223,8 +111070,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12119/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  81%|▊| 12119/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  81%|▊| 12114/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  81%|▊| 12114/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111232,8 +111079,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12120/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  81%|▊| 12120/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12115/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12115/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111241,8 +111088,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12121/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12121/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  81%|▊| 12116/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12116/14932 [17:12<04:00, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111250,8 +111097,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12122/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  81%|▊| 12122/14932 [17:15<04:00, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  81%|▊| 12117/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12117/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111259,8 +111106,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12123/14932 [17:16<04:00, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  81%|▊| 12123/14932 [17:16<04:00, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  81%|▊| 12118/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12118/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111268,8 +111115,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12124/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  81%|▊| 12124/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12119/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12119/14932 [17:12<03:59, 11.73it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -111277,8 +111124,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12125/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12125/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12120/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  81%|▊| 12120/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -111286,8 +111133,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12126/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12126/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12121/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  81%|▊| 12121/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -111295,8 +111142,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12127/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12127/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  81%|▊| 12122/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12122/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -111304,8 +111151,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12128/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  81%|▊| 12128/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12123/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  81%|▊| 12123/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -111313,8 +111160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12129/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12129/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  81%|▊| 12124/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  81%|▊| 12124/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -111322,8 +111169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12130/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  81%|▊| 12130/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12125/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12125/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111331,8 +111178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12131/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  81%|▊| 12131/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12126/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12126/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -111340,8 +111187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12132/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12132/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  81%|▊| 12127/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12127/14932 [17:13<03:59, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -111349,8 +111196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12133/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  81%|▊| 12133/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  81%|▊| 12128/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12128/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -111358,8 +111205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12134/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  81%|▊| 12134/14932 [17:16<03:59, 11.70it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  81%|▊| 12129/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  81%|▊| 12129/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -111367,8 +111214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12135/14932 [17:17<03:59, 11.70it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  81%|▊| 12135/14932 [17:17<03:59, 11.70it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  81%|▊| 12130/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  81%|▊| 12130/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111376,8 +111223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12136/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  81%|▊| 12136/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  81%|▊| 12131/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12131/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -111385,8 +111232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12137/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  81%|▊| 12137/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12132/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  81%|▊| 12132/14932 [17:13<03:58, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111394,8 +111241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12138/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12138/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12133/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12133/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111403,8 +111250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12139/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12139/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  81%|▊| 12134/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12134/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111412,8 +111259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12140/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  81%|▊| 12140/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  81%|▊| 12135/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12135/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -111421,8 +111268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12141/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12141/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  81%|▊| 12136/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12136/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -111430,8 +111277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12142/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  81%|▊| 12142/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12137/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12137/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111439,8 +111286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12143/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12143/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  81%|▊| 12138/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12138/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111448,8 +111295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12144/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  81%|▊| 12144/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12139/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12139/14932 [17:14<03:58, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111457,8 +111304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12145/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12145/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12140/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12140/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -111466,7 +111313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12146/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  81%|▊| 12141/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  81%|▊| 12141/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111474,7 +111322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12146/14932 [17:17<03:58, 11.70it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  81%|▊| 12142/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12142/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111482,8 +111331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12147/14932 [17:17<03:57, 11.70it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  81%|▊| 12147/14932 [17:17<03:57, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12143/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12143/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111491,8 +111340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12148/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12148/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  81%|▊| 12144/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12144/14932 [17:14<03:57, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111500,8 +111349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12149/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  81%|▊| 12149/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12145/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  81%|▊| 12145/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111509,8 +111358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12150/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  81%|▊| 12150/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  81%|▊| 12146/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12146/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -111518,8 +111367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12151/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  81%|▊| 12151/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  81%|▊| 12147/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12147/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -111527,8 +111376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12152/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  81%|▊| 12152/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12148/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12148/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -111536,8 +111385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12153/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12153/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  81%|▊| 12149/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  81%|▊| 12149/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -111545,8 +111394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12154/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  81%|▊| 12154/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  81%|▊| 12150/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  81%|▊| 12150/14932 [17:15<03:57, 11.73it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -111554,8 +111403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12155/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  81%|▊| 12155/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  81%|▊| 12151/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  81%|▊| 12151/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111563,8 +111412,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12156/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  81%|▊| 12156/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12152/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111572,8 +111420,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12157/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12157/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  81%|▊| 12152/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111581,8 +111428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12158/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  81%|▊| 12158/14932 [17:18<03:57, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  81%|▊| 12153/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  81%|▊| 12153/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111590,8 +111437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12159/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  81%|▊| 12159/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  81%|▊| 12154/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12154/14932 [17:15<03:56, 11.73it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -111599,8 +111446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12160/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  81%|▊| 12160/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  81%|▊| 12155/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  81%|▊| 12155/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -111608,8 +111455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12161/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  81%|▊| 12161/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  81%|▊| 12156/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  81%|▊| 12156/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -111617,8 +111464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12162/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  81%|▊| 12162/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  81%|▊| 12157/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  81%|▊| 12157/14932 [17:15<03:56, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -111626,8 +111473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12163/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  81%|▊| 12163/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  81%|▊| 12158/14932 [17:16<03:56, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12158/14932 [17:16<03:56, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -111635,8 +111482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12164/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  81%|▊| 12164/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  81%|▊| 12159/14932 [17:16<03:56, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  81%|▊| 12159/14932 [17:16<03:56, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111644,8 +111491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12165/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  81%|▊| 12165/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  81%|▊| 12160/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  81%|▊| 12160/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111653,8 +111500,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12166/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  81%|▊| 12166/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  81%|▊| 12161/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -111662,8 +111508,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12167/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  81%|▊| 12167/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  81%|▊| 12161/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -111671,7 +111516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12168/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  81%|▊| 12162/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  81%|▊| 12162/14932 [17:16<03:56, 11.73it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111679,7 +111525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12168/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12163/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  81%|▊| 12163/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -111687,8 +111534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  81%|▊| 12169/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  81%|▊| 12169/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  81%|▊| 12164/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  81%|▊| 12164/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -111696,8 +111543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12170/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  82%|▊| 12170/14932 [17:19<03:56, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  81%|▊| 12165/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12165/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111705,8 +111552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12171/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12171/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  81%|▊| 12166/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  81%|▊| 12166/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -111714,8 +111561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12172/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12172/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  81%|▊| 12167/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  81%|▊| 12167/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -111723,8 +111570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12173/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12173/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  81%|▊| 12168/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  81%|▊| 12168/14932 [17:16<03:55, 11.73it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -111732,8 +111579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12174/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  82%|▊| 12174/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  81%|▊| 12169/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  81%|▊| 12169/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -111741,8 +111588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12175/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12175/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  82%|▊| 12170/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12170/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111750,8 +111597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12176/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  82%|▊| 12176/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12171/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  82%|▊| 12171/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -111759,8 +111606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12177/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12177/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  82%|▊| 12172/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  82%|▊| 12172/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111768,8 +111615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12178/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  82%|▊| 12178/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12173/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12173/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -111777,8 +111624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12179/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12179/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  82%|▊| 12174/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12174/14932 [17:17<03:55, 11.73it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -111786,8 +111633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12180/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  82%|▊| 12180/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12175/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12175/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -111795,8 +111642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12181/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12181/14932 [17:20<03:55, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12176/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  82%|▊| 12176/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111804,8 +111651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12182/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12182/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  82%|▊| 12177/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12177/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -111813,8 +111660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12183/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  82%|▊| 12183/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12178/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12178/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -111822,8 +111669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12184/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12184/14932 [17:20<03:54, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12179/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12179/14932 [17:17<03:54, 11.73it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111831,8 +111678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12185/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  82%|▊| 12185/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12180/14932 [17:17<03:54, 11.74it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  82%|▊| 12180/14932 [17:17<03:54, 11.74it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -111840,8 +111687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12186/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12186/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12181/14932 [17:17<03:54, 11.74it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12181/14932 [17:17<03:54, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111849,8 +111696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12187/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  82%|▊| 12187/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12182/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12182/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111858,8 +111705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12188/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12188/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12183/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  82%|▊| 12183/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -111867,8 +111714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12189/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12189/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  82%|▊| 12184/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12184/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -111876,8 +111723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12190/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  82%|▊| 12190/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12185/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12185/14932 [17:18<03:54, 11.74it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -111885,8 +111732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12191/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12191/14932 [17:21<03:54, 11.71it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  82%|▊| 12186/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  82%|▊| 12186/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -111894,8 +111741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12192/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  82%|▊| 12192/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12187/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  82%|▊| 12187/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111903,8 +111750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12193/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  82%|▊| 12193/14932 [17:21<03:54, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12188/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12188/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -111912,8 +111759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12194/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12194/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  82%|▊| 12189/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  82%|▊| 12189/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -111921,8 +111768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12195/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  82%|▊| 12195/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12190/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12190/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -111930,8 +111777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12196/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12196/14932 [17:21<03:53, 11.70it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  82%|▊| 12191/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12191/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -111939,8 +111786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12197/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  82%|▊| 12197/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12192/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12192/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -111948,8 +111795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12198/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12198/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12193/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12193/14932 [17:18<03:53, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -111957,8 +111804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12199/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12199/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12194/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12194/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -111966,7 +111813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12200/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12195/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12195/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -111974,7 +111822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12200/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12196/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  82%|▊| 12196/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -111982,8 +111831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12201/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12201/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  82%|▊| 12197/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  82%|▊| 12197/14932 [17:19<03:53, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -111991,8 +111840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12202/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  82%|▊| 12202/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  82%|▊| 12198/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12198/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112000,8 +111849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12203/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  82%|▊| 12203/14932 [17:22<03:53, 11.70it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  82%|▊| 12199/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12199/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -112009,8 +111858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12204/14932 [17:22<03:53, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  82%|▊| 12204/14932 [17:22<03:53, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12200/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  82%|▊| 12200/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -112018,8 +111867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12205/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  82%|▊| 12205/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12201/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  82%|▊| 12201/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112027,8 +111876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12206/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12206/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  82%|▊| 12202/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12202/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112036,8 +111885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12207/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  82%|▊| 12207/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  82%|▊| 12203/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12203/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=5.7"
      ]
     },
     {
@@ -112045,8 +111894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12208/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  82%|▊| 12208/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  82%|▊| 12204/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=5.7\r",
+      "Epoch 0:  82%|▊| 12204/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -112054,8 +111903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12209/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  82%|▊| 12209/14932 [17:22<03:52, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12205/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  82%|▊| 12205/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112063,8 +111912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12210/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12210/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  82%|▊| 12206/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12206/14932 [17:19<03:52, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -112072,8 +111921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12211/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  82%|▊| 12211/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12207/14932 [17:20<03:52, 11.74it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12207/14932 [17:20<03:52, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112081,8 +111930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12212/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12212/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12208/14932 [17:20<03:52, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12208/14932 [17:20<03:52, 11.74it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -112090,8 +111939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12213/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12213/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  82%|▊| 12209/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  82%|▊| 12209/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112099,8 +111948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12214/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  82%|▊| 12214/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  82%|▊| 12210/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12210/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112108,8 +111957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12215/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  82%|▊| 12215/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12211/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12211/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -112117,8 +111966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12216/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12216/14932 [17:23<03:52, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12212/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  82%|▊| 12212/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -112126,8 +111975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12217/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12217/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12213/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  82%|▊| 12213/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -112135,8 +111984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12218/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12218/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  82%|▊| 12214/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12214/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112144,8 +111993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12219/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  82%|▊| 12219/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  82%|▊| 12215/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12215/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112153,8 +112002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12220/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  82%|▊| 12220/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  82%|▊| 12216/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12216/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112162,8 +112011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12221/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  82%|▊| 12221/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  82%|▊| 12217/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12217/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -112171,8 +112020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12222/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  82%|▊| 12222/14932 [17:23<03:51, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12218/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12218/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -112180,7 +112029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12223/14932 [17:24<03:51, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12219/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  82%|▊| 12219/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112188,7 +112038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12223/14932 [17:24<03:51, 11.71it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  82%|▊| 12220/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12220/14932 [17:20<03:51, 11.74it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -112196,8 +112047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12224/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  82%|▊| 12224/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12221/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12221/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112205,8 +112056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12225/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12225/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12222/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12222/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112214,8 +112065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12226/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12226/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12223/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12223/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112223,8 +112074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12227/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12227/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12224/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12224/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -112232,8 +112083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12228/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12228/14932 [17:24<03:51, 11.70it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12225/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12225/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -112241,8 +112092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12229/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  82%|▊| 12229/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  82%|▊| 12226/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  82%|▊| 12226/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -112250,8 +112101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12230/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  82%|▊| 12230/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  82%|▊| 12227/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  82%|▊| 12227/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -112259,8 +112110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12231/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  82%|▊| 12231/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  82%|▊| 12228/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  82%|▊| 12228/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -112268,8 +112119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12232/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  82%|▊| 12232/14932 [17:24<03:50, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12229/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  82%|▊| 12229/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -112277,8 +112128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12233/14932 [17:25<03:50, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12233/14932 [17:25<03:50, 11.70it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  82%|▊| 12230/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  82%|▊| 12230/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -112286,8 +112137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12234/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  82%|▊| 12234/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12231/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  82%|▊| 12231/14932 [17:21<03:50, 11.74it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -112295,8 +112146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12235/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12235/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  82%|▊| 12232/14932 [17:22<03:50, 11.74it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  82%|▊| 12232/14932 [17:22<03:50, 11.74it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -112304,8 +112155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12236/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  82%|▊| 12236/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  82%|▊| 12233/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  82%|▊| 12233/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112313,8 +112164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12237/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  82%|▊| 12237/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12234/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12234/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112322,8 +112173,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12238/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12238/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12235/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112331,8 +112181,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12239/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12239/14932 [17:25<03:50, 11.71it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  82%|▊| 12235/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112340,8 +112189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12240/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  82%|▊| 12240/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  82%|▊| 12236/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12236/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112349,8 +112198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12241/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  82%|▊| 12241/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  82%|▊| 12237/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12237/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -112358,8 +112207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12242/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  82%|▊| 12242/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  82%|▊| 12238/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  82%|▊| 12238/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112367,8 +112216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12243/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  82%|▊| 12243/14932 [17:25<03:49, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  82%|▊| 12239/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12239/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112376,8 +112225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12244/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  82%|▊| 12244/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  82%|▊| 12240/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12240/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -112385,8 +112234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12245/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  82%|▊| 12245/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  82%|▊| 12241/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  82%|▊| 12241/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -112394,8 +112243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12246/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  82%|▊| 12246/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  82%|▊| 12242/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12242/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112403,8 +112252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12247/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  82%|▊| 12247/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12243/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12243/14932 [17:22<03:49, 11.74it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -112412,8 +112261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12248/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12248/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12244/14932 [17:22<03:48, 11.74it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  82%|▊| 12244/14932 [17:22<03:48, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112421,8 +112270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12249/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12249/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12245/14932 [17:22<03:48, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12245/14932 [17:22<03:48, 11.74it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -112430,8 +112279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12250/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12250/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  82%|▊| 12246/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  82%|▊| 12246/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112439,8 +112288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12251/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  82%|▊| 12251/14932 [17:26<03:49, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12247/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12247/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -112448,8 +112297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12252/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12252/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12248/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  82%|▊| 12248/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -112457,8 +112306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12253/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12253/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  82%|▊| 12249/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12249/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -112466,8 +112315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12254/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  82%|▊| 12254/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  82%|▊| 12250/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  82%|▊| 12250/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112475,8 +112324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12255/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  82%|▊| 12255/14932 [17:26<03:48, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12251/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12251/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -112484,8 +112333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12256/14932 [17:27<03:48, 11.70it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12256/14932 [17:27<03:48, 11.70it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  82%|▊| 12252/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  82%|▊| 12252/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -112493,8 +112342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12257/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  82%|▊| 12257/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12253/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  82%|▊| 12253/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -112502,8 +112351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12258/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12258/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  82%|▊| 12254/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12254/14932 [17:23<03:48, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112511,8 +112360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12259/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  82%|▊| 12259/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  82%|▊| 12255/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12255/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=4.8"
      ]
     },
     {
@@ -112520,8 +112369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12260/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  82%|▊| 12260/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12256/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=4.8\r",
+      "Epoch 0:  82%|▊| 12256/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -112529,8 +112378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12261/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12261/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12257/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  82%|▊| 12257/14932 [17:23<03:47, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -112538,8 +112387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12262/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12262/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12258/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  82%|▊| 12258/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112547,8 +112396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12263/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12263/14932 [17:27<03:48, 11.71it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  82%|▊| 12259/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12259/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112556,8 +112405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12264/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  82%|▊| 12264/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12260/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12260/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112565,8 +112414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12265/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12265/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  82%|▊| 12261/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12261/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112574,8 +112423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12266/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  82%|▊| 12266/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12262/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12262/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -112583,8 +112432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12267/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12267/14932 [17:27<03:47, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  82%|▊| 12263/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  82%|▊| 12263/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112592,8 +112441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12268/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  82%|▊| 12268/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  82%|▊| 12264/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12264/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -112601,8 +112450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12269/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  82%|▊| 12269/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12265/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12265/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112610,8 +112459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12270/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12270/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  82%|▊| 12266/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12266/14932 [17:24<03:47, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112619,8 +112468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12271/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  82%|▊| 12271/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12267/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12267/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112628,8 +112477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12272/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12272/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  82%|▊| 12268/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12268/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -112637,8 +112486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12273/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  82%|▊| 12273/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  82%|▊| 12269/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12269/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -112646,8 +112495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12274/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  82%|▊| 12274/14932 [17:28<03:47, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12270/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  82%|▊| 12270/14932 [17:24<03:46, 11.74it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -112655,8 +112504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12275/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12275/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12271/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  82%|▊| 12271/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -112664,8 +112513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12276/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  82%|▊| 12276/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  82%|▊| 12272/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  82%|▊| 12272/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112673,8 +112522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12277/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  82%|▊| 12277/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  82%|▊| 12273/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12273/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -112682,8 +112531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12278/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  82%|▊| 12278/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  82%|▊| 12274/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  82%|▊| 12274/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -112691,8 +112540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12279/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  82%|▊| 12279/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12275/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  82%|▊| 12275/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112700,8 +112549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12280/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  82%|▊| 12280/14932 [17:28<03:46, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12276/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12276/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -112709,8 +112558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12281/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12281/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12277/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  82%|▊| 12277/14932 [17:25<03:46, 11.74it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -112718,8 +112567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12282/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12282/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12278/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12278/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -112727,8 +112576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12283/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12283/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12279/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12279/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -112736,8 +112585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12284/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  82%|▊| 12284/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  82%|▊| 12280/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  82%|▊| 12280/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -112745,8 +112594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12285/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  82%|▊| 12285/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  82%|▊| 12281/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  82%|▊| 12281/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -112754,8 +112603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12286/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  82%|▊| 12286/14932 [17:29<03:46, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12282/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  82%|▊| 12282/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -112763,8 +112612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12287/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12287/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  82%|▊| 12283/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  82%|▊| 12283/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -112772,8 +112621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12288/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  82%|▊| 12288/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  82%|▊| 12284/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12284/14932 [17:25<03:45, 11.74it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -112781,8 +112630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12289/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  82%|▊| 12289/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  82%|▊| 12285/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  82%|▊| 12285/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112790,8 +112639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12290/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  82%|▊| 12290/14932 [17:29<03:45, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12286/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12286/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112799,8 +112648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12291/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12291/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12287/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12287/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112808,8 +112657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12292/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12292/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12288/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12288/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -112817,8 +112666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12293/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12293/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12289/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  82%|▊| 12289/14932 [17:26<03:45, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112826,8 +112675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12294/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12294/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  82%|▊| 12290/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12290/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112835,8 +112684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12295/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  82%|▊| 12295/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12291/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12291/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112844,8 +112693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12296/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12296/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  82%|▊| 12292/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12292/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -112853,8 +112702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12297/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  82%|▊| 12297/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12293/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  82%|▊| 12293/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -112862,8 +112711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12298/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12298/14932 [17:30<03:45, 11.71it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  82%|▊| 12294/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  82%|▊| 12294/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -112871,8 +112720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12299/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  82%|▊| 12299/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  82%|▊| 12295/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  82%|▊| 12295/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -112880,8 +112729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12300/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  82%|▊| 12300/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12296/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  82%|▊| 12296/14932 [17:26<03:44, 11.74it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -112889,8 +112738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12301/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12301/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12297/14932 [17:27<03:44, 11.74it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  82%|▊| 12297/14932 [17:27<03:44, 11.74it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -112898,8 +112747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12302/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12302/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12298/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  82%|▊| 12298/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -112907,8 +112756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12303/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  82%|▊| 12303/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12299/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  82%|▊| 12299/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -112916,8 +112765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12304/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12304/14932 [17:30<03:44, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  82%|▊| 12300/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  82%|▊| 12300/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112925,8 +112774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12305/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  82%|▊| 12305/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12301/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12301/14932 [17:27<03:44, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -112934,8 +112783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12306/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12306/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12302/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  82%|▊| 12302/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112943,8 +112792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12307/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  82%|▊| 12307/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  82%|▊| 12303/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12303/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -112952,8 +112801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12308/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  82%|▊| 12308/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  82%|▊| 12304/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  82%|▊| 12304/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -112961,8 +112810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12309/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  82%|▊| 12309/14932 [17:31<03:44, 11.71it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  82%|▊| 12305/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  82%|▊| 12305/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -112970,8 +112819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12310/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  82%|▊| 12310/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  82%|▊| 12306/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  82%|▊| 12306/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -112979,8 +112828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12311/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  82%|▊| 12311/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  82%|▊| 12307/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12307/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -112988,8 +112837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12312/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  82%|▊| 12312/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  82%|▊| 12308/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12308/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -112997,8 +112846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12313/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  82%|▊| 12313/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12309/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  82%|▊| 12309/14932 [17:27<03:43, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -113006,8 +112855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12314/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  82%|▊| 12314/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  82%|▊| 12310/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  82%|▊| 12310/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113015,8 +112864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12315/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  82%|▊| 12315/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  82%|▊| 12311/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12311/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113024,8 +112873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12316/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  82%|▊| 12316/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  82%|▊| 12312/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  82%|▊| 12312/14932 [17:28<03:43, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -113033,8 +112882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12317/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  82%|▊| 12317/14932 [17:31<03:43, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  82%|▊| 12313/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  82%|▊| 12313/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -113042,8 +112891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  82%|▊| 12318/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  82%|▊| 12318/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  82%|▊| 12314/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  82%|▊| 12314/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -113051,8 +112900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12319/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  83%|▊| 12319/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  82%|▊| 12315/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  82%|▊| 12315/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -113060,8 +112909,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12320/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12320/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  82%|▊| 12316/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -113069,8 +112917,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12321/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  83%|▊| 12321/14932 [17:32<03:43, 11.71it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  82%|▊| 12316/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -113078,8 +112925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12322/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  83%|▊| 12322/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  82%|▊| 12317/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  82%|▊| 12317/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113087,8 +112934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12323/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12323/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  82%|▊| 12318/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  82%|▊| 12318/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -113096,8 +112943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12324/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12324/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12319/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12319/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113105,8 +112952,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12325/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12325/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12320/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  83%|▊| 12320/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -113114,8 +112961,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12326/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12326/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12321/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12321/14932 [17:28<03:42, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -113123,8 +112970,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12327/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12327/14932 [17:32<03:42, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12322/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12322/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113132,8 +112979,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12328/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12328/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12323/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12323/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113141,8 +112988,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12329/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12329/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12324/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12324/14932 [17:29<03:42, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113150,8 +112997,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12330/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12330/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  83%|▊| 12325/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12325/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -113159,8 +113006,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12331/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  83%|▊| 12331/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12326/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  83%|▊| 12326/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113168,8 +113015,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12332/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12332/14932 [17:33<03:42, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12327/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12327/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -113177,8 +113024,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12333/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12333/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12328/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12328/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113186,8 +113033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12334/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12334/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  83%|▊| 12329/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12329/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -113195,8 +113042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12335/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12335/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12330/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  83%|▊| 12330/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -113204,8 +113051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12336/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12336/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  83%|▊| 12331/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12331/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -113213,8 +113060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12337/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  83%|▊| 12337/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  83%|▊| 12332/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12332/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -113222,8 +113069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12338/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  83%|▊| 12338/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12333/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  83%|▊| 12333/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -113231,7 +113078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12339/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12334/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  83%|▊| 12334/14932 [17:29<03:41, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113239,7 +113087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12339/14932 [17:33<03:41, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12335/14932 [17:30<03:41, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12335/14932 [17:30<03:41, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -113247,8 +113096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12340/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12340/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12336/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12336/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -113256,8 +113105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12341/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  83%|▊| 12341/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  83%|▊| 12337/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  83%|▊| 12337/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113265,8 +113114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12342/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  83%|▊| 12342/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  83%|▊| 12338/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  83%|▊| 12338/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -113274,8 +113123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12343/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  83%|▊| 12343/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12339/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  83%|▊| 12339/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -113283,8 +113132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12344/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12344/14932 [17:34<03:41, 11.71it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  83%|▊| 12340/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  83%|▊| 12340/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113292,8 +113141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12345/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  83%|▊| 12345/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12341/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12341/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113301,8 +113150,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12346/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12346/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  83%|▊| 12342/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113310,8 +113158,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12347/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  83%|▊| 12347/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12342/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -113319,8 +113166,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12348/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12348/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  83%|▊| 12343/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  83%|▊| 12343/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -113328,8 +113175,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12349/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  83%|▊| 12349/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12344/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12344/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113337,8 +113184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12350/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12350/14932 [17:34<03:40, 11.71it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  83%|▊| 12345/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12345/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113346,8 +113193,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12351/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  83%|▊| 12351/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12346/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12346/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113355,8 +113202,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12352/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12352/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12347/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12347/14932 [17:30<03:40, 11.75it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -113364,8 +113211,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12353/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12353/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  83%|▊| 12348/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  83%|▊| 12348/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -113373,8 +113220,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12354/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  83%|▊| 12354/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12349/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12349/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113382,8 +113229,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12355/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12355/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  83%|▊| 12350/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12350/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113391,8 +113238,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12356/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  83%|▊| 12356/14932 [17:35<03:40, 11.71it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  83%|▊| 12351/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12351/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -113400,8 +113247,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12357/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  83%|▊| 12357/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12352/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12352/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -113409,8 +113256,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12358/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12358/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12353/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12353/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -113418,8 +113265,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12359/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12359/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  83%|▊| 12354/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  83%|▊| 12354/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -113427,8 +113274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12360/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  83%|▊| 12360/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  83%|▊| 12355/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  83%|▊| 12355/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113436,8 +113283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12361/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  83%|▊| 12361/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12356/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12356/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -113445,8 +113292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12362/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12362/14932 [17:35<03:39, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12357/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  83%|▊| 12357/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113454,8 +113301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12363/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12363/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12358/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12358/14932 [17:31<03:39, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -113463,8 +113310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12364/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12364/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12359/14932 [17:31<03:38, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12359/14932 [17:31<03:38, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113472,8 +113319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12365/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12365/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  83%|▊| 12360/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12360/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -113481,8 +113328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12366/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  83%|▊| 12366/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12361/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12361/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -113490,8 +113337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12367/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12367/14932 [17:36<03:39, 11.71it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  83%|▊| 12362/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12362/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -113499,8 +113346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12368/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  83%|▊| 12368/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12363/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12363/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113508,8 +113355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12369/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12369/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12364/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12364/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -113517,8 +113364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12370/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  83%|▊| 12370/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12365/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12365/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -113526,8 +113373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12371/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12371/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12366/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  83%|▊| 12366/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -113535,8 +113382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12372/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12372/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12367/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12367/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113544,8 +113391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12373/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12373/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12368/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12368/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113553,8 +113400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12374/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12374/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  83%|▊| 12369/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12369/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -113562,8 +113409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12375/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  83%|▊| 12375/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  83%|▊| 12370/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  83%|▊| 12370/14932 [17:32<03:38, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -113571,8 +113418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12376/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  83%|▊| 12376/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12371/14932 [17:32<03:37, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  83%|▊| 12371/14932 [17:32<03:37, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -113580,8 +113427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12377/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12377/14932 [17:36<03:38, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12372/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  83%|▊| 12372/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -113589,8 +113436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12378/14932 [17:37<03:38, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12378/14932 [17:37<03:38, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12373/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  83%|▊| 12373/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113598,8 +113445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12379/14932 [17:37<03:38, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12379/14932 [17:37<03:38, 11.71it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  83%|▊| 12374/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12374/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113607,8 +113454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12380/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  83%|▊| 12380/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12375/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12375/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113616,8 +113463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12381/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12381/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  83%|▊| 12376/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12376/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -113625,8 +113472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12382/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  83%|▊| 12382/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12377/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  83%|▊| 12377/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -113634,8 +113481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12383/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12383/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12378/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12378/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -113643,8 +113490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12384/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12384/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12379/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12379/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -113652,8 +113499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12385/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12385/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  83%|▊| 12380/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  83%|▊| 12380/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -113661,8 +113508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12386/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  83%|▊| 12386/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  83%|▊| 12381/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12381/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -113670,8 +113517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12387/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  83%|▊| 12387/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  83%|▊| 12382/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  83%|▊| 12382/14932 [17:33<03:37, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113679,8 +113526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12388/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  83%|▊| 12388/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12383/14932 [17:33<03:36, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12383/14932 [17:33<03:36, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -113688,8 +113535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12389/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12389/14932 [17:37<03:37, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12384/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12384/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113697,8 +113544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12390/14932 [17:38<03:37, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12390/14932 [17:38<03:37, 11.71it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  83%|▊| 12385/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12385/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113706,8 +113553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12391/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  83%|▊| 12391/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  83%|▊| 12386/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12386/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -113715,8 +113562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12392/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  83%|▊| 12392/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12387/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12387/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113724,8 +113571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12393/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12393/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12388/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12388/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -113733,8 +113580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12394/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12394/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12389/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12389/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113742,8 +113589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12395/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12395/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12390/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12390/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -113751,8 +113598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12396/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12396/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12391/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  83%|▊| 12391/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113760,8 +113607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12397/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12397/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  83%|▊| 12392/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12392/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113769,8 +113616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12398/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  83%|▊| 12398/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12393/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12393/14932 [17:34<03:36, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113778,8 +113625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12399/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12399/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12394/14932 [17:35<03:36, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12394/14932 [17:35<03:36, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113787,8 +113634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12400/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12400/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  83%|▊| 12395/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12395/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -113796,8 +113643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12401/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  83%|▊| 12401/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  83%|▊| 12396/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  83%|▊| 12396/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -113805,8 +113652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12402/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  83%|▊| 12402/14932 [17:38<03:36, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12397/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  83%|▊| 12397/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -113814,8 +113661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12403/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12403/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  83%|▊| 12398/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  83%|▊| 12398/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113823,8 +113670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12404/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  83%|▊| 12404/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  83%|▊| 12399/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12399/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -113832,8 +113679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12405/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  83%|▊| 12405/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12400/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  83%|▊| 12400/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -113841,8 +113688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12406/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12406/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  83%|▊| 12401/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12401/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113850,8 +113697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12407/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  83%|▊| 12407/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12402/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12402/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -113859,7 +113706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12408/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12403/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  83%|▊| 12403/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -113867,7 +113715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12408/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  83%|▊| 12404/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12404/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -113875,8 +113724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12409/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12409/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  83%|▊| 12405/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  83%|▊| 12405/14932 [17:35<03:35, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -113884,8 +113733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12410/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  83%|▊| 12410/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12406/14932 [17:36<03:35, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  83%|▊| 12406/14932 [17:36<03:35, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -113893,8 +113742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12411/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12411/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12407/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12407/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -113902,8 +113751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12412/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12412/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12408/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  83%|▊| 12408/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -113911,8 +113760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12413/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12413/14932 [17:39<03:35, 11.71it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  83%|▊| 12409/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12409/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -113920,7 +113769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12414/14932 [17:39<03:34, 11.71it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  83%|▊| 12410/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  83%|▊| 12410/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -113928,7 +113778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12414/14932 [17:39<03:34, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12411/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  83%|▊| 12411/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -113936,8 +113787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12415/14932 [17:39<03:34, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12415/14932 [17:39<03:34, 11.71it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  83%|▊| 12412/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12412/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -113945,8 +113796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12416/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12416/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  83%|▊| 12413/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  83%|▊| 12413/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -113954,8 +113805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12417/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  83%|▊| 12417/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12414/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  83%|▊| 12414/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -113963,8 +113814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12418/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12418/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12415/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  83%|▊| 12415/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -113972,8 +113823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12419/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12419/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  83%|▊| 12416/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12416/14932 [17:36<03:34, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -113981,8 +113832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12420/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  83%|▊| 12420/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12417/14932 [17:37<03:34, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12417/14932 [17:37<03:34, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -113990,8 +113841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12421/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12421/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12418/14932 [17:37<03:34, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12418/14932 [17:37<03:34, 11.75it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -113999,8 +113850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12422/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12422/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12419/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  83%|▊| 12419/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -114008,8 +113859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12423/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12423/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  83%|▊| 12420/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  83%|▊| 12420/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -114017,8 +113868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12424/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  83%|▊| 12424/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  83%|▊| 12421/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  83%|▊| 12421/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -114026,8 +113877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12425/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  83%|▊| 12425/14932 [17:40<03:34, 11.71it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  83%|▊| 12422/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  83%|▊| 12422/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114035,8 +113886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12426/14932 [17:40<03:33, 11.71it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  83%|▊| 12426/14932 [17:40<03:33, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12423/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12423/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -114044,8 +113895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12427/14932 [17:40<03:33, 11.71it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12427/14932 [17:40<03:33, 11.71it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12424/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12424/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -114053,8 +113904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12428/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12428/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12425/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  83%|▊| 12425/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -114062,8 +113913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12429/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12429/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  83%|▊| 12426/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12426/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -114071,8 +113922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12430/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  83%|▊| 12430/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12427/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  83%|▊| 12427/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -114080,8 +113931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12431/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12431/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  83%|▊| 12428/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  83%|▊| 12428/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -114089,8 +113940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12432/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  83%|▊| 12432/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  83%|▊| 12429/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  83%|▊| 12429/14932 [17:37<03:33, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -114098,8 +113949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12433/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  83%|▊| 12433/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  83%|▊| 12430/14932 [17:37<03:32, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12430/14932 [17:37<03:32, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -114107,8 +113958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12434/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  83%|▊| 12434/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  83%|▊| 12431/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  83%|▊| 12431/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114116,8 +113967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12435/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  83%|▊| 12435/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12432/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12432/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -114125,8 +113976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12436/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  83%|▊| 12436/14932 [17:41<03:33, 11.71it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  83%|▊| 12433/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12433/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -114134,8 +113985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12437/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  83%|▊| 12437/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12434/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  83%|▊| 12434/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114143,8 +113994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12438/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  83%|▊| 12438/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  83%|▊| 12435/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12435/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -114152,8 +114003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12439/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  83%|▊| 12439/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12436/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12436/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -114161,8 +114012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12440/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  83%|▊| 12440/14932 [17:41<03:32, 11.71it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12437/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  83%|▊| 12437/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114170,8 +114021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12441/14932 [17:41<03:32, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12441/14932 [17:41<03:32, 11.72it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  83%|▊| 12438/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  83%|▊| 12438/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -114179,8 +114030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12442/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  83%|▊| 12442/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12439/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12439/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -114188,8 +114039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12443/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12443/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  83%|▊| 12440/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12440/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -114197,8 +114048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12444/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12444/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  83%|▊| 12441/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12441/14932 [17:38<03:32, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114206,8 +114057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12445/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  83%|▊| 12445/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  83%|▊| 12442/14932 [17:38<03:31, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12442/14932 [17:38<03:31, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -114215,8 +114066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12446/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  83%|▊| 12446/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  83%|▊| 12443/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12443/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -114224,8 +114075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12447/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  83%|▊| 12447/14932 [17:42<03:32, 11.72it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  83%|▊| 12444/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  83%|▊| 12444/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -114233,8 +114084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12448/14932 [17:42<03:32, 11.71it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  83%|▊| 12448/14932 [17:42<03:32, 11.71it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12445/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12445/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -114242,8 +114093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12449/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12449/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12446/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  83%|▊| 12446/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -114251,8 +114102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12450/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12450/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  83%|▊| 12447/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  83%|▊| 12447/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114260,8 +114111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12451/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  83%|▊| 12451/14932 [17:42<03:31, 11.71it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  83%|▊| 12448/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12448/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114269,8 +114120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12452/14932 [17:42<03:31, 11.72it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  83%|▊| 12452/14932 [17:42<03:31, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12449/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12449/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -114278,8 +114129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12453/14932 [17:42<03:31, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12453/14932 [17:42<03:31, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12450/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  83%|▊| 12450/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -114287,8 +114138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12454/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12454/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  83%|▊| 12451/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12451/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -114296,8 +114147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12455/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  83%|▊| 12455/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  83%|▊| 12452/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  83%|▊| 12452/14932 [17:39<03:31, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -114305,8 +114156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12456/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  83%|▊| 12456/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12453/14932 [17:39<03:30, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12453/14932 [17:39<03:30, 11.75it/s, v_num=ui8w, train/loss=4.9"
      ]
     },
     {
@@ -114314,8 +114165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12457/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12457/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12454/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=4.9\r",
+      "Epoch 0:  83%|▊| 12454/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114323,8 +114174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12458/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12458/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12455/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  83%|▊| 12455/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -114332,8 +114183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12459/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12459/14932 [17:43<03:31, 11.72it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  83%|▊| 12456/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  83%|▊| 12456/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -114341,8 +114192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12460/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  83%|▊| 12460/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12457/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  83%|▊| 12457/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -114350,8 +114201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12461/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  83%|▊| 12461/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  83%|▊| 12458/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  83%|▊| 12458/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114359,8 +114210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12462/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  83%|▊| 12462/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12459/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  83%|▊| 12459/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114368,8 +114219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12463/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12463/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  83%|▊| 12460/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  83%|▊| 12460/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114377,8 +114228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12464/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  83%|▊| 12464/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12461/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  83%|▊| 12461/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -114386,8 +114237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12465/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12465/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  83%|▊| 12462/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  83%|▊| 12462/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114395,8 +114246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12466/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  83%|▊| 12466/14932 [17:43<03:30, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  83%|▊| 12463/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12463/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114404,8 +114255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12467/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  83%|▊| 12467/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12464/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  83%|▊| 12464/14932 [17:40<03:30, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -114413,7 +114264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12468/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  83%|▊| 12465/14932 [17:40<03:29, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  83%|▊| 12465/14932 [17:40<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -114421,7 +114273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  83%|▊| 12468/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  83%|▊| 12466/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  83%|▊| 12466/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -114429,8 +114282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12469/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  84%|▊| 12469/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  83%|▊| 12467/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  83%|▊| 12467/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -114438,8 +114291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12470/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  84%|▊| 12470/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  83%|▊| 12468/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  83%|▊| 12468/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -114447,8 +114300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12471/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  84%|▊| 12471/14932 [17:44<03:30, 11.72it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  84%|▊| 12469/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12469/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -114456,8 +114309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12472/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  84%|▊| 12472/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  84%|▊| 12470/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  84%|▊| 12470/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -114465,8 +114318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12473/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  84%|▊| 12473/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  84%|▊| 12471/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  84%|▊| 12471/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114474,8 +114327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12474/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  84%|▊| 12474/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12472/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12472/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -114483,8 +114336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12475/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12475/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  84%|▊| 12473/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12473/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114492,8 +114345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12476/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  84%|▊| 12476/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12474/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12474/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -114501,8 +114354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12477/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12477/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  84%|▊| 12475/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12475/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -114510,8 +114363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12478/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  84%|▊| 12478/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12476/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  84%|▊| 12476/14932 [17:41<03:29, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -114519,8 +114372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12479/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12479/14932 [17:44<03:29, 11.72it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  84%|▊| 12477/14932 [17:41<03:28, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12477/14932 [17:41<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114528,8 +114381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12480/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  84%|▊| 12480/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  84%|▊| 12478/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12478/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114537,8 +114390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12481/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  84%|▊| 12481/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12479/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12479/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -114546,8 +114399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12482/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12482/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  84%|▊| 12480/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  84%|▊| 12480/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114555,8 +114408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12483/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  84%|▊| 12483/14932 [17:45<03:29, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12481/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12481/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114564,8 +114417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12484/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12484/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12482/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12482/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -114573,8 +114426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12485/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  84%|▊| 12485/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12483/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12483/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -114582,8 +114435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12486/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  84%|▊| 12486/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12484/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  84%|▊| 12484/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -114591,8 +114444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12487/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12487/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12485/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12485/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -114600,8 +114453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12488/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12488/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  84%|▊| 12486/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  84%|▊| 12486/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114609,8 +114462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12489/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  84%|▊| 12489/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12487/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12487/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -114618,8 +114471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12490/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12490/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  84%|▊| 12488/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12488/14932 [17:42<03:28, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -114627,8 +114480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12491/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  84%|▊| 12491/14932 [17:45<03:28, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12489/14932 [17:42<03:27, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12489/14932 [17:42<03:27, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -114636,8 +114489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12492/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12492/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12490/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12490/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -114645,8 +114498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12493/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12493/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12491/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  84%|▊| 12491/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -114654,8 +114507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12494/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12494/14932 [17:46<03:28, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12492/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12492/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -114663,8 +114516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12495/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12495/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12493/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12493/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -114672,8 +114525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12496/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12496/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12494/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  84%|▊| 12494/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114681,8 +114534,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12497/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12497/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  84%|▊| 12495/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114690,8 +114542,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12498/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  84%|▊| 12498/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12495/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114699,8 +114550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12499/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12499/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12496/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12496/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -114708,8 +114559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12500/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12500/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12497/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  84%|▊| 12497/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -114717,8 +114568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12501/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12501/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12498/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12498/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114726,8 +114577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12502/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12502/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  84%|▊| 12499/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  84%|▊| 12499/14932 [17:43<03:27, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -114735,7 +114586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12503/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  84%|▊| 12500/14932 [17:43<03:26, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  84%|▊| 12500/14932 [17:43<03:26, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -114743,7 +114595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12503/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12501/14932 [17:43<03:26, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  84%|▊| 12501/14932 [17:43<03:26, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -114751,8 +114604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12504/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12504/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12502/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  84%|▊| 12502/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -114760,8 +114613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12505/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12505/14932 [17:46<03:27, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12503/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  84%|▊| 12503/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -114769,8 +114622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12506/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12506/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12504/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  84%|▊| 12504/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -114778,8 +114631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12507/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12507/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  84%|▊| 12505/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12505/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -114787,8 +114640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12508/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  84%|▊| 12508/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  84%|▊| 12506/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  84%|▊| 12506/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -114796,8 +114649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12509/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  84%|▊| 12509/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  84%|▊| 12507/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12507/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -114805,8 +114658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12510/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  84%|▊| 12510/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  84%|▊| 12508/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  84%|▊| 12508/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -114814,8 +114667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12511/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  84%|▊| 12511/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  84%|▊| 12509/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12509/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114823,8 +114676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12512/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  84%|▊| 12512/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  84%|▊| 12510/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  84%|▊| 12510/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114832,8 +114685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12513/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  84%|▊| 12513/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  84%|▊| 12511/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12511/14932 [17:44<03:26, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114841,8 +114694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12514/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  84%|▊| 12514/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12512/14932 [17:44<03:25, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12512/14932 [17:44<03:25, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114850,8 +114703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12515/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12515/14932 [17:47<03:26, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12513/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12513/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -114859,8 +114712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12516/14932 [17:48<03:26, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12516/14932 [17:48<03:26, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12514/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  84%|▊| 12514/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -114868,8 +114721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12517/14932 [17:48<03:26, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12517/14932 [17:48<03:26, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12515/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  84%|▊| 12515/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114877,8 +114730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12518/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12518/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12516/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12516/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114886,8 +114739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12519/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12519/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12517/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12517/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114895,8 +114748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12520/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12520/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12518/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12518/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -114904,8 +114757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12521/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12521/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  84%|▊| 12519/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12519/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -114913,8 +114766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12522/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  84%|▊| 12522/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  84%|▊| 12520/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  84%|▊| 12520/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114922,8 +114775,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12523/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  84%|▊| 12523/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  84%|▊| 12521/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114931,8 +114783,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12524/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  84%|▊| 12524/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12521/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114940,7 +114791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12525/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12522/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12522/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -114948,7 +114800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12525/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12523/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12523/14932 [17:45<03:25, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -114956,8 +114809,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12526/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12526/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12524/14932 [17:45<03:24, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  84%|▊| 12524/14932 [17:45<03:24, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -114965,8 +114818,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12527/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12527/14932 [17:48<03:25, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12525/14932 [17:45<03:24, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  84%|▊| 12525/14932 [17:45<03:24, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -114974,8 +114827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12528/14932 [17:49<03:25, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12528/14932 [17:49<03:25, 11.72it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  84%|▊| 12526/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  84%|▊| 12526/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -114983,8 +114836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12529/14932 [17:49<03:25, 11.72it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  84%|▊| 12529/14932 [17:49<03:25, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12527/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12527/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -114992,8 +114845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12530/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12530/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  84%|▊| 12528/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  84%|▊| 12528/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115001,8 +114854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12531/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  84%|▊| 12531/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  84%|▊| 12529/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12529/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -115010,8 +114863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12532/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  84%|▊| 12532/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12530/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  84%|▊| 12530/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115019,8 +114872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12533/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12533/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12531/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12531/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -115028,8 +114881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12534/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12534/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12532/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  84%|▊| 12532/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115037,8 +114890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12535/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12535/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12533/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12533/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -115046,8 +114899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12536/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12536/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12534/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12534/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -115055,8 +114908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12537/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12537/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  84%|▊| 12535/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  84%|▊| 12535/14932 [17:46<03:24, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -115064,8 +114917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12538/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  84%|▊| 12538/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12536/14932 [17:46<03:23, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12536/14932 [17:46<03:23, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115073,8 +114926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12539/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12539/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  84%|▊| 12537/14932 [17:46<03:23, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  84%|▊| 12537/14932 [17:46<03:23, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -115082,8 +114935,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12540/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  84%|▊| 12540/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12538/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  84%|▊| 12538/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115091,8 +114944,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12541/14932 [17:49<03:24, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12541/14932 [17:50<03:24, 11.72it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  84%|▊| 12539/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115100,8 +114952,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12542/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  84%|▊| 12542/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12539/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -115109,8 +114960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12543/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12543/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  84%|▊| 12540/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  84%|▊| 12540/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -115118,8 +114969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12544/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  84%|▊| 12544/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  84%|▊| 12541/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  84%|▊| 12541/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115127,8 +114978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12545/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  84%|▊| 12545/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  84%|▊| 12542/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12542/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115136,8 +114987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12546/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  84%|▊| 12546/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  84%|▊| 12543/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12543/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -115145,8 +114996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12547/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  84%|▊| 12547/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12544/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  84%|▊| 12544/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -115154,8 +115005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12548/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12548/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12545/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  84%|▊| 12545/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -115163,8 +115014,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12549/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12549/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  84%|▊| 12546/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -115172,8 +115022,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12550/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  84%|▊| 12550/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12546/14932 [17:47<03:23, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -115181,8 +115030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12551/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12551/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12547/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  84%|▊| 12547/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115190,8 +115039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12552/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12552/14932 [17:50<03:23, 11.72it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  84%|▊| 12548/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  84%|▊| 12548/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -115199,8 +115048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12553/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  84%|▊| 12553/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  84%|▊| 12549/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  84%|▊| 12549/14932 [17:47<03:22, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -115208,8 +115057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12554/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  84%|▊| 12554/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  84%|▊| 12550/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12550/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115217,8 +115066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12555/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  84%|▊| 12555/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12551/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12551/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -115226,8 +115075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12556/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12556/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  84%|▊| 12552/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  84%|▊| 12552/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -115235,8 +115084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12557/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  84%|▊| 12557/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12553/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  84%|▊| 12553/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -115244,8 +115093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12558/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12558/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12554/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12554/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115253,8 +115102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12559/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12559/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  84%|▊| 12555/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12555/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115262,8 +115111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12560/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  84%|▊| 12560/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  84%|▊| 12556/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  84%|▊| 12556/14932 [17:48<03:22, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115271,8 +115120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12561/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  84%|▊| 12561/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  84%|▊| 12557/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12557/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -115280,8 +115129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12562/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  84%|▊| 12562/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12558/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  84%|▊| 12558/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -115289,8 +115138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12563/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  84%|▊| 12563/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  84%|▊| 12559/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  84%|▊| 12559/14932 [17:49<03:22, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115298,8 +115147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12564/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  84%|▊| 12564/14932 [17:51<03:22, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12560/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12560/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -115307,7 +115156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12565/14932 [17:51<03:21, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12561/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  84%|▊| 12561/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115315,7 +115165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12565/14932 [17:51<03:21, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12562/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12562/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -115323,8 +115174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12566/14932 [17:51<03:21, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12566/14932 [17:51<03:21, 11.72it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  84%|▊| 12563/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  84%|▊| 12563/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115332,8 +115183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12567/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  84%|▊| 12567/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12564/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12564/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -115341,8 +115192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12568/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12568/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12565/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  84%|▊| 12565/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -115350,8 +115201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12569/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12569/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  84%|▊| 12566/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  84%|▊| 12566/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115359,8 +115210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12570/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  84%|▊| 12570/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  84%|▊| 12567/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12567/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -115368,8 +115219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12571/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  84%|▊| 12571/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12568/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  84%|▊| 12568/14932 [17:49<03:21, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115377,8 +115228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12572/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12572/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12569/14932 [17:50<03:21, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12569/14932 [17:50<03:21, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -115386,8 +115237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12573/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12573/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  84%|▊| 12570/14932 [17:50<03:21, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  84%|▊| 12570/14932 [17:50<03:21, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -115395,8 +115246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12574/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  84%|▊| 12574/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  84%|▊| 12571/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  84%|▊| 12571/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115404,8 +115255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12575/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  84%|▊| 12575/14932 [17:52<03:21, 11.72it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  84%|▊| 12572/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12572/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115413,8 +115264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12576/14932 [17:52<03:20, 11.72it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  84%|▊| 12576/14932 [17:52<03:20, 11.72it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  84%|▊| 12573/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12573/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115422,8 +115273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12577/14932 [17:52<03:20, 11.72it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  84%|▊| 12577/14932 [17:52<03:20, 11.72it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  84%|▊| 12574/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12574/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -115431,8 +115282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12578/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  84%|▊| 12578/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  84%|▊| 12575/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  84%|▊| 12575/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -115440,8 +115291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12579/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  84%|▊| 12579/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12576/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  84%|▊| 12576/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115449,8 +115300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12580/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12580/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12577/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12577/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -115458,8 +115309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12581/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12581/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  84%|▊| 12578/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  84%|▊| 12578/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -115467,8 +115318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12582/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  84%|▊| 12582/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12579/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12579/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -115476,8 +115327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12583/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12583/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12580/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  84%|▊| 12580/14932 [17:50<03:20, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -115485,8 +115336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12584/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12584/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12581/14932 [17:51<03:20, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  84%|▊| 12581/14932 [17:51<03:20, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -115494,8 +115345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12585/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12585/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12582/14932 [17:51<03:20, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  84%|▊| 12582/14932 [17:51<03:20, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115503,8 +115354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12586/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12586/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  84%|▊| 12583/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12583/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -115512,8 +115363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12587/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  84%|▊| 12587/14932 [17:53<03:20, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12584/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12584/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115521,8 +115372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12588/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12588/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12585/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  84%|▊| 12585/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -115530,8 +115381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12589/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12589/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  84%|▊| 12586/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  84%|▊| 12586/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -115539,8 +115390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12590/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  84%|▊| 12590/14932 [17:53<03:19, 11.72it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  84%|▊| 12587/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12587/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115548,8 +115399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12591/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  84%|▊| 12591/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  84%|▊| 12588/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12588/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -115557,8 +115408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12592/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  84%|▊| 12592/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12589/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12589/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -115566,8 +115417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12593/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12593/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12590/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  84%|▊| 12590/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -115575,8 +115426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12594/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12594/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  84%|▊| 12591/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  84%|▊| 12591/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115584,8 +115435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12595/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  84%|▊| 12595/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12592/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  84%|▊| 12592/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -115593,8 +115444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12596/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12596/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12593/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  84%|▊| 12593/14932 [17:51<03:19, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115602,8 +115453,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12597/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12597/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12594/14932 [17:52<03:19, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115611,8 +115461,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12598/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12598/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  84%|▊| 12594/14932 [17:52<03:19, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115620,8 +115469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12599/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  84%|▊| 12599/14932 [17:54<03:19, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12595/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  84%|▊| 12595/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -115629,8 +115478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12600/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12600/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  84%|▊| 12596/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  84%|▊| 12596/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -115638,8 +115487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12601/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  84%|▊| 12601/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12597/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  84%|▊| 12597/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115647,8 +115496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12602/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12602/14932 [17:54<03:18, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12598/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  84%|▊| 12598/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115656,8 +115505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12603/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12603/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12599/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12599/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -115665,8 +115514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12604/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  84%|▊| 12604/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12600/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  84%|▊| 12600/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -115674,8 +115523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12605/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12605/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  84%|▊| 12601/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  84%|▊| 12601/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115683,8 +115532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12606/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  84%|▊| 12606/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  84%|▊| 12602/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  84%|▊| 12602/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -115692,8 +115541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12607/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  84%|▊| 12607/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  84%|▊| 12603/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  84%|▊| 12603/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115701,8 +115550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12608/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  84%|▊| 12608/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  84%|▊| 12604/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12604/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -115710,8 +115559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12609/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  84%|▊| 12609/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  84%|▊| 12605/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  84%|▊| 12605/14932 [17:52<03:18, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -115719,8 +115568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12610/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  84%|▊| 12610/14932 [17:55<03:18, 11.72it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  84%|▊| 12606/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  84%|▊| 12606/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -115728,8 +115577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12611/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  84%|▊| 12611/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  84%|▊| 12607/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  84%|▊| 12607/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -115737,8 +115586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12612/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  84%|▊| 12612/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12608/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  84%|▊| 12608/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -115746,8 +115595,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12613/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12613/14932 [17:55<03:17, 11.72it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  84%|▊| 12609/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -115755,8 +115603,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12614/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  84%|▊| 12614/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  84%|▊| 12609/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115764,8 +115611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12615/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  84%|▊| 12615/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  84%|▊| 12610/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12610/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115773,8 +115620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12616/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  84%|▊| 12616/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12611/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  84%|▊| 12611/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115782,8 +115629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  84%|▊| 12617/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  84%|▊| 12617/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  84%|▊| 12612/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  84%|▊| 12612/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -115791,8 +115638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12618/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  85%|▊| 12618/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  84%|▊| 12613/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  84%|▊| 12613/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115800,8 +115647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12619/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12619/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  84%|▊| 12614/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  84%|▊| 12614/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -115809,8 +115656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12620/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12620/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  84%|▊| 12615/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  84%|▊| 12615/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -115818,8 +115665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12621/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  85%|▊| 12621/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  84%|▊| 12616/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  84%|▊| 12616/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -115827,8 +115674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12622/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  85%|▊| 12622/14932 [17:56<03:17, 11.72it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  84%|▊| 12617/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  84%|▊| 12617/14932 [17:53<03:17, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -115836,8 +115683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12623/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  85%|▊| 12623/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  85%|▊| 12618/14932 [17:53<03:16, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12618/14932 [17:53<03:16, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -115845,8 +115692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12624/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  85%|▊| 12624/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  85%|▊| 12619/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  85%|▊| 12619/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -115854,8 +115701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12625/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  85%|▊| 12625/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12620/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12620/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -115863,8 +115710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12626/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12626/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12621/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12621/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -115872,8 +115719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12627/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12627/14932 [17:56<03:16, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12622/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12622/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115881,8 +115728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12628/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12628/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12623/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12623/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -115890,8 +115737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12629/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12629/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  85%|▊| 12624/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12624/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -115899,8 +115746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12630/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  85%|▊| 12630/14932 [17:57<03:16, 11.72it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  85%|▊| 12625/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12625/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -115908,8 +115755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12631/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  85%|▊| 12631/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12626/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  85%|▊| 12626/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115917,8 +115764,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12632/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12632/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12627/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115926,8 +115772,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12633/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12633/14932 [17:57<03:16, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12627/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -115935,8 +115780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12634/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12634/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  85%|▊| 12628/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12628/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115944,8 +115789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12635/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  85%|▊| 12635/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12629/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12629/14932 [17:54<03:16, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -115953,8 +115798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12636/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12636/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  85%|▊| 12630/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12630/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -115962,8 +115807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12637/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  85%|▊| 12637/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12631/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  85%|▊| 12631/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -115971,8 +115816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12638/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  85%|▊| 12638/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12632/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12632/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -115980,8 +115825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12639/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12639/14932 [17:57<03:15, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  85%|▊| 12633/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  85%|▊| 12633/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -115989,8 +115834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12640/14932 [17:58<03:15, 11.72it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  85%|▊| 12640/14932 [17:58<03:15, 11.72it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12634/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12634/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -115998,8 +115843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12641/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12641/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12635/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12635/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -116007,8 +115852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12642/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12642/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12636/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12636/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -116016,8 +115861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12643/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12643/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12637/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12637/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -116025,8 +115870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12644/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12644/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12638/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  85%|▊| 12638/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116034,8 +115879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12645/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12645/14932 [17:58<03:15, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12639/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12639/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116043,8 +115888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12646/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12646/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12640/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12640/14932 [17:55<03:15, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -116052,8 +115897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12647/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12647/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12641/14932 [17:55<03:14, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  85%|▊| 12641/14932 [17:55<03:14, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -116061,8 +115906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12648/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12648/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12642/14932 [17:55<03:14, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  85%|▊| 12642/14932 [17:55<03:14, 11.75it/s, v_num=ui8w, train/loss=4.8"
      ]
     },
     {
@@ -116070,8 +115915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12649/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12649/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  85%|▊| 12643/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=4.8\r",
+      "Epoch 0:  85%|▊| 12643/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -116079,8 +115924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12650/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  85%|▊| 12650/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12644/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12644/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116088,8 +115933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12651/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12651/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12645/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12645/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -116097,8 +115942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12652/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12652/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12646/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  85%|▊| 12646/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116106,8 +115951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12653/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12653/14932 [17:58<03:14, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12647/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12647/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116115,8 +115960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12654/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12654/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12648/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12648/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -116124,8 +115969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12655/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  85%|▊| 12655/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12649/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12649/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116133,8 +115978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12656/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  85%|▊| 12656/14932 [17:59<03:14, 11.73it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  85%|▊| 12650/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12650/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116142,8 +115987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12657/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  85%|▊| 12657/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12651/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12651/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -116151,8 +115996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12658/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12658/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  85%|▊| 12652/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  85%|▊| 12652/14932 [17:56<03:14, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -116160,8 +116005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12659/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  85%|▊| 12659/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12653/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12653/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -116169,8 +116014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12660/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12660/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12654/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  85%|▊| 12654/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -116178,8 +116023,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12661/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12661/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12655/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  85%|▊| 12655/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116187,8 +116032,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12662/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12662/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  85%|▊| 12656/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12656/14932 [17:56<03:13, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -116196,8 +116041,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12663/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  85%|▊| 12663/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12657/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  85%|▊| 12657/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -116205,8 +116050,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12664/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12664/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  85%|▊| 12658/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12658/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116214,8 +116059,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12665/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  85%|▊| 12665/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12659/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12659/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -116223,8 +116068,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12666/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12666/14932 [17:59<03:13, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12660/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12660/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116232,8 +116077,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12667/14932 [18:00<03:13, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12667/14932 [18:00<03:13, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12661/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12661/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -116241,8 +116086,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12668/14932 [18:00<03:13, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12668/14932 [18:00<03:13, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12662/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12662/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116250,8 +116095,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12669/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12669/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  85%|▊| 12663/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12663/14932 [17:57<03:13, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -116259,8 +116104,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12670/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  85%|▊| 12670/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12664/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -116268,8 +116112,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12671/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12671/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12664/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116277,8 +116120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12672/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12672/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  85%|▊| 12665/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12665/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -116286,8 +116129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12673/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  85%|▊| 12673/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  85%|▊| 12666/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12666/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -116295,8 +116138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12674/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  85%|▊| 12674/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12667/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  85%|▊| 12667/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -116304,8 +116147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12675/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12675/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12668/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  85%|▊| 12668/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -116313,8 +116156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12676/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12676/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12669/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  85%|▊| 12669/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -116322,8 +116165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12677/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12677/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  85%|▊| 12670/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  85%|▊| 12670/14932 [17:57<03:12, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -116331,8 +116174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12678/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  85%|▊| 12678/14932 [18:00<03:12, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  85%|▊| 12671/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12671/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116340,8 +116183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12679/14932 [18:01<03:12, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  85%|▊| 12679/14932 [18:01<03:12, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12672/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12672/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -116349,8 +116192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12680/14932 [18:01<03:12, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12680/14932 [18:01<03:12, 11.73it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  85%|▊| 12673/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12673/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116358,8 +116201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12681/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  85%|▊| 12681/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12674/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12674/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -116367,8 +116210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12682/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12682/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12675/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  85%|▊| 12675/14932 [17:58<03:12, 11.75it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -116376,8 +116219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12683/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12683/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12676/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  85%|▊| 12676/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -116385,8 +116228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12684/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12684/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  85%|▊| 12677/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  85%|▊| 12677/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -116394,8 +116237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12685/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  85%|▊| 12685/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  85%|▊| 12678/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  85%|▊| 12678/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116403,8 +116246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12686/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  85%|▊| 12686/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  85%|▊| 12679/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12679/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116412,8 +116255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12687/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  85%|▊| 12687/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12680/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12680/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -116421,8 +116264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12688/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12688/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12681/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  85%|▊| 12681/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -116430,8 +116273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12689/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12689/14932 [18:01<03:11, 11.73it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  85%|▊| 12682/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12682/14932 [17:58<03:11, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116439,8 +116282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12690/14932 [18:02<03:11, 11.73it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  85%|▊| 12690/14932 [18:02<03:11, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12683/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12683/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -116448,8 +116291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12691/14932 [18:02<03:11, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12691/14932 [18:02<03:11, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12684/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  85%|▊| 12684/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -116457,8 +116300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12692/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12692/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  85%|▊| 12685/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  85%|▊| 12685/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -116466,8 +116309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12693/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  85%|▊| 12693/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  85%|▊| 12686/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12686/14932 [17:59<03:11, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116475,8 +116318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12694/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  85%|▊| 12694/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12687/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12687/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -116484,8 +116327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12695/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12695/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  85%|▊| 12688/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  85%|▊| 12688/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -116493,8 +116336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12696/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  85%|▊| 12696/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  85%|▊| 12689/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  85%|▊| 12689/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116502,8 +116345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12697/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  85%|▊| 12697/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12690/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12690/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -116511,8 +116354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12698/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12698/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  85%|▊| 12691/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  85%|▊| 12691/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -116520,8 +116363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12699/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  85%|▊| 12699/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  85%|▊| 12692/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  85%|▊| 12692/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -116529,8 +116372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12700/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  85%|▊| 12700/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  85%|▊| 12693/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  85%|▊| 12693/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -116538,8 +116381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12701/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  85%|▊| 12701/14932 [18:02<03:10, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12694/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12694/14932 [17:59<03:10, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116547,8 +116390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12702/14932 [18:03<03:10, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12702/14932 [18:03<03:10, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12695/14932 [17:59<03:10, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12695/14932 [17:59<03:10, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -116556,8 +116399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12703/14932 [18:03<03:10, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12703/14932 [18:03<03:10, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12696/14932 [18:00<03:10, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12696/14932 [18:00<03:10, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116565,8 +116408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12704/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12704/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12697/14932 [18:00<03:10, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12697/14932 [18:00<03:10, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116574,8 +116417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12705/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12705/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  85%|▊| 12698/14932 [18:00<03:10, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12698/14932 [18:00<03:10, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -116583,8 +116426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12706/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  85%|▊| 12706/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  85%|▊| 12699/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  85%|▊| 12699/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -116592,8 +116435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12707/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  85%|▊| 12707/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  85%|▊| 12700/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  85%|▊| 12700/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116601,8 +116444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12708/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  85%|▊| 12708/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12701/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12701/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -116610,8 +116453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12709/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12709/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12702/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  85%|▊| 12702/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116619,8 +116462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12710/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12710/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12703/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12703/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116628,8 +116471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12711/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  85%|▊| 12711/14932 [18:03<03:09, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12704/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12704/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116637,8 +116480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12712/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12712/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  85%|▊| 12705/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12705/14932 [18:00<03:09, 11.75it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -116646,8 +116489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12713/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  85%|▊| 12713/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  85%|▊| 12706/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  85%|▊| 12706/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -116655,8 +116498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12714/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  85%|▊| 12714/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  85%|▊| 12707/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  85%|▊| 12707/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -116664,8 +116507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12715/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  85%|▊| 12715/14932 [18:04<03:09, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12708/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12708/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -116673,8 +116516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12716/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12716/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12709/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  85%|▊| 12709/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -116682,8 +116525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12717/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12717/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  85%|▊| 12710/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  85%|▊| 12710/14932 [18:01<03:09, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -116691,8 +116534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12718/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  85%|▊| 12718/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  85%|▊| 12711/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  85%|▊| 12711/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116700,8 +116543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12719/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  85%|▊| 12719/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  85%|▊| 12712/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12712/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -116709,8 +116552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12720/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  85%|▊| 12720/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  85%|▊| 12713/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12713/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -116718,8 +116561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12721/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  85%|▊| 12721/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  85%|▊| 12714/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  85%|▊| 12714/14932 [18:01<03:08, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -116727,8 +116570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12722/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  85%|▊| 12722/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  85%|▊| 12715/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  85%|▊| 12715/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -116736,8 +116579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12723/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  85%|▊| 12723/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  85%|▊| 12716/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12716/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -116745,8 +116588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12724/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  85%|▊| 12724/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  85%|▊| 12717/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12717/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -116754,8 +116597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12725/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  85%|▊| 12725/14932 [18:04<03:08, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12718/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  85%|▊| 12718/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116763,8 +116606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12726/14932 [18:05<03:08, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12726/14932 [18:05<03:08, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12719/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12719/14932 [18:01<03:08, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116772,8 +116615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12727/14932 [18:05<03:08, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12727/14932 [18:05<03:08, 11.73it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  85%|▊| 12720/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12720/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116781,8 +116624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12728/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  85%|▊| 12728/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  85%|▊| 12721/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12721/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -116790,8 +116633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12729/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  85%|▊| 12729/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12722/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12722/14932 [18:02<03:08, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116799,8 +116642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12730/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12730/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  85%|▊| 12723/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12723/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -116808,8 +116651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12731/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  85%|▊| 12731/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  85%|▊| 12724/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  85%|▊| 12724/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -116817,8 +116660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12732/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  85%|▊| 12732/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  85%|▊| 12725/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  85%|▊| 12725/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116826,8 +116669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12733/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  85%|▊| 12733/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  85%|▊| 12726/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12726/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -116835,8 +116678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12734/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  85%|▊| 12734/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12727/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12727/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -116844,8 +116687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12735/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12735/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12728/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12728/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -116853,8 +116696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12736/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12736/14932 [18:05<03:07, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12729/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  85%|▊| 12729/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116862,8 +116705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12737/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  85%|▊| 12737/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  85%|▊| 12730/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12730/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -116871,8 +116714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12738/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  85%|▊| 12738/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12731/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12731/14932 [18:02<03:07, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -116880,8 +116723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12739/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  85%|▊| 12739/14932 [18:06<03:07, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12732/14932 [18:03<03:07, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  85%|▊| 12732/14932 [18:03<03:07, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -116889,8 +116732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12740/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12740/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  85%|▊| 12733/14932 [18:03<03:07, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  85%|▊| 12733/14932 [18:03<03:07, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -116898,8 +116741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12741/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  85%|▊| 12741/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  85%|▊| 12734/14932 [18:03<03:07, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12734/14932 [18:03<03:07, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -116907,8 +116750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12742/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  85%|▊| 12742/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  85%|▊| 12735/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12735/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -116916,8 +116759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12743/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  85%|▊| 12743/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  85%|▊| 12736/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  85%|▊| 12736/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -116925,8 +116768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12744/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  85%|▊| 12744/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  85%|▊| 12737/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  85%|▊| 12737/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -116934,8 +116777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12745/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  85%|▊| 12745/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  85%|▊| 12738/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12738/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -116943,8 +116786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12746/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  85%|▊| 12746/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  85%|▊| 12739/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  85%|▊| 12739/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -116952,8 +116795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12747/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  85%|▊| 12747/14932 [18:06<03:06, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  85%|▊| 12740/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12740/14932 [18:03<03:06, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -116961,8 +116804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12748/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  85%|▊| 12748/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12741/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  85%|▊| 12741/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -116970,8 +116813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12749/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12749/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12742/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  85%|▊| 12742/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -116979,8 +116822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12750/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12750/14932 [18:07<03:06, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12743/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  85%|▊| 12743/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -116988,8 +116831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12751/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12751/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12744/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  85%|▊| 12744/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -116997,8 +116840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12752/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  85%|▊| 12752/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  85%|▊| 12745/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  85%|▊| 12745/14932 [18:04<03:06, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -117006,8 +116849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12753/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  85%|▊| 12753/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  85%|▊| 12746/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12746/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -117015,8 +116858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12754/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  85%|▊| 12754/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  85%|▊| 12747/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  85%|▊| 12747/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117024,8 +116867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12755/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  85%|▊| 12755/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  85%|▊| 12748/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12748/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -117033,8 +116876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12756/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  85%|▊| 12756/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  85%|▊| 12749/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  85%|▊| 12749/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117042,8 +116885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12757/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  85%|▊| 12757/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  85%|▊| 12750/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12750/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -117051,8 +116894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12758/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  85%|▊| 12758/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12751/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  85%|▊| 12751/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117060,7 +116903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12759/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  85%|▊| 12752/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12752/14932 [18:04<03:05, 11.75it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -117068,7 +116912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12759/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  85%|▊| 12753/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  85%|▊| 12753/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117076,8 +116921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12760/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  85%|▊| 12760/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  85%|▊| 12754/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12754/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -117085,8 +116930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12761/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  85%|▊| 12761/14932 [18:07<03:05, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  85%|▊| 12755/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  85%|▊| 12755/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -117094,8 +116939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12762/14932 [18:08<03:05, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  85%|▊| 12762/14932 [18:08<03:05, 11.73it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  85%|▊| 12756/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  85%|▊| 12756/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117103,8 +116948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12763/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  85%|▊| 12763/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12757/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  85%|▊| 12757/14932 [18:05<03:05, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117112,8 +116957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12764/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12764/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12758/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  85%|▊| 12758/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117121,8 +116966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12765/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  85%|▊| 12765/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  85%|▊| 12759/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12759/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117130,8 +116975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  85%|▊| 12766/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  85%|▊| 12766/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  85%|▊| 12760/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  85%|▊| 12760/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -117139,8 +116984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12767/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  86%|▊| 12767/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  85%|▊| 12761/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  85%|▊| 12761/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -117148,8 +116993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12768/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  86%|▊| 12768/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  85%|▊| 12762/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  85%|▊| 12762/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117157,8 +117002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12769/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12769/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  85%|▊| 12763/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  85%|▊| 12763/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117166,8 +117011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12770/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12770/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  85%|▊| 12764/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  85%|▊| 12764/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117175,8 +117020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12771/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12771/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  85%|▊| 12765/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  85%|▊| 12765/14932 [18:05<03:04, 11.75it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117184,8 +117029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12772/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  86%|▊| 12772/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  85%|▊| 12766/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  85%|▊| 12766/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -117193,8 +117038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12773/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  86%|▊| 12773/14932 [18:08<03:04, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  86%|▊| 12767/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  86%|▊| 12767/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -117202,8 +117047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12774/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  86%|▊| 12774/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12768/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  86%|▊| 12768/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -117211,8 +117056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12775/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12775/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  86%|▊| 12769/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  86%|▊| 12769/14932 [18:06<03:04, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117220,8 +117065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12776/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  86%|▊| 12776/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  86%|▊| 12770/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  86%|▊| 12770/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117229,8 +117074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12777/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  86%|▊| 12777/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  86%|▊| 12771/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12771/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -117238,8 +117083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12778/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  86%|▊| 12778/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  86%|▊| 12772/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  86%|▊| 12772/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117247,8 +117092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12779/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  86%|▊| 12779/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  86%|▊| 12773/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12773/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -117256,8 +117101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12780/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  86%|▊| 12780/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12774/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  86%|▊| 12774/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -117265,8 +117110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12781/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12781/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12775/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  86%|▊| 12775/14932 [18:06<03:03, 11.75it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117274,8 +117119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12782/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12782/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  86%|▊| 12776/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12776/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117283,8 +117128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12783/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  86%|▊| 12783/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12777/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12777/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117292,8 +117137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12784/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12784/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12778/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  86%|▊| 12778/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117301,8 +117146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12785/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12785/14932 [18:09<03:03, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12779/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12779/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -117310,8 +117155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12786/14932 [18:09<03:02, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12786/14932 [18:09<03:02, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  86%|▊| 12780/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  86%|▊| 12780/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -117319,8 +117164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12787/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  86%|▊| 12787/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  86%|▊| 12781/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12781/14932 [18:07<03:03, 11.75it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117328,8 +117173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12788/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  86%|▊| 12788/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12782/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12782/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117337,8 +117182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12789/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  86%|▊| 12789/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12783/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12783/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -117346,8 +117191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12790/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  86%|▊| 12790/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12784/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  86%|▊| 12784/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117355,8 +117200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12791/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12791/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12785/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12785/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117364,8 +117209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12792/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12792/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12786/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12786/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117373,8 +117218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12793/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12793/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12787/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12787/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -117382,8 +117227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12794/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12794/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  86%|▊| 12788/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  86%|▊| 12788/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -117391,8 +117236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12795/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  86%|▊| 12795/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  86%|▊| 12789/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12789/14932 [18:07<03:02, 11.75it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -117400,8 +117245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12796/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  86%|▊| 12796/14932 [18:10<03:02, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12790/14932 [18:08<03:02, 11.75it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  86%|▊| 12790/14932 [18:08<03:02, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117409,8 +117254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12797/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  86%|▊| 12797/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12791/14932 [18:08<03:02, 11.75it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12791/14932 [18:08<03:02, 11.75it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117418,8 +117263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12798/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12798/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  86%|▊| 12792/14932 [18:08<03:02, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12792/14932 [18:08<03:02, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117427,8 +117272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12799/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  86%|▊| 12799/14932 [18:10<03:01, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  86%|▊| 12793/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12793/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -117436,8 +117281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12800/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  86%|▊| 12800/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12794/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  86%|▊| 12794/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -117445,8 +117290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12801/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12801/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  86%|▊| 12795/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  86%|▊| 12795/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -117454,8 +117299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12802/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  86%|▊| 12802/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12796/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12796/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117463,8 +117308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12803/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12803/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  86%|▊| 12797/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12797/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -117472,8 +117317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12804/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  86%|▊| 12804/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  86%|▊| 12798/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  86%|▊| 12798/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117481,8 +117326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12805/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  86%|▊| 12805/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12799/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12799/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -117490,8 +117335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12806/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12806/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  86%|▊| 12800/14932 [18:08<03:01, 11.75it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  86%|▊| 12800/14932 [18:08<03:01, 11.75it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -117499,8 +117344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12807/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  86%|▊| 12807/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12801/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  86%|▊| 12801/14932 [18:08<03:01, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117508,8 +117353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12808/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12808/14932 [18:11<03:01, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  86%|▊| 12802/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12802/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -117517,8 +117362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12809/14932 [18:11<03:00, 11.73it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  86%|▊| 12809/14932 [18:11<03:00, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12803/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  86%|▊| 12803/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117526,8 +117371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12810/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12810/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12804/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12804/14932 [18:09<03:01, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117535,8 +117380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12811/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  86%|▊| 12811/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12805/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12805/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117544,8 +117389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12812/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12812/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  86%|▊| 12806/14932 [18:09<03:00, 11.75it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12806/14932 [18:09<03:00, 11.75it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -117553,8 +117398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12813/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  86%|▊| 12813/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12807/14932 [18:09<03:00, 11.75it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12807/14932 [18:09<03:00, 11.75it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -117562,8 +117407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12814/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  86%|▊| 12814/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  86%|▊| 12808/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12808/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -117571,8 +117416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12815/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  86%|▊| 12815/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12809/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  86%|▊| 12809/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117580,8 +117425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12816/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12816/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12810/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12810/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -117589,8 +117434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12817/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12817/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  86%|▊| 12811/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  86%|▊| 12811/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -117598,8 +117443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12818/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  86%|▊| 12818/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  86%|▊| 12812/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  86%|▊| 12812/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117607,8 +117452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12819/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  86%|▊| 12819/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12813/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12813/14932 [18:09<03:00, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117616,8 +117461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12820/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12820/14932 [18:12<03:00, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12814/14932 [18:10<03:00, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12814/14932 [18:10<03:00, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -117625,8 +117470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12821/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  86%|▊| 12821/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12815/14932 [18:10<03:00, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12815/14932 [18:10<03:00, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -117634,8 +117479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12822/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12822/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  86%|▊| 12816/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  86%|▊| 12816/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -117643,8 +117488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12823/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  86%|▊| 12823/14932 [18:12<02:59, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12817/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  86%|▊| 12817/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117652,8 +117497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12824/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12824/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  86%|▊| 12818/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12818/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117661,8 +117506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12825/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  86%|▊| 12825/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  86%|▊| 12819/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12819/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -117670,8 +117515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12826/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  86%|▊| 12826/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12820/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  86%|▊| 12820/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117679,8 +117524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12827/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12827/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  86%|▊| 12821/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12821/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117688,8 +117533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12828/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  86%|▊| 12828/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12822/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12822/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -117697,8 +117542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12829/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12829/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12823/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  86%|▊| 12823/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117706,8 +117551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12830/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12830/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12824/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12824/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117715,8 +117560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12831/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12831/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12825/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12825/14932 [18:10<02:59, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -117724,8 +117569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12832/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12832/14932 [18:13<02:59, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  86%|▊| 12826/14932 [18:11<02:59, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  86%|▊| 12826/14932 [18:11<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117733,8 +117578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12833/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  86%|▊| 12833/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12827/14932 [18:11<02:59, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12827/14932 [18:11<02:59, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117742,8 +117587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12834/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12834/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12828/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12828/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -117751,8 +117596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12835/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12835/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  86%|▊| 12829/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12829/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117760,7 +117605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12836/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  86%|▊| 12830/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12830/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -117768,7 +117614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12836/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  86%|▊| 12831/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  86%|▊| 12831/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117776,8 +117623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12837/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  86%|▊| 12837/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  86%|▊| 12832/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12832/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -117785,8 +117632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12838/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  86%|▊| 12838/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  86%|▊| 12833/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  86%|▊| 12833/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117794,8 +117641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12839/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  86%|▊| 12839/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12834/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  86%|▊| 12834/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117803,8 +117650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12840/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12840/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12835/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12835/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -117812,8 +117659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12841/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12841/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  86%|▊| 12836/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12836/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -117821,8 +117668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12842/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  86%|▊| 12842/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  86%|▊| 12837/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12837/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -117830,8 +117677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12843/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  86%|▊| 12843/14932 [18:14<02:58, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  86%|▊| 12838/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  86%|▊| 12838/14932 [18:11<02:58, 11.76it/s, v_num=ui8w, train/loss=4.7"
      ]
     },
     {
@@ -117839,8 +117686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12844/14932 [18:14<02:57, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12844/14932 [18:14<02:57, 11.73it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  86%|▊| 12839/14932 [18:12<02:58, 11.76it/s, v_num=ui8w, train/loss=4.7\r",
+      "Epoch 0:  86%|▊| 12839/14932 [18:12<02:58, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117848,8 +117695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12845/14932 [18:14<02:57, 11.73it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  86%|▊| 12845/14932 [18:14<02:57, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  86%|▊| 12840/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12840/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -117857,7 +117704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12846/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  86%|▊| 12841/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  86%|▊| 12841/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117865,7 +117713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12846/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12842/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12842/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -117873,8 +117722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12847/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12847/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12843/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  86%|▊| 12843/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -117882,8 +117731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12848/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12848/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  86%|▊| 12844/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  86%|▊| 12844/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -117891,8 +117740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12849/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12849/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  86%|▊| 12845/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  86%|▊| 12845/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -117900,8 +117749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12850/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  86%|▊| 12850/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  86%|▊| 12846/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12846/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -117909,8 +117758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12851/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  86%|▊| 12851/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12847/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  86%|▊| 12847/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -117918,8 +117767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12852/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12852/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  86%|▊| 12848/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12848/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -117927,8 +117776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12853/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  86%|▊| 12853/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12849/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  86%|▊| 12849/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -117936,8 +117785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12854/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12854/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  86%|▊| 12850/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  86%|▊| 12850/14932 [18:12<02:57, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -117945,8 +117794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12855/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  86%|▊| 12855/14932 [18:15<02:57, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  86%|▊| 12851/14932 [18:12<02:56, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12851/14932 [18:12<02:56, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -117954,8 +117803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12856/14932 [18:15<02:56, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  86%|▊| 12856/14932 [18:15<02:56, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12852/14932 [18:12<02:56, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  86%|▊| 12852/14932 [18:12<02:56, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -117963,8 +117812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12857/14932 [18:15<02:56, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12857/14932 [18:15<02:56, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12853/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12853/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -117972,8 +117821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12858/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12858/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12854/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12854/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -117981,8 +117830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12859/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  86%|▊| 12859/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  86%|▊| 12855/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  86%|▊| 12855/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -117990,8 +117839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12860/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  86%|▊| 12860/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12856/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12856/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -117999,8 +117848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12861/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12861/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12857/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  86%|▊| 12857/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -118008,8 +117857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12862/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12862/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12858/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  86%|▊| 12858/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -118017,8 +117866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12863/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12863/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  86%|▊| 12859/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  86%|▊| 12859/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -118026,8 +117875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12864/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  86%|▊| 12864/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12860/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  86%|▊| 12860/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -118035,8 +117884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12865/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12865/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  86%|▊| 12861/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  86%|▊| 12861/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -118044,8 +117893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12866/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  86%|▊| 12866/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  86%|▊| 12862/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12862/14932 [18:13<02:56, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118053,8 +117902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12867/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  86%|▊| 12867/14932 [18:16<02:56, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  86%|▊| 12863/14932 [18:13<02:55, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12863/14932 [18:13<02:55, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118062,8 +117911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12868/14932 [18:16<02:55, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  86%|▊| 12868/14932 [18:16<02:55, 11.73it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  86%|▊| 12864/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12864/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118071,8 +117920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12869/14932 [18:16<02:55, 11.73it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  86%|▊| 12869/14932 [18:16<02:55, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  86%|▊| 12865/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12865/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -118080,8 +117929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12870/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12870/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  86%|▊| 12866/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  86%|▊| 12866/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118089,8 +117938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12871/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12871/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12867/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  86%|▊| 12867/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118098,8 +117947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12872/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12872/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  86%|▊| 12868/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  86%|▊| 12868/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -118107,8 +117956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12873/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  86%|▊| 12873/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12869/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12869/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -118116,8 +117965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12874/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  86%|▊| 12874/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  86%|▊| 12870/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  86%|▊| 12870/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -118125,8 +117974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12875/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  86%|▊| 12875/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  86%|▊| 12871/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  86%|▊| 12871/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=5.2"
      ]
     },
     {
@@ -118134,7 +117983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12876/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  86%|▊| 12872/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=5.2\r",
+      "Epoch 0:  86%|▊| 12872/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -118142,7 +117992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12876/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  86%|▊| 12873/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  86%|▊| 12873/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -118150,8 +118001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12877/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  86%|▊| 12877/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  86%|▊| 12874/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12874/14932 [18:14<02:55, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -118159,8 +118010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12878/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  86%|▊| 12878/14932 [18:17<02:55, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  86%|▊| 12875/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  86%|▊| 12875/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118168,8 +118019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12879/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  86%|▊| 12879/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  86%|▊| 12876/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12876/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -118177,8 +118028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12880/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12880/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12877/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  86%|▊| 12877/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -118186,8 +118037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12881/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12881/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12878/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12878/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -118195,8 +118046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12882/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  86%|▊| 12882/14932 [18:17<02:54, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12879/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  86%|▊| 12879/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -118204,8 +118055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12883/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  86%|▊| 12883/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  86%|▊| 12880/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12880/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -118213,8 +118064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12884/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  86%|▊| 12884/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  86%|▊| 12881/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  86%|▊| 12881/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -118222,8 +118073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12885/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  86%|▊| 12885/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  86%|▊| 12882/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12882/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -118231,8 +118082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12886/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12886/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  86%|▊| 12883/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  86%|▊| 12883/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -118240,8 +118091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12887/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  86%|▊| 12887/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  86%|▊| 12884/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  86%|▊| 12884/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -118249,8 +118100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12888/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12888/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12885/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  86%|▊| 12885/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -118258,8 +118109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12889/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12889/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  86%|▊| 12886/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  86%|▊| 12886/14932 [18:15<02:54, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118267,8 +118118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12890/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  86%|▊| 12890/14932 [18:18<02:54, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  86%|▊| 12887/14932 [18:15<02:53, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12887/14932 [18:15<02:53, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -118276,8 +118127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12891/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  86%|▊| 12891/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  86%|▊| 12888/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  86%|▊| 12888/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -118285,8 +118136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12892/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  86%|▊| 12892/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  86%|▊| 12889/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  86%|▊| 12889/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -118294,8 +118145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12893/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  86%|▊| 12893/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  86%|▊| 12890/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  86%|▊| 12890/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -118303,8 +118154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12894/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  86%|▊| 12894/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  86%|▊| 12891/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  86%|▊| 12891/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -118312,8 +118163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12895/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  86%|▊| 12895/14932 [18:18<02:53, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12892/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  86%|▊| 12892/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -118321,8 +118172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12896/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12896/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12893/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12893/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -118330,8 +118181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12897/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  86%|▊| 12897/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12894/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  86%|▊| 12894/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -118339,8 +118190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12898/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12898/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  86%|▊| 12895/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  86%|▊| 12895/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -118348,8 +118199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12899/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  86%|▊| 12899/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  86%|▊| 12896/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  86%|▊| 12896/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -118357,8 +118208,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12900/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12900/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12897/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -118366,8 +118216,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12901/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12901/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  86%|▊| 12897/14932 [18:16<02:53, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -118375,8 +118224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12902/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  86%|▊| 12902/14932 [18:19<02:53, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12898/14932 [18:17<02:53, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12898/14932 [18:17<02:53, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -118384,8 +118233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12903/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12903/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12899/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  86%|▊| 12899/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -118393,8 +118242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12904/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12904/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  86%|▊| 12900/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12900/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -118402,8 +118251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12905/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  86%|▊| 12905/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  86%|▊| 12901/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  86%|▊| 12901/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118411,8 +118260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12906/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  86%|▊| 12906/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  86%|▊| 12902/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  86%|▊| 12902/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -118420,8 +118269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12907/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  86%|▊| 12907/14932 [18:19<02:52, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  86%|▊| 12903/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  86%|▊| 12903/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -118429,8 +118278,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12908/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  86%|▊| 12908/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  86%|▊| 12904/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -118438,8 +118286,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12909/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  86%|▊| 12909/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12904/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -118447,8 +118294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12910/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12910/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  86%|▊| 12905/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12905/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -118456,8 +118303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12911/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  86%|▊| 12911/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  86%|▊| 12906/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  86%|▊| 12906/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -118465,8 +118312,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12912/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  86%|▊| 12912/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12907/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -118474,7 +118320,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12913/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  86%|▊| 12907/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118482,7 +118328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12913/14932 [18:20<02:52, 11.73it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  86%|▊| 12908/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12908/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118490,8 +118337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12914/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  86%|▊| 12914/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  86%|▊| 12909/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12909/14932 [18:17<02:52, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -118499,8 +118346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12915/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  86%|▊| 12915/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  86%|▊| 12910/14932 [18:17<02:51, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  86%|▊| 12910/14932 [18:17<02:51, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118508,8 +118355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  86%|▊| 12916/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  86%|▊| 12916/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12911/14932 [18:17<02:51, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12911/14932 [18:17<02:51, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -118517,7 +118364,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12917/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  86%|▊| 12912/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -118525,7 +118372,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12917/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  86%|▊| 12912/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118533,8 +118380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12918/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  87%|▊| 12918/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  86%|▊| 12913/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  86%|▊| 12913/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -118542,8 +118389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12919/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  87%|▊| 12919/14932 [18:20<02:51, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  86%|▊| 12914/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  86%|▊| 12914/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118551,8 +118398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12920/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  87%|▊| 12920/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  86%|▊| 12915/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  86%|▊| 12915/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -118560,8 +118407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12921/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 12921/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  86%|▊| 12916/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  86%|▊| 12916/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -118569,8 +118416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12922/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  87%|▊| 12922/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12917/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  87%|▊| 12917/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -118578,8 +118425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12923/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12923/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  87%|▊| 12918/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 12918/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -118587,8 +118434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12924/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  87%|▊| 12924/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  87%|▊| 12919/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  87%|▊| 12919/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -118596,8 +118443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12925/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  87%|▊| 12925/14932 [18:21<02:51, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 12920/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  87%|▊| 12920/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -118605,8 +118452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12926/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  87%|▊| 12926/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  87%|▊| 12921/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 12921/14932 [18:18<02:51, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -118614,8 +118461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12927/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  87%|▊| 12927/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 12922/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  87%|▊| 12922/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118623,8 +118470,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12928/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 12928/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12923/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118632,8 +118478,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12929/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12929/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  87%|▊| 12923/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118641,8 +118486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12930/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  87%|▊| 12930/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  87%|▊| 12924/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 12924/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -118650,8 +118495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12931/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  87%|▊| 12931/14932 [18:21<02:50, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  87%|▊| 12925/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 12925/14932 [18:18<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118659,8 +118504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12932/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  87%|▊| 12932/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 12926/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 12926/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -118668,8 +118513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12933/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 12933/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  87%|▊| 12927/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 12927/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -118677,8 +118522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12934/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  87%|▊| 12934/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 12928/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 12928/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -118686,8 +118531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12935/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 12935/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  87%|▊| 12929/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 12929/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -118695,8 +118540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12936/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  87%|▊| 12936/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 12930/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  87%|▊| 12930/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -118704,8 +118549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12937/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  87%|▊| 12937/14932 [18:22<02:50, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12931/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 12931/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -118713,8 +118558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12938/14932 [18:22<02:49, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12938/14932 [18:22<02:49, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 12932/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  87%|▊| 12932/14932 [18:19<02:50, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -118722,8 +118567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12939/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 12939/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12933/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 12933/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118731,8 +118576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12940/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12940/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 12934/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12934/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118740,8 +118585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12941/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  87%|▊| 12941/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  87%|▊| 12935/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12935/14932 [18:19<02:49, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118749,8 +118594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12942/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  87%|▊| 12942/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 12936/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 12936/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -118758,8 +118603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12943/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 12943/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12937/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 12937/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -118767,8 +118612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12944/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12944/14932 [18:22<02:49, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  87%|▊| 12938/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  87%|▊| 12938/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -118776,8 +118621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12945/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  87%|▊| 12945/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 12939/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  87%|▊| 12939/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -118785,8 +118630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12946/14932 [18:23<02:49, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 12946/14932 [18:23<02:49, 11.73it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  87%|▊| 12940/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  87%|▊| 12940/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -118794,8 +118639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12947/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  87%|▊| 12947/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 12941/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  87%|▊| 12941/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -118803,8 +118648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12948/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 12948/14932 [18:23<02:49, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12942/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 12942/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -118812,8 +118657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12949/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12949/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 12943/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 12943/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -118821,8 +118666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12950/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 12950/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  87%|▊| 12944/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 12944/14932 [18:20<02:49, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -118830,8 +118675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12951/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  87%|▊| 12951/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12945/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  87%|▊| 12945/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118839,8 +118684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12952/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12952/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  87%|▊| 12946/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 12946/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -118848,8 +118693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12953/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  87%|▊| 12953/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 12947/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 12947/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -118857,8 +118702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12954/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 12954/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 12948/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 12948/14932 [18:20<02:48, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -118866,8 +118711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12955/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 12955/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 12949/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 12949/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -118875,8 +118720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12956/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 12956/14932 [18:23<02:48, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  87%|▊| 12950/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 12950/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -118884,8 +118729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12957/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  87%|▊| 12957/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 12951/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  87%|▊| 12951/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -118893,8 +118738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12958/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 12958/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  87%|▊| 12952/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  87%|▊| 12952/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -118902,8 +118747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12959/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  87%|▊| 12959/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12953/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 12953/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118911,8 +118756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12960/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12960/14932 [18:24<02:48, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  87%|▊| 12954/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12954/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -118920,8 +118765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12961/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  87%|▊| 12961/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  87%|▊| 12955/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 12955/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -118929,7 +118774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12962/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  87%|▊| 12956/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  87%|▊| 12956/14932 [18:21<02:48, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -118937,7 +118783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12962/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  87%|▊| 12957/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12957/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -118945,8 +118792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12963/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  87%|▊| 12963/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 12958/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  87%|▊| 12958/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -118954,8 +118801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12964/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 12964/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12959/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 12959/14932 [18:21<02:47, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -118963,7 +118810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12965/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12960/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  87%|▊| 12960/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -118971,7 +118819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12965/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  87%|▊| 12961/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  87%|▊| 12961/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -118979,8 +118828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12966/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  87%|▊| 12966/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  87%|▊| 12962/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  87%|▊| 12962/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -118988,8 +118837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12967/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  87%|▊| 12967/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  87%|▊| 12963/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  87%|▊| 12963/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -118997,8 +118846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12968/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  87%|▊| 12968/14932 [18:24<02:47, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12964/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  87%|▊| 12964/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -119006,8 +118855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12969/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12969/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 12965/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  87%|▊| 12965/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -119015,8 +118864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12970/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 12970/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  87%|▊| 12966/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  87%|▊| 12966/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119024,8 +118873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12971/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  87%|▊| 12971/14932 [18:25<02:47, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 12967/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  87%|▊| 12967/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119033,8 +118882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12972/14932 [18:25<02:47, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  87%|▊| 12972/14932 [18:25<02:47, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 12968/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 12968/14932 [18:22<02:47, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119042,8 +118891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12973/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 12973/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 12969/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 12969/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -119051,8 +118900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12974/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 12974/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 12970/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  87%|▊| 12970/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -119060,8 +118909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12975/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 12975/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  87%|▊| 12971/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  87%|▊| 12971/14932 [18:22<02:46, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119069,8 +118918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12976/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  87%|▊| 12976/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  87%|▊| 12972/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12972/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -119078,8 +118927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12977/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  87%|▊| 12977/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 12973/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  87%|▊| 12973/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -119087,8 +118936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12978/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 12978/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 12974/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  87%|▊| 12974/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119096,8 +118945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12979/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 12979/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12975/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  87%|▊| 12975/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -119105,8 +118954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12980/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12980/14932 [18:25<02:46, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  87%|▊| 12976/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 12976/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119114,8 +118963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12981/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  87%|▊| 12981/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12977/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 12977/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -119123,8 +118972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12982/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 12982/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 12978/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  87%|▊| 12978/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119132,8 +118981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12983/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 12983/14932 [18:26<02:46, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12979/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 12979/14932 [18:23<02:46, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -119141,8 +118990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12984/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12984/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  87%|▊| 12980/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  87%|▊| 12980/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -119150,8 +118999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12985/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  87%|▊| 12985/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  87%|▊| 12981/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  87%|▊| 12981/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -119159,8 +119008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12986/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  87%|▊| 12986/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  87%|▊| 12982/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  87%|▊| 12982/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -119168,8 +119017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12987/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  87%|▊| 12987/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  87%|▊| 12983/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  87%|▊| 12983/14932 [18:23<02:45, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119177,8 +119026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12988/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  87%|▊| 12988/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 12984/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 12984/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119186,8 +119035,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12989/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 12989/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 12985/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119195,8 +119043,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12990/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  87%|▊| 12990/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 12985/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119204,8 +119051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12991/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  87%|▊| 12991/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 12986/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 12986/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -119213,8 +119060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12992/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 12992/14932 [18:26<02:45, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12987/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 12987/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -119222,8 +119069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12993/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12993/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  87%|▊| 12988/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  87%|▊| 12988/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119231,8 +119078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12994/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  87%|▊| 12994/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  87%|▊| 12989/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 12989/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -119240,8 +119087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12995/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  87%|▊| 12995/14932 [18:27<02:45, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  87%|▊| 12990/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  87%|▊| 12990/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119249,8 +119096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12996/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  87%|▊| 12996/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  87%|▊| 12991/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 12991/14932 [18:24<02:45, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -119258,8 +119105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12997/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  87%|▊| 12997/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  87%|▊| 12992/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  87%|▊| 12992/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119267,8 +119114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12998/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  87%|▊| 12998/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 12993/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 12993/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119276,8 +119123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 12999/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 12999/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 12994/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 12994/14932 [18:24<02:44, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -119285,8 +119132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13000/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 13000/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  87%|▊| 12995/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  87%|▊| 12995/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -119294,8 +119141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13001/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  87%|▊| 13001/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 12996/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  87%|▊| 12996/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119303,8 +119150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13002/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 13002/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 12997/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 12997/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -119312,7 +119159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13003/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 12998/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  87%|▊| 12998/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119320,7 +119168,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13003/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 12999/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119328,8 +119176,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13004/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 13004/14932 [18:27<02:44, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 12999/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -119337,8 +119184,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13005/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 13005/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  87%|▊| 13000/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 13000/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119346,8 +119193,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13006/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  87%|▊| 13006/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  87%|▊| 13001/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119355,8 +119201,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13007/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  87%|▊| 13007/14932 [18:28<02:44, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  87%|▊| 13001/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -119364,8 +119209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13008/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  87%|▊| 13008/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 13002/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  87%|▊| 13002/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119373,8 +119218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13009/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 13009/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 13003/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 13003/14932 [18:25<02:44, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119382,8 +119227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13010/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 13010/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 13004/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13004/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119391,8 +119236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13011/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 13011/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  87%|▊| 13005/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 13005/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -119400,8 +119245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13012/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  87%|▊| 13012/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13006/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 13006/14932 [18:25<02:43, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119409,8 +119254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13013/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13013/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 13007/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13007/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -119418,8 +119263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13014/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 13014/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 13008/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 13008/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119427,8 +119272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13015/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 13015/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 13009/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 13009/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119436,8 +119281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13016/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 13016/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 13010/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13010/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119445,8 +119290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13017/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 13017/14932 [18:28<02:43, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13011/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 13011/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119454,8 +119299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13018/14932 [18:29<02:43, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13018/14932 [18:29<02:43, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  87%|▊| 13012/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 13012/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -119463,8 +119308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13019/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  87%|▊| 13019/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  87%|▊| 13013/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  87%|▊| 13013/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119472,8 +119317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13020/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  87%|▊| 13020/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  87%|▊| 13014/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13014/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -119481,8 +119326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13021/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  87%|▊| 13021/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  87%|▊| 13015/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  87%|▊| 13015/14932 [18:26<02:43, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119490,8 +119335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13022/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  87%|▊| 13022/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 13016/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 13016/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -119499,8 +119344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13023/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 13023/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  87%|▊| 13017/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  87%|▊| 13017/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -119508,8 +119353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13024/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  87%|▊| 13024/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 13018/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  87%|▊| 13018/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119517,8 +119362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13025/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  87%|▊| 13025/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 13019/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 13019/14932 [18:26<02:42, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119526,8 +119371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13026/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 13026/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  87%|▊| 13020/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13020/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -119535,7 +119380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13027/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  87%|▊| 13021/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  87%|▊| 13021/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119543,7 +119389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13027/14932 [18:29<02:42, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  87%|▊| 13022/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 13022/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119551,8 +119398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13028/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  87%|▊| 13028/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  87%|▊| 13023/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  87%|▊| 13023/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -119560,8 +119407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13029/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  87%|▊| 13029/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 13024/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  87%|▊| 13024/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -119569,8 +119416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13030/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 13030/14932 [18:30<02:42, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 13025/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  87%|▊| 13025/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -119578,8 +119425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13031/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 13031/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  87%|▊| 13026/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 13026/14932 [18:27<02:42, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119587,8 +119434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13032/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  87%|▊| 13032/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13027/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13027/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119596,8 +119443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13033/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13033/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  87%|▊| 13028/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13028/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119605,8 +119452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13034/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  87%|▊| 13034/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13029/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13029/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -119614,8 +119461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13035/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13035/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 13030/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  87%|▊| 13030/14932 [18:27<02:41, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119623,8 +119470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13036/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  87%|▊| 13036/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  87%|▊| 13031/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 13031/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119632,8 +119479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13037/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  87%|▊| 13037/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  87%|▊| 13032/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13032/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -119641,8 +119488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13038/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  87%|▊| 13038/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 13033/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 13033/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119650,8 +119497,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13039/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 13039/14932 [18:30<02:41, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  87%|▊| 13034/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119659,8 +119505,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13040/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  87%|▊| 13040/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 13034/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -119668,8 +119513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13041/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 13041/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  87%|▊| 13035/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  87%|▊| 13035/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119677,8 +119522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13042/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  87%|▊| 13042/14932 [18:31<02:41, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  87%|▊| 13036/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13036/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -119686,8 +119531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13043/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  87%|▊| 13043/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 13037/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  87%|▊| 13037/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -119695,8 +119540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13044/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 13044/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 13038/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  87%|▊| 13038/14932 [18:28<02:41, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -119704,8 +119549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13045/14932 [18:31<02:40, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 13045/14932 [18:31<02:40, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 13039/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  87%|▊| 13039/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119713,8 +119558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13046/14932 [18:31<02:40, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 13046/14932 [18:31<02:40, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13040/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 13040/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119722,8 +119567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13047/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13047/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 13041/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13041/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -119731,8 +119576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13048/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 13048/14932 [18:31<02:40, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  87%|▊| 13042/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  87%|▊| 13042/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -119740,8 +119585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13049/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  87%|▊| 13049/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  87%|▊| 13043/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 13043/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119749,8 +119594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13050/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  87%|▊| 13050/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  87%|▊| 13044/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 13044/14932 [18:28<02:40, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -119758,8 +119603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13051/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  87%|▊| 13051/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  87%|▊| 13045/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  87%|▊| 13045/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -119767,8 +119612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13052/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  87%|▊| 13052/14932 [18:32<02:40, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  87%|▊| 13046/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  87%|▊| 13046/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -119776,8 +119621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13053/14932 [18:32<02:40, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  87%|▊| 13053/14932 [18:32<02:40, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  87%|▊| 13047/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  87%|▊| 13047/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -119785,8 +119630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13054/14932 [18:32<02:40, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  87%|▊| 13054/14932 [18:32<02:40, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  87%|▊| 13048/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 13048/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -119794,8 +119639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13055/14932 [18:32<02:39, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  87%|▊| 13055/14932 [18:32<02:39, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  87%|▊| 13049/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  87%|▊| 13049/14932 [18:29<02:40, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119803,8 +119648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13056/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  87%|▊| 13056/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  87%|▊| 13050/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 13050/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119812,8 +119657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13057/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  87%|▊| 13057/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 13051/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 13051/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119821,8 +119666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13058/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  87%|▊| 13058/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  87%|▊| 13052/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  87%|▊| 13052/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119830,8 +119675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13059/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  87%|▊| 13059/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  87%|▊| 13053/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  87%|▊| 13053/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119839,8 +119684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13060/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  87%|▊| 13060/14932 [18:32<02:39, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  87%|▊| 13054/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 13054/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119848,8 +119693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13061/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  87%|▊| 13061/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  87%|▊| 13055/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 13055/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -119857,8 +119702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13062/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  87%|▊| 13062/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  87%|▊| 13056/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  87%|▊| 13056/14932 [18:29<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119866,8 +119711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13063/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  87%|▊| 13063/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 13057/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  87%|▊| 13057/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -119875,8 +119720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13064/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  87%|▊| 13064/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  87%|▊| 13058/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  87%|▊| 13058/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119884,8 +119729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  87%|▊| 13065/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  87%|▊| 13065/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  87%|▊| 13059/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13059/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119893,8 +119738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13066/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13066/14932 [18:33<02:39, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  87%|▊| 13060/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13060/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119902,8 +119747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13067/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13067/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  87%|▊| 13061/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  87%|▊| 13061/14932 [18:30<02:39, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -119911,8 +119756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13068/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  88%|▉| 13068/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  87%|▊| 13062/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 13062/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -119920,8 +119765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13069/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  88%|▉| 13069/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  87%|▊| 13063/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  87%|▊| 13063/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -119929,8 +119774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13070/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13070/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  87%|▊| 13064/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  87%|▊| 13064/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119938,8 +119783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13071/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13071/14932 [18:33<02:38, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  87%|▊| 13065/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  87%|▊| 13065/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -119947,8 +119792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13072/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13072/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  88%|▉| 13066/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13066/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -119956,8 +119801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13073/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  88%|▉| 13073/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  88%|▉| 13067/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13067/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -119965,8 +119810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13074/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  88%|▉| 13074/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13068/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13068/14932 [18:30<02:38, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -119974,8 +119819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13075/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13075/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  88%|▉| 13069/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  88%|▉| 13069/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -119983,8 +119828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13076/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  88%|▉| 13076/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13070/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  88%|▉| 13070/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -119992,8 +119837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13077/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13077/14932 [18:34<02:38, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13071/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13071/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -120001,8 +119846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13078/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13078/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13072/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  88%|▉| 13072/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120010,8 +119855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13079/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13079/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13073/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13073/14932 [18:31<02:38, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -120019,8 +119864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13080/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13080/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  88%|▉| 13074/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  88%|▉| 13074/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -120028,8 +119873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13081/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  88%|▉| 13081/14932 [18:34<02:37, 11.73it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  88%|▉| 13075/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13075/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -120037,8 +119882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13082/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  88%|▉| 13082/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13076/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13076/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -120046,8 +119891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13083/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13083/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  88%|▉| 13077/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  88%|▉| 13077/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120055,8 +119900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13084/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  88%|▉| 13084/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13078/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13078/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120064,8 +119909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13085/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13085/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  88%|▉| 13079/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13079/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -120073,8 +119918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13086/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13086/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  88%|▉| 13080/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13080/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -120082,8 +119927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13087/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  88%|▉| 13087/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  88%|▉| 13081/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  88%|▉| 13081/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120091,8 +119936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13088/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  88%|▉| 13088/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  88%|▉| 13082/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13082/14932 [18:31<02:37, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -120100,8 +119945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13089/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  88%|▉| 13089/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  88%|▉| 13083/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  88%|▉| 13083/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -120109,8 +119954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13090/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  88%|▉| 13090/14932 [18:35<02:37, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13084/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13084/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120118,8 +119963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13091/14932 [18:35<02:36, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13091/14932 [18:35<02:36, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13085/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13085/14932 [18:32<02:37, 11.76it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -120127,8 +119972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13092/14932 [18:35<02:36, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13092/14932 [18:35<02:36, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13086/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  88%|▉| 13086/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -120136,8 +119981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13093/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13093/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  88%|▉| 13087/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  88%|▉| 13087/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -120145,8 +119990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13094/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  88%|▉| 13094/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  88%|▉| 13088/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  88%|▉| 13088/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120154,8 +119999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13095/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13095/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13089/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13089/14932 [18:32<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120163,8 +120008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13096/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13096/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  88%|▉| 13090/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13090/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120172,8 +120017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13097/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  88%|▉| 13097/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13091/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13091/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120181,8 +120026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13098/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13098/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13092/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13092/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120190,8 +120035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13099/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13099/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13093/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13093/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -120199,8 +120044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13100/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13100/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13094/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13094/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120208,8 +120053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13101/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13101/14932 [18:36<02:36, 11.73it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13095/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13095/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120217,8 +120062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13102/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13102/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  88%|▉| 13096/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13096/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -120226,8 +120071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13103/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  88%|▉| 13103/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  88%|▉| 13097/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  88%|▉| 13097/14932 [18:33<02:36, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -120235,8 +120080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13104/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  88%|▉| 13104/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13098/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  88%|▉| 13098/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -120244,8 +120089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13105/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13105/14932 [18:36<02:35, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13099/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13099/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -120253,8 +120098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13106/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13106/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13100/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  88%|▉| 13100/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120262,7 +120107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13107/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13101/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13101/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120270,7 +120116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13107/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13102/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13102/14932 [18:33<02:35, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -120278,8 +120125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13108/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13108/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13103/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13103/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -120287,8 +120134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13109/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13109/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  88%|▉| 13104/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  88%|▉| 13104/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120296,8 +120143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13110/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  88%|▉| 13110/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13105/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13105/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -120305,8 +120152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13111/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13111/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13106/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13106/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120314,8 +120161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13112/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13112/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  88%|▉| 13107/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13107/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -120323,8 +120170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13113/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13113/14932 [18:37<02:35, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13108/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  88%|▉| 13108/14932 [18:34<02:35, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120332,8 +120179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13114/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13114/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13109/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13109/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120341,8 +120188,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13115/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13115/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  88%|▉| 13110/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120350,8 +120196,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13116/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  88%|▉| 13116/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  88%|▉| 13110/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -120359,8 +120204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13117/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  88%|▉| 13117/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  88%|▉| 13111/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  88%|▉| 13111/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -120368,8 +120213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13118/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  88%|▉| 13118/14932 [18:37<02:34, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13112/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13112/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -120377,8 +120222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13119/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13119/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13113/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  88%|▉| 13113/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -120386,8 +120231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13120/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13120/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13114/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  88%|▉| 13114/14932 [18:34<02:34, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120395,8 +120240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13121/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13121/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  88%|▉| 13115/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13115/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -120404,8 +120249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13122/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  88%|▉| 13122/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  88%|▉| 13116/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  88%|▉| 13116/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120413,8 +120258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13123/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  88%|▉| 13123/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13117/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13117/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -120422,8 +120267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13124/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13124/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  88%|▉| 13118/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  88%|▉| 13118/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120431,8 +120276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13125/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  88%|▉| 13125/14932 [18:38<02:34, 11.73it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13119/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13119/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120440,8 +120285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13126/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13126/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13120/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13120/14932 [18:35<02:34, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -120449,8 +120294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13127/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13127/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13121/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  88%|▉| 13121/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -120458,8 +120303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13128/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13128/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  88%|▉| 13122/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13122/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -120467,8 +120312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13129/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  88%|▉| 13129/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  88%|▉| 13123/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  88%|▉| 13123/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120476,8 +120321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13130/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  88%|▉| 13130/14932 [18:38<02:33, 11.73it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  88%|▉| 13124/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13124/14932 [18:35<02:33, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -120485,8 +120330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13131/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  88%|▉| 13131/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  88%|▉| 13125/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  88%|▉| 13125/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120494,8 +120339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13132/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  88%|▉| 13132/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13126/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13126/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -120503,8 +120348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13133/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13133/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  88%|▉| 13127/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13127/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -120512,8 +120357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13134/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  88%|▉| 13134/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  88%|▉| 13128/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  88%|▉| 13128/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -120521,8 +120366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13135/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  88%|▉| 13135/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13129/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13129/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -120530,8 +120375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13136/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13136/14932 [18:39<02:33, 11.73it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  88%|▉| 13130/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  88%|▉| 13130/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -120539,8 +120384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13137/14932 [18:39<02:32, 11.73it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  88%|▉| 13137/14932 [18:39<02:32, 11.73it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  88%|▉| 13131/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  88%|▉| 13131/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120548,8 +120393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13138/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  88%|▉| 13138/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13132/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13132/14932 [18:36<02:33, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -120557,8 +120402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13139/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13139/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  88%|▉| 13133/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13133/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -120566,8 +120411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13140/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  88%|▉| 13140/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  88%|▉| 13134/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  88%|▉| 13134/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120575,8 +120420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13141/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  88%|▉| 13141/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13135/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13135/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120584,8 +120429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13142/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13142/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13136/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13136/14932 [18:36<02:32, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -120593,8 +120438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13143/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13143/14932 [18:39<02:32, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13137/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  88%|▉| 13137/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120602,8 +120447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13144/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13144/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13138/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13138/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120611,8 +120456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13145/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13145/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  88%|▉| 13139/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13139/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120620,8 +120465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13146/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  88%|▉| 13146/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13140/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13140/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120629,8 +120474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13147/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13147/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  88%|▉| 13141/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13141/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120638,8 +120483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13148/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  88%|▉| 13148/14932 [18:40<02:32, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13142/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13142/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -120647,8 +120492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13149/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13149/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13143/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  88%|▉| 13143/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120656,8 +120501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13150/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13150/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13144/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13144/14932 [18:37<02:32, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -120665,8 +120510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13151/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13151/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13145/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  88%|▉| 13145/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120674,8 +120519,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13152/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13152/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  88%|▉| 13146/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13146/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120683,8 +120528,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13153/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  88%|▉| 13153/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13147/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13147/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120692,8 +120537,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13154/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13154/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13148/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13148/14932 [18:37<02:31, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -120701,8 +120546,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13155/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13155/14932 [18:40<02:31, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13149/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  88%|▉| 13149/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -120710,8 +120555,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13156/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13156/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  88%|▉| 13150/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  88%|▉| 13150/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -120719,8 +120564,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13157/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  88%|▉| 13157/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13151/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  88%|▉| 13151/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -120728,8 +120573,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13158/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13158/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  88%|▉| 13152/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  88%|▉| 13152/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120737,8 +120582,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13159/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  88%|▉| 13159/14932 [18:41<02:31, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13153/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13153/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -120746,8 +120591,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13160/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13160/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  88%|▉| 13154/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13154/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120755,8 +120600,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13161/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  88%|▉| 13161/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  88%|▉| 13155/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13155/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120764,8 +120609,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13162/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  88%|▉| 13162/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  88%|▉| 13156/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13156/14932 [18:38<02:31, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -120773,8 +120618,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13163/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  88%|▉| 13163/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13157/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  88%|▉| 13157/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -120782,8 +120627,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13164/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13164/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  88%|▉| 13158/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13158/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -120791,8 +120636,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13165/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13165/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13159/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  88%|▉| 13159/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -120800,8 +120645,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13166/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13166/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  88%|▉| 13160/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  88%|▉| 13160/14932 [18:38<02:30, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -120809,8 +120654,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13167/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  88%|▉| 13167/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  88%|▉| 13161/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  88%|▉| 13161/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120818,8 +120663,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13168/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  88%|▉| 13168/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13162/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13162/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -120827,8 +120672,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13169/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13169/14932 [18:41<02:30, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  88%|▉| 13163/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13163/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -120836,8 +120681,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13170/14932 [18:42<02:30, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  88%|▉| 13170/14932 [18:42<02:30, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13164/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  88%|▉| 13164/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120845,8 +120690,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13171/14932 [18:42<02:30, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  88%|▉| 13171/14932 [18:42<02:30, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  88%|▉| 13165/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13165/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -120854,8 +120699,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13172/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  88%|▉| 13172/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13166/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  88%|▉| 13166/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -120863,8 +120708,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13173/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13173/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13167/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13167/14932 [18:39<02:30, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120872,8 +120717,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13174/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13174/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13168/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13168/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -120881,8 +120726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13175/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13175/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13169/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  88%|▉| 13169/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -120890,8 +120735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13176/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13176/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13170/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  88%|▉| 13170/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -120899,8 +120744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13177/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13177/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  88%|▉| 13171/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  88%|▉| 13171/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -120908,8 +120753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13178/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  88%|▉| 13178/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13172/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13172/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120917,8 +120762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13179/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13179/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  88%|▉| 13173/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13173/14932 [18:39<02:29, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -120926,8 +120771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13180/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  88%|▉| 13180/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13174/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13174/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -120935,8 +120780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13181/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13181/14932 [18:42<02:29, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13175/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13175/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -120944,8 +120789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13182/14932 [18:43<02:29, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13182/14932 [18:43<02:29, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13176/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  88%|▉| 13176/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -120953,8 +120798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13183/14932 [18:43<02:29, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13183/14932 [18:43<02:29, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13177/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  88%|▉| 13177/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -120962,7 +120807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13184/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13178/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  88%|▉| 13178/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -120970,7 +120816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13184/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13179/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13179/14932 [18:40<02:29, 11.76it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -120978,8 +120825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13185/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13185/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13180/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  88%|▉| 13180/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -120987,8 +120834,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13186/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13186/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  88%|▉| 13181/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -120996,8 +120842,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13187/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  88%|▉| 13187/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  88%|▉| 13181/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121005,8 +120850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13188/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  88%|▉| 13188/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13182/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13182/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121014,8 +120859,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13189/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  88%|▉| 13189/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  88%|▉| 13183/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121023,8 +120867,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13190/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  88%|▉| 13190/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  88%|▉| 13183/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -121032,8 +120875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13191/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  88%|▉| 13191/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13184/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  88%|▉| 13184/14932 [18:40<02:28, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121041,8 +120884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13192/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13192/14932 [18:43<02:28, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  88%|▉| 13185/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13185/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -121050,8 +120893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13193/14932 [18:44<02:28, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  88%|▉| 13193/14932 [18:44<02:28, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  88%|▉| 13186/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  88%|▉| 13186/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -121059,8 +120902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13194/14932 [18:44<02:28, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  88%|▉| 13194/14932 [18:44<02:28, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  88%|▉| 13187/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13187/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121068,8 +120911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13195/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  88%|▉| 13195/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  88%|▉| 13188/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13188/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -121077,8 +120920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13196/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  88%|▉| 13196/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13189/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  88%|▉| 13189/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121086,8 +120929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13197/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13197/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  88%|▉| 13190/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  88%|▉| 13190/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -121095,8 +120938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13198/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  88%|▉| 13198/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13191/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  88%|▉| 13191/14932 [18:41<02:28, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121104,8 +120947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13199/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13199/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  88%|▉| 13192/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13192/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -121113,8 +120956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13200/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  88%|▉| 13200/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  88%|▉| 13193/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  88%|▉| 13193/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -121122,8 +120965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13201/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  88%|▉| 13201/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  88%|▉| 13194/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  88%|▉| 13194/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -121131,8 +120974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13202/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  88%|▉| 13202/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  88%|▉| 13195/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  88%|▉| 13195/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -121140,8 +120983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13203/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  88%|▉| 13203/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  88%|▉| 13196/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  88%|▉| 13196/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -121149,8 +120992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13204/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  88%|▉| 13204/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  88%|▉| 13197/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  88%|▉| 13197/14932 [18:41<02:27, 11.76it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -121158,8 +121001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13205/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  88%|▉| 13205/14932 [18:44<02:27, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  88%|▉| 13198/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  88%|▉| 13198/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121167,8 +121010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13206/14932 [18:45<02:27, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  88%|▉| 13206/14932 [18:45<02:27, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  88%|▉| 13199/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13199/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -121176,8 +121019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13207/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  88%|▉| 13207/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  88%|▉| 13200/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  88%|▉| 13200/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121185,8 +121028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13208/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  88%|▉| 13208/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  88%|▉| 13201/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  88%|▉| 13201/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121194,8 +121037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13209/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  88%|▉| 13209/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  88%|▉| 13202/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  88%|▉| 13202/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -121203,8 +121046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13210/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  88%|▉| 13210/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  88%|▉| 13203/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  88%|▉| 13203/14932 [18:42<02:27, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121212,8 +121055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13211/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  88%|▉| 13211/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  88%|▉| 13204/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  88%|▉| 13204/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -121221,8 +121064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13212/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  88%|▉| 13212/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  88%|▉| 13205/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  88%|▉| 13205/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -121230,8 +121073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13213/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  88%|▉| 13213/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13206/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  88%|▉| 13206/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121239,8 +121082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  88%|▉| 13214/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  88%|▉| 13214/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13207/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13207/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121248,8 +121091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13215/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13215/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  88%|▉| 13208/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  88%|▉| 13208/14932 [18:42<02:26, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -121257,8 +121100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13216/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13216/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  88%|▉| 13209/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  88%|▉| 13209/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121266,8 +121109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13217/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  89%|▉| 13217/14932 [18:45<02:26, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  88%|▉| 13210/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13210/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121275,8 +121118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13218/14932 [18:46<02:26, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13218/14932 [18:46<02:26, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  88%|▉| 13211/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13211/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -121284,8 +121127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13219/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  89%|▉| 13219/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  88%|▉| 13212/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  88%|▉| 13212/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -121293,8 +121136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13220/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  89%|▉| 13220/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  88%|▉| 13213/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  88%|▉| 13213/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121302,8 +121145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13221/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13221/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  88%|▉| 13214/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  88%|▉| 13214/14932 [18:43<02:26, 11.76it/s, v_num=ui8w, train/loss=4.8"
      ]
     },
     {
@@ -121311,8 +121154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13222/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13222/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13215/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=4.8\r",
+      "Epoch 0:  89%|▉| 13215/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121320,8 +121163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13223/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13223/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  89%|▉| 13216/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13216/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -121329,8 +121172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13224/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  89%|▉| 13224/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13217/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  89%|▉| 13217/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -121338,8 +121181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13225/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13225/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13218/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13218/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -121347,8 +121190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13226/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13226/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  89%|▉| 13219/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13219/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -121356,8 +121199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13227/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  89%|▉| 13227/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  89%|▉| 13220/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  89%|▉| 13220/14932 [18:43<02:25, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -121365,8 +121208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13228/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  89%|▉| 13228/14932 [18:46<02:25, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13221/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  89%|▉| 13221/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -121374,8 +121217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13229/14932 [18:47<02:25, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13229/14932 [18:47<02:25, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13222/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  89%|▉| 13222/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -121383,8 +121226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13230/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13230/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  89%|▉| 13223/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  89%|▉| 13223/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -121392,7 +121235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13231/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  89%|▉| 13224/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13224/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -121400,7 +121244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13231/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  89%|▉| 13225/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  89%|▉| 13225/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -121408,8 +121253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13232/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  89%|▉| 13232/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13226/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  89%|▉| 13226/14932 [18:44<02:25, 11.76it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -121417,8 +121262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13233/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13233/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13227/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  89%|▉| 13227/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -121426,8 +121271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13234/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13234/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13228/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13228/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121435,8 +121280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13235/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13235/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13229/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13229/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -121444,8 +121289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13236/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13236/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13230/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  89%|▉| 13230/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -121453,8 +121298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13237/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13237/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13231/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13231/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121462,8 +121307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13238/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  89%|▉| 13238/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13232/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13232/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121471,8 +121316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13239/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13239/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13233/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13233/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -121480,8 +121325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13240/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13240/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13234/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  89%|▉| 13234/14932 [18:44<02:24, 11.76it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121489,8 +121334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13241/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13241/14932 [18:47<02:24, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13235/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  89%|▉| 13235/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -121498,8 +121343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13242/14932 [18:47<02:23, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13242/14932 [18:47<02:23, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13236/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  89%|▉| 13236/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -121507,8 +121352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13243/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13243/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13237/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13237/14932 [18:45<02:24, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121516,8 +121361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13244/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  89%|▉| 13244/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  89%|▉| 13238/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13238/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -121525,8 +121370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13245/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  89%|▉| 13245/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13239/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  89%|▉| 13239/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -121534,8 +121379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13246/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13246/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  89%|▉| 13240/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  89%|▉| 13240/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121543,8 +121388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13247/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  89%|▉| 13247/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13241/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13241/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121552,8 +121397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13248/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13248/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13242/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13242/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -121561,8 +121406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13249/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13249/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  89%|▉| 13243/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13243/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -121570,8 +121415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13250/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  89%|▉| 13250/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13244/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  89%|▉| 13244/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -121579,8 +121424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13251/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  89%|▉| 13251/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  89%|▉| 13245/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  89%|▉| 13245/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -121588,8 +121433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13252/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  89%|▉| 13252/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13246/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13246/14932 [18:45<02:23, 11.76it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -121597,8 +121442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13253/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13253/14932 [18:48<02:23, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13247/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  89%|▉| 13247/14932 [18:45<02:23, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121606,8 +121451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13254/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13254/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13248/14932 [18:46<02:23, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13248/14932 [18:46<02:23, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121615,8 +121460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13255/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13255/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13249/14932 [18:46<02:23, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13249/14932 [18:46<02:23, 11.76it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -121624,8 +121469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13256/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13256/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13250/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  89%|▉| 13250/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121633,8 +121478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13257/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13257/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13251/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13251/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -121642,8 +121487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13258/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13258/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  89%|▉| 13252/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  89%|▉| 13252/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121651,8 +121496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13259/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  89%|▉| 13259/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13253/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13253/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -121660,8 +121505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13260/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13260/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  89%|▉| 13254/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  89%|▉| 13254/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -121669,8 +121514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13261/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  89%|▉| 13261/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13255/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  89%|▉| 13255/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -121678,8 +121523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13262/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13262/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13256/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13256/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121687,8 +121532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13263/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13263/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13257/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13257/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -121696,8 +121541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13264/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13264/14932 [18:49<02:22, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  89%|▉| 13258/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13258/14932 [18:46<02:22, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121705,8 +121550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13265/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  89%|▉| 13265/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13259/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  89%|▉| 13259/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121714,8 +121559,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13266/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13266/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13260/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121723,8 +121567,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13267/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13267/14932 [18:49<02:21, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13260/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121732,8 +121575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13268/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13268/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  89%|▉| 13261/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13261/14932 [18:47<02:22, 11.76it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -121741,8 +121584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13269/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  89%|▉| 13269/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  89%|▉| 13262/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13262/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -121750,8 +121593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13270/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  89%|▉| 13270/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  89%|▉| 13263/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13263/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -121759,8 +121602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13271/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  89%|▉| 13271/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  89%|▉| 13264/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13264/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121768,8 +121611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13272/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  89%|▉| 13272/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  89%|▉| 13265/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13265/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -121777,8 +121620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13273/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  89%|▉| 13273/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13266/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  89%|▉| 13266/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -121786,8 +121629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13274/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13274/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13267/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13267/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121795,8 +121638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13275/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13275/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13268/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  89%|▉| 13268/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -121804,7 +121647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13276/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13269/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  89%|▉| 13269/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -121812,7 +121656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13276/14932 [18:50<02:21, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13270/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13270/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -121820,8 +121665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13277/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13277/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13271/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  89%|▉| 13271/14932 [18:47<02:21, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121829,8 +121674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13278/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13278/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13272/14932 [18:48<02:21, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13272/14932 [18:48<02:21, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -121838,8 +121683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13279/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  89%|▉| 13279/14932 [18:50<02:20, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13273/14932 [18:48<02:21, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13273/14932 [18:48<02:21, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -121847,8 +121692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13280/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13280/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  89%|▉| 13274/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13274/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -121856,8 +121701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13281/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  89%|▉| 13281/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13275/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13275/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -121865,8 +121710,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13282/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  89%|▉| 13282/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  89%|▉| 13276/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13276/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -121874,7 +121719,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13283/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  89%|▉| 13277/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13277/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -121882,7 +121728,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13283/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  89%|▉| 13278/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  89%|▉| 13278/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -121890,8 +121737,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13284/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  89%|▉| 13284/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13279/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  89%|▉| 13279/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -121899,8 +121746,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13285/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13285/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13280/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13280/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121908,8 +121755,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13286/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13286/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13281/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13281/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121917,8 +121764,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13287/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13287/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13282/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13282/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -121926,8 +121773,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13288/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13288/14932 [18:51<02:20, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13283/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  89%|▉| 13283/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -121935,8 +121782,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13289/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13289/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13284/14932 [18:48<02:20, 11.77it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  89%|▉| 13284/14932 [18:49<02:20, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -121944,8 +121791,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13290/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13290/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13285/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  89%|▉| 13285/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121953,8 +121800,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13291/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13291/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13286/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13286/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121962,8 +121809,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13292/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13292/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13287/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -121971,8 +121817,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13293/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13293/14932 [18:51<02:19, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13287/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -121980,7 +121825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13294/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13288/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13288/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -121988,7 +121834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13294/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  89%|▉| 13289/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13289/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -121996,8 +121843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13295/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  89%|▉| 13295/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  89%|▉| 13290/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  89%|▉| 13290/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -122005,8 +121852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13296/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  89%|▉| 13296/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  89%|▉| 13291/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13291/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -122014,8 +121861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13297/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  89%|▉| 13297/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13292/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  89%|▉| 13292/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -122023,8 +121870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13298/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13298/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  89%|▉| 13293/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  89%|▉| 13293/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -122032,8 +121879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13299/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  89%|▉| 13299/14932 [18:52<02:19, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13294/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  89%|▉| 13294/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -122041,8 +121888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13300/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13300/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13295/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  89%|▉| 13295/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -122050,8 +121897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13301/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13301/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  89%|▉| 13296/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13296/14932 [18:49<02:19, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -122059,8 +121906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13302/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  89%|▉| 13302/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13297/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  89%|▉| 13297/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122068,8 +121915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13303/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13303/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13298/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13298/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -122077,8 +121924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13304/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13304/14932 [18:52<02:18, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13299/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  89%|▉| 13299/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122086,8 +121933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13305/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13305/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13300/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  89%|▉| 13300/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -122095,8 +121942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13306/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13306/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  89%|▉| 13301/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  89%|▉| 13301/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122104,8 +121951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13307/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  89%|▉| 13307/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13302/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13302/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122113,8 +121960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13308/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13308/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13303/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  89%|▉| 13303/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -122122,8 +121969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13309/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13309/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  89%|▉| 13304/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13304/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -122131,8 +121978,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13310/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  89%|▉| 13310/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  89%|▉| 13305/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -122140,8 +121986,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13311/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  89%|▉| 13311/14932 [18:53<02:18, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13305/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -122149,8 +121994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13312/14932 [18:53<02:17, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13312/14932 [18:53<02:17, 11.74it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  89%|▉| 13306/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  89%|▉| 13306/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122158,8 +122003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13313/14932 [18:53<02:17, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  89%|▉| 13313/14932 [18:53<02:17, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13307/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13307/14932 [18:50<02:18, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122167,8 +122012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13314/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13314/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13308/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13308/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -122176,8 +122021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13315/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13315/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13309/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13309/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -122185,8 +122030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13316/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  89%|▉| 13316/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13310/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  89%|▉| 13310/14932 [18:50<02:17, 11.77it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -122194,8 +122039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13317/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13317/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  89%|▉| 13311/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  89%|▉| 13311/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -122203,8 +122048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13318/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  89%|▉| 13318/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13312/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13312/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122212,8 +122057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13319/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13319/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  89%|▉| 13313/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13313/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -122221,8 +122066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13320/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  89%|▉| 13320/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13314/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13314/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -122230,8 +122075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13321/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13321/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  89%|▉| 13315/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13315/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -122239,8 +122084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13322/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  89%|▉| 13322/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13316/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13316/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -122248,8 +122093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13323/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13323/14932 [18:54<02:17, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13317/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13317/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -122257,8 +122102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13324/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13324/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13318/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13318/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -122266,8 +122111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13325/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13325/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13319/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13319/14932 [18:51<02:17, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -122275,8 +122120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13326/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13326/14932 [18:54<02:16, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  89%|▉| 13320/14932 [18:51<02:16, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13320/14932 [18:51<02:16, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -122284,8 +122129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13327/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  89%|▉| 13327/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13321/14932 [18:51<02:16, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13321/14932 [18:51<02:16, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122293,8 +122138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13328/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  89%|▉| 13328/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13322/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13322/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -122302,8 +122147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13329/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13329/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13323/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13323/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -122311,8 +122156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13330/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13330/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13324/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13324/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -122320,8 +122165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13331/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13331/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  89%|▉| 13325/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  89%|▉| 13325/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -122329,8 +122174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13332/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  89%|▉| 13332/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13326/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  89%|▉| 13326/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -122338,8 +122183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13333/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13333/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13327/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13327/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -122347,7 +122192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13334/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13328/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13328/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122355,7 +122201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13334/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13329/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  89%|▉| 13329/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122363,8 +122210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13335/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13335/14932 [18:55<02:16, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  89%|▉| 13330/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13330/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -122372,8 +122219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13336/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  89%|▉| 13336/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13331/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  89%|▉| 13331/14932 [18:52<02:16, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -122381,8 +122228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13337/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13337/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13332/14932 [18:52<02:15, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  89%|▉| 13332/14932 [18:52<02:15, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122390,8 +122237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13338/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13338/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13333/14932 [18:52<02:15, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13333/14932 [18:52<02:15, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122399,8 +122246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13339/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  89%|▉| 13339/14932 [18:55<02:15, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  89%|▉| 13334/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13334/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -122408,8 +122255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13340/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  89%|▉| 13340/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  89%|▉| 13335/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13335/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -122417,8 +122264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13341/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  89%|▉| 13341/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13336/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  89%|▉| 13336/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -122426,8 +122273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13342/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  89%|▉| 13342/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13337/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  89%|▉| 13337/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -122435,8 +122282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13343/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13343/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  89%|▉| 13338/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  89%|▉| 13338/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -122444,8 +122291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13344/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  89%|▉| 13344/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13339/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  89%|▉| 13339/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -122453,8 +122300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13345/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13345/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  89%|▉| 13340/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13340/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -122462,8 +122309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13346/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  89%|▉| 13346/14932 [18:56<02:15, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13341/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  89%|▉| 13341/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -122471,8 +122318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13347/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13347/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  89%|▉| 13342/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13342/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -122480,8 +122327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13348/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  89%|▉| 13348/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  89%|▉| 13343/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  89%|▉| 13343/14932 [18:53<02:15, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122489,8 +122336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13349/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  89%|▉| 13349/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  89%|▉| 13344/14932 [18:53<02:14, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  89%|▉| 13344/14932 [18:53<02:14, 11.77it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -122498,8 +122345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13350/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  89%|▉| 13350/14932 [18:56<02:14, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13345/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  89%|▉| 13345/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -122507,8 +122354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13351/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13351/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13346/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  89%|▉| 13346/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -122516,8 +122363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13352/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  89%|▉| 13352/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  89%|▉| 13347/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13347/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -122525,8 +122372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13353/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  89%|▉| 13353/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13348/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  89%|▉| 13348/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -122534,8 +122381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13354/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13354/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  89%|▉| 13349/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  89%|▉| 13349/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -122543,8 +122390,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13355/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  89%|▉| 13355/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  89%|▉| 13350/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -122552,8 +122398,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13356/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  89%|▉| 13356/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13350/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -122561,8 +122406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13357/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  89%|▉| 13357/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13351/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  89%|▉| 13351/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -122570,8 +122415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13358/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  89%|▉| 13358/14932 [18:57<02:14, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  89%|▉| 13352/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  89%|▉| 13352/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -122579,8 +122424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13359/14932 [18:57<02:13, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  89%|▉| 13359/14932 [18:57<02:13, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  89%|▉| 13353/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  89%|▉| 13353/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -122588,8 +122433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13360/14932 [18:57<02:13, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  89%|▉| 13360/14932 [18:57<02:13, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  89%|▉| 13354/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  89%|▉| 13354/14932 [18:54<02:14, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -122597,8 +122442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13361/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  89%|▉| 13361/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  89%|▉| 13355/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  89%|▉| 13355/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -122606,8 +122451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13362/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  89%|▉| 13362/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  89%|▉| 13356/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  89%|▉| 13356/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -122615,8 +122460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13363/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  89%|▉| 13363/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  89%|▉| 13357/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  89%|▉| 13357/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -122624,8 +122469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  89%|▉| 13364/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  89%|▉| 13364/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13358/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  89%|▉| 13358/14932 [18:54<02:13, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -122633,7 +122478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13365/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  89%|▉| 13359/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  89%|▉| 13359/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -122641,7 +122487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13365/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  89%|▉| 13360/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  89%|▉| 13360/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -122649,8 +122496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13366/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13366/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  89%|▉| 13361/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  89%|▉| 13361/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -122658,8 +122505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13367/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13367/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  89%|▉| 13362/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  89%|▉| 13362/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -122667,8 +122514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13368/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  90%|▉| 13368/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  89%|▉| 13363/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  89%|▉| 13363/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -122676,8 +122523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13369/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13369/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  89%|▉| 13364/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  89%|▉| 13364/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122685,8 +122532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13370/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13370/14932 [18:58<02:13, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13365/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13365/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -122694,8 +122541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13371/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13371/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13366/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  90%|▉| 13366/14932 [18:55<02:13, 11.77it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -122703,8 +122550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13372/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13372/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13367/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  90%|▉| 13367/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -122712,8 +122559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13373/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13373/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  90%|▉| 13368/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  90%|▉| 13368/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -122721,8 +122568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13374/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  90%|▉| 13374/14932 [18:58<02:12, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  90%|▉| 13369/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  90%|▉| 13369/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -122730,8 +122577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13375/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  90%|▉| 13375/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13370/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  90%|▉| 13370/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -122739,8 +122586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13376/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13376/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  90%|▉| 13371/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  90%|▉| 13371/14932 [18:55<02:12, 11.77it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -122748,8 +122595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13377/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  90%|▉| 13377/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13372/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  90%|▉| 13372/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122757,8 +122604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13378/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13378/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13373/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13373/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122766,8 +122613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13379/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  90%|▉| 13379/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13374/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13374/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122775,8 +122622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13380/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13380/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  90%|▉| 13375/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13375/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122784,8 +122631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13381/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  90%|▉| 13381/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  90%|▉| 13376/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13376/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -122793,8 +122640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13382/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  90%|▉| 13382/14932 [18:59<02:12, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  90%|▉| 13377/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  90%|▉| 13377/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -122802,8 +122649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13383/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  90%|▉| 13383/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  90%|▉| 13378/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13378/14932 [18:56<02:12, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122811,8 +122658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13384/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13384/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  90%|▉| 13379/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13379/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122820,8 +122667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13385/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  90%|▉| 13385/14932 [18:59<02:11, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  90%|▉| 13380/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13380/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -122829,8 +122676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13386/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  90%|▉| 13386/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13381/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  90%|▉| 13381/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -122838,8 +122685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13387/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13387/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13382/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  90%|▉| 13382/14932 [18:56<02:11, 11.77it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -122847,8 +122694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13388/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13388/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13383/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  90%|▉| 13383/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -122856,7 +122703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13389/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13384/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  90%|▉| 13384/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -122864,7 +122712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13389/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  90%|▉| 13385/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13385/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -122872,8 +122721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13390/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  90%|▉| 13390/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13386/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13386/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122881,8 +122730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13391/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13391/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13387/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13387/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -122890,8 +122739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13392/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13392/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  90%|▉| 13388/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13388/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -122899,8 +122748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13393/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  90%|▉| 13393/14932 [19:00<02:11, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13389/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13389/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -122908,8 +122757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13394/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13394/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  90%|▉| 13390/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  90%|▉| 13390/14932 [18:57<02:11, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -122917,8 +122766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13395/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  90%|▉| 13395/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  90%|▉| 13391/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  90%|▉| 13391/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -122926,8 +122775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13396/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  90%|▉| 13396/14932 [19:00<02:10, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  90%|▉| 13392/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  90%|▉| 13392/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122935,8 +122784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13397/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  90%|▉| 13397/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  90%|▉| 13393/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13393/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -122944,8 +122793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13398/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  90%|▉| 13398/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  90%|▉| 13394/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13394/14932 [18:57<02:10, 11.77it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -122953,8 +122802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13399/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  90%|▉| 13399/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13395/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  90%|▉| 13395/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -122962,8 +122811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13400/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13400/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  90%|▉| 13396/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13396/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -122971,8 +122820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13401/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  90%|▉| 13401/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13397/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13397/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -122980,8 +122829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13402/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  90%|▉| 13402/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13398/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  90%|▉| 13398/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -122989,8 +122838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13403/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13403/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  90%|▉| 13399/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  90%|▉| 13399/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -122998,8 +122847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13404/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  90%|▉| 13404/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13400/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  90%|▉| 13400/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -123007,8 +122856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13405/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  90%|▉| 13405/14932 [19:01<02:10, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13401/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  90%|▉| 13401/14932 [18:58<02:10, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -123016,8 +122865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13406/14932 [19:01<02:09, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13406/14932 [19:01<02:09, 11.74it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  90%|▉| 13402/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  90%|▉| 13402/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -123025,8 +122874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13407/14932 [19:01<02:09, 11.74it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  90%|▉| 13407/14932 [19:01<02:09, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13403/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  90%|▉| 13403/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -123034,8 +122883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13408/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13408/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  90%|▉| 13404/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  90%|▉| 13404/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -123043,8 +122892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13409/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  90%|▉| 13409/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13405/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  90%|▉| 13405/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -123052,8 +122901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13410/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  90%|▉| 13410/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  90%|▉| 13406/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  90%|▉| 13406/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -123061,8 +122910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13411/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  90%|▉| 13411/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13407/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13407/14932 [18:58<02:09, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123070,8 +122919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13412/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13412/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  90%|▉| 13408/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13408/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123079,8 +122928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13413/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  90%|▉| 13413/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  90%|▉| 13409/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13409/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123088,8 +122937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13414/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  90%|▉| 13414/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13410/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13410/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123097,8 +122946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13415/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  90%|▉| 13415/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  90%|▉| 13411/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13411/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123106,8 +122955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13416/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  90%|▉| 13416/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13412/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13412/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -123115,8 +122964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13417/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13417/14932 [19:02<02:09, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13413/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  90%|▉| 13413/14932 [18:59<02:09, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -123124,8 +122973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13418/14932 [19:02<02:08, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13418/14932 [19:02<02:08, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13414/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  90%|▉| 13414/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -123133,8 +122982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13419/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  90%|▉| 13419/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13415/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13415/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123142,8 +122991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13420/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13420/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13416/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13416/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -123151,8 +123000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13421/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13421/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13417/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  90%|▉| 13417/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -123160,8 +123009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13422/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13422/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  90%|▉| 13418/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  90%|▉| 13418/14932 [18:59<02:08, 11.77it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -123169,8 +123018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13423/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  90%|▉| 13423/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13419/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  90%|▉| 13419/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -123178,8 +123027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13424/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13424/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  90%|▉| 13420/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  90%|▉| 13420/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -123187,8 +123036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13425/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  90%|▉| 13425/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  90%|▉| 13421/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  90%|▉| 13421/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123196,8 +123045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13426/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  90%|▉| 13426/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  90%|▉| 13422/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13422/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123205,8 +123054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13427/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  90%|▉| 13427/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  90%|▉| 13423/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13423/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -123214,8 +123063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13428/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  90%|▉| 13428/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  90%|▉| 13424/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  90%|▉| 13424/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -123223,8 +123072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13429/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  90%|▉| 13429/14932 [19:03<02:08, 11.74it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  90%|▉| 13425/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13425/14932 [19:00<02:08, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -123232,8 +123081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13430/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  90%|▉| 13430/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13426/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  90%|▉| 13426/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -123241,7 +123090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13431/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13427/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  90%|▉| 13427/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123249,7 +123099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13431/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13428/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13428/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123257,8 +123108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13432/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13432/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13429/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13429/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -123266,7 +123117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13433/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13430/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  90%|▉| 13430/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -123274,7 +123126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13433/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  90%|▉| 13431/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  90%|▉| 13431/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -123282,8 +123135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13434/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  90%|▉| 13434/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13432/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13432/14932 [19:00<02:07, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -123291,8 +123144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13435/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13435/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13433/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  90%|▉| 13433/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -123300,8 +123153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13436/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13436/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13434/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  90%|▉| 13434/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=4.9"
      ]
     },
     {
@@ -123309,8 +123162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13437/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13437/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13435/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=4.9\r",
+      "Epoch 0:  90%|▉| 13435/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123318,8 +123171,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13438/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  90%|▉| 13438/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13436/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123327,8 +123179,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13439/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13439/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13436/14932 [19:01<02:07, 11.77it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -123336,8 +123187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13440/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13440/14932 [19:04<02:07, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  90%|▉| 13437/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  90%|▉| 13437/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -123345,8 +123196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13441/14932 [19:05<02:07, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  90%|▉| 13441/14932 [19:05<02:07, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  90%|▉| 13438/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  90%|▉| 13438/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -123354,8 +123205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13442/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13442/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13439/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  90%|▉| 13439/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -123363,8 +123214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13443/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13443/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13440/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  90%|▉| 13440/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=4.8"
      ]
     },
     {
@@ -123372,8 +123223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13444/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13444/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  90%|▉| 13441/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=4.8\r",
+      "Epoch 0:  90%|▉| 13441/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123381,8 +123232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13445/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  90%|▉| 13445/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13442/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13442/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123390,8 +123241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13446/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13446/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13443/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13443/14932 [19:01<02:06, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -123399,8 +123250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13447/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13447/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13444/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  90%|▉| 13444/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -123408,8 +123259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13448/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13448/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  90%|▉| 13445/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  90%|▉| 13445/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123417,8 +123268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13449/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  90%|▉| 13449/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13446/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  90%|▉| 13446/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -123426,8 +123277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13450/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13450/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  90%|▉| 13447/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  90%|▉| 13447/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -123435,8 +123286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13451/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  90%|▉| 13451/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13448/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  90%|▉| 13448/14932 [19:02<02:06, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -123444,8 +123295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13452/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13452/14932 [19:05<02:06, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  90%|▉| 13449/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13449/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123453,8 +123304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13453/14932 [19:05<02:05, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  90%|▉| 13453/14932 [19:05<02:05, 11.74it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  90%|▉| 13450/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13450/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -123462,8 +123313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13454/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  90%|▉| 13454/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13451/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  90%|▉| 13451/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -123471,8 +123322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13455/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13455/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  90%|▉| 13452/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  90%|▉| 13452/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -123480,8 +123331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13456/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  90%|▉| 13456/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  90%|▉| 13453/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13453/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123489,8 +123340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13457/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  90%|▉| 13457/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  90%|▉| 13454/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13454/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -123498,8 +123349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13458/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  90%|▉| 13458/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  90%|▉| 13455/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  90%|▉| 13455/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123507,8 +123358,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13459/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13459/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  90%|▉| 13456/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123516,8 +123366,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13460/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  90%|▉| 13460/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  90%|▉| 13456/14932 [19:02<02:05, 11.77it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -123525,7 +123374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13461/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  90%|▉| 13457/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  90%|▉| 13457/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123533,7 +123383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13461/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13458/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13458/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123541,8 +123392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13462/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13462/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  90%|▉| 13459/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  90%|▉| 13459/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123550,8 +123401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13463/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  90%|▉| 13463/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13460/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13460/14932 [19:03<02:05, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123559,8 +123410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13464/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13464/14932 [19:06<02:05, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13461/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13461/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123568,8 +123419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13465/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13465/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13462/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  90%|▉| 13462/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -123577,8 +123428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13466/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13466/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13463/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  90%|▉| 13463/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -123586,8 +123437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13467/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13467/14932 [19:06<02:04, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13464/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13464/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -123595,8 +123446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13468/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13468/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13465/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  90%|▉| 13465/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -123604,8 +123455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13469/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  90%|▉| 13469/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13466/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  90%|▉| 13466/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -123613,8 +123464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13470/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13470/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  90%|▉| 13467/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13467/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -123622,8 +123473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13471/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  90%|▉| 13471/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=4.9"
+      "Epoch 0:  90%|▉| 13468/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13468/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -123631,8 +123482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13472/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=4.9\r",
-      "Epoch 0:  90%|▉| 13472/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13469/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  90%|▉| 13469/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -123640,8 +123491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13473/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  90%|▉| 13473/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13470/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  90%|▉| 13470/14932 [19:03<02:04, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123649,8 +123500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13474/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13474/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  90%|▉| 13471/14932 [19:04<02:04, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13471/14932 [19:04<02:04, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -123658,8 +123509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13475/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  90%|▉| 13475/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  90%|▉| 13472/14932 [19:04<02:04, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  90%|▉| 13472/14932 [19:04<02:04, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123667,8 +123518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13476/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  90%|▉| 13476/14932 [19:07<02:04, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  90%|▉| 13473/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13473/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -123676,8 +123527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13477/14932 [19:07<02:03, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  90%|▉| 13477/14932 [19:07<02:03, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13474/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  90%|▉| 13474/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -123685,8 +123536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13478/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  90%|▉| 13478/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  90%|▉| 13475/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  90%|▉| 13475/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -123694,8 +123545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13479/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13479/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13476/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  90%|▉| 13476/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123703,8 +123554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13480/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13480/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13477/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13477/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -123712,8 +123563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13481/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13481/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  90%|▉| 13478/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  90%|▉| 13478/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -123721,8 +123572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13482/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  90%|▉| 13482/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13479/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  90%|▉| 13479/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -123730,8 +123581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13483/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13483/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  90%|▉| 13480/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  90%|▉| 13480/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123739,8 +123590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13484/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  90%|▉| 13484/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13481/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13481/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -123748,8 +123599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13485/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13485/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13482/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  90%|▉| 13482/14932 [19:04<02:03, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123757,8 +123608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13486/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13486/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13483/14932 [19:05<02:03, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13483/14932 [19:05<02:03, 11.77it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -123766,8 +123617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13487/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13487/14932 [19:08<02:03, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13484/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  90%|▉| 13484/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -123775,8 +123626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13488/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  90%|▉| 13488/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13485/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  90%|▉| 13485/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -123784,8 +123635,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13489/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13489/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  90%|▉| 13486/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  90%|▉| 13486/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -123793,8 +123644,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13490/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  90%|▉| 13490/14932 [19:08<02:02, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  90%|▉| 13487/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13487/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -123802,8 +123653,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13491/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  90%|▉| 13491/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13488/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  90%|▉| 13488/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -123811,8 +123662,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13492/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13492/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  90%|▉| 13489/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  90%|▉| 13489/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -123820,8 +123671,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13493/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  90%|▉| 13493/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13490/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13490/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -123829,8 +123680,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13494/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13494/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  90%|▉| 13491/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  90%|▉| 13491/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -123838,8 +123689,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13495/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  90%|▉| 13495/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13492/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  90%|▉| 13492/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -123847,8 +123698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13496/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13496/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  90%|▉| 13493/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  90%|▉| 13493/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123856,8 +123707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13497/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  90%|▉| 13497/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  90%|▉| 13494/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13494/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -123865,8 +123716,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13498/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  90%|▉| 13498/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  90%|▉| 13495/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  90%|▉| 13495/14932 [19:05<02:02, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123874,8 +123725,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13499/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  90%|▉| 13499/14932 [19:09<02:02, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  90%|▉| 13496/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  90%|▉| 13496/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -123883,8 +123734,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13500/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  90%|▉| 13500/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13497/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  90%|▉| 13497/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -123892,8 +123743,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13501/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13501/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13498/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  90%|▉| 13498/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123901,8 +123752,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13502/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  90%|▉| 13502/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  90%|▉| 13499/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  90%|▉| 13499/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -123910,8 +123761,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13503/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  90%|▉| 13503/14932 [19:09<02:01, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  90%|▉| 13500/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  90%|▉| 13500/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -123919,8 +123770,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13504/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  90%|▉| 13504/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13501/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  90%|▉| 13501/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -123928,8 +123779,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13505/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13505/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  90%|▉| 13502/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  90%|▉| 13502/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -123937,8 +123788,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13506/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  90%|▉| 13506/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13503/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  90%|▉| 13503/14932 [19:06<02:01, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -123946,8 +123797,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13507/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13507/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  90%|▉| 13504/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  90%|▉| 13504/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -123955,8 +123806,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13508/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  90%|▉| 13508/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  90%|▉| 13505/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  90%|▉| 13505/14932 [19:06<02:01, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -123964,8 +123815,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13509/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  90%|▉| 13509/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13506/14932 [19:07<02:01, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  90%|▉| 13506/14932 [19:07<02:01, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -123973,8 +123824,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13510/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  90%|▉| 13510/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13507/14932 [19:07<02:01, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  90%|▉| 13507/14932 [19:07<02:01, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -123982,8 +123833,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13511/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  90%|▉| 13511/14932 [19:10<02:01, 11.74it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  90%|▉| 13508/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  90%|▉| 13508/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -123991,8 +123842,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13512/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  90%|▉| 13512/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  90%|▉| 13509/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -124000,8 +123850,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  90%|▉| 13513/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  90%|▉| 13513/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13509/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -124009,8 +123858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13514/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13514/14932 [19:10<02:00, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  90%|▉| 13510/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  90%|▉| 13510/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -124018,8 +123867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13515/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  91%|▉| 13515/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  90%|▉| 13511/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  90%|▉| 13511/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -124027,8 +123876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13516/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13516/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  90%|▉| 13512/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  90%|▉| 13512/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124036,8 +123885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13517/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13517/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  90%|▉| 13513/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  90%|▉| 13513/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -124045,8 +123894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13518/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  91%|▉| 13518/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13514/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  91%|▉| 13514/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -124054,8 +123903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13519/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13519/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13515/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13515/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -124063,8 +123912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13520/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13520/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  91%|▉| 13516/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  91%|▉| 13516/14932 [19:07<02:00, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -124072,8 +123921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13521/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  91%|▉| 13521/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  91%|▉| 13517/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  91%|▉| 13517/14932 [19:07<02:00, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -124081,8 +123930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13522/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  91%|▉| 13522/14932 [19:11<02:00, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13518/14932 [19:08<02:00, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  91%|▉| 13518/14932 [19:08<02:00, 11.78it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -124090,8 +123939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13523/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13523/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  91%|▉| 13519/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  91%|▉| 13519/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -124099,8 +123948,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13524/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  91%|▉| 13524/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13520/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -124108,8 +123956,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13525/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  91%|▉| 13525/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  91%|▉| 13520/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124117,8 +123964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13526/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  91%|▉| 13526/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13521/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13521/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -124126,8 +123973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13527/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13527/14932 [19:11<01:59, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13522/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  91%|▉| 13522/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -124135,8 +123982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13528/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13528/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  91%|▉| 13523/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  91%|▉| 13523/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -124144,8 +123991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13529/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13529/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13524/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  91%|▉| 13524/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -124153,8 +124000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13530/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13530/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  91%|▉| 13525/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  91%|▉| 13525/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -124162,8 +124009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13531/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  91%|▉| 13531/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13526/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13526/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -124171,8 +124018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13532/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13532/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  91%|▉| 13527/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  91%|▉| 13527/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -124180,8 +124027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13533/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  91%|▉| 13533/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13528/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  91%|▉| 13528/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -124189,8 +124036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13534/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13534/14932 [19:12<01:59, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13529/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13529/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=4.7"
      ]
     },
     {
@@ -124198,8 +124045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13535/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  91%|▉| 13535/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13530/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=4.7\r",
+      "Epoch 0:  91%|▉| 13530/14932 [19:08<01:59, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124207,8 +124054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13536/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13536/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13531/14932 [19:08<01:58, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13531/14932 [19:08<01:58, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -124216,8 +124063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13537/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13537/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13532/14932 [19:08<01:58, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  91%|▉| 13532/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124225,8 +124072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13538/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13538/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  91%|▉| 13533/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13533/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124234,8 +124081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13539/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  91%|▉| 13539/14932 [19:12<01:58, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13534/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13534/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -124243,8 +124090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13540/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13540/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13535/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  91%|▉| 13535/14932 [19:09<01:58, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -124252,8 +124099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13541/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13541/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13536/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13536/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124261,8 +124108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13542/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13542/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13537/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13537/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124270,8 +124117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13543/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13543/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13538/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13538/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -124279,8 +124126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13544/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13544/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13539/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  91%|▉| 13539/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124288,8 +124135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13545/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13545/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  91%|▉| 13540/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13540/14932 [19:09<01:58, 11.77it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -124297,8 +124144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13546/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13546/14932 [19:13<01:58, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13541/14932 [19:10<01:58, 11.77it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  91%|▉| 13541/14932 [19:10<01:58, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124306,8 +124153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13547/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13547/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13542/14932 [19:10<01:58, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13542/14932 [19:10<01:58, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -124315,8 +124162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13548/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13548/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13543/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  91%|▉| 13543/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -124324,8 +124171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13549/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13549/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13544/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  91%|▉| 13544/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -124333,8 +124180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13550/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13550/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  91%|▉| 13545/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  91%|▉| 13545/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -124342,8 +124189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13551/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  91%|▉| 13551/14932 [19:13<01:57, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13546/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13546/14932 [19:10<01:57, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124351,8 +124198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13552/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13552/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13547/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13547/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -124360,8 +124207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13553/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13553/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13548/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  91%|▉| 13548/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -124369,8 +124216,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13554/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13554/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13549/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -124378,8 +124224,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13555/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13555/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13549/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -124387,8 +124232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13556/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13556/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13550/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  91%|▉| 13550/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124396,8 +124241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13557/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13557/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13551/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13551/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -124405,8 +124250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13558/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13558/14932 [19:14<01:57, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13552/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  91%|▉| 13552/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -124414,8 +124259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13559/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13559/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13553/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13553/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -124423,8 +124268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13560/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13560/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  91%|▉| 13554/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  91%|▉| 13554/14932 [19:10<01:57, 11.78it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -124432,8 +124277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13561/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  91%|▉| 13561/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13555/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  91%|▉| 13555/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -124441,8 +124286,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13562/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13562/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  91%|▉| 13556/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13556/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -124450,8 +124295,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13563/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  91%|▉| 13563/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13557/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  91%|▉| 13557/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124459,8 +124304,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13564/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13564/14932 [19:14<01:56, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  91%|▉| 13558/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13558/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -124468,7 +124313,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13565/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  91%|▉| 13559/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13559/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -124476,7 +124322,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13565/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  91%|▉| 13560/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13560/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124484,8 +124331,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13566/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  91%|▉| 13566/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13561/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13561/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -124493,8 +124340,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13567/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13567/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13562/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  91%|▉| 13562/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124502,7 +124349,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13568/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13563/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13563/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -124510,7 +124358,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13568/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  91%|▉| 13564/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13564/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -124518,8 +124367,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13569/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13569/14932 [19:15<01:56, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13565/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  91%|▉| 13565/14932 [19:11<01:56, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -124527,8 +124376,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13570/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13570/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  91%|▉| 13566/14932 [19:12<01:56, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  91%|▉| 13566/14932 [19:12<01:56, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -124536,8 +124385,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13571/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  91%|▉| 13571/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13567/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13567/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -124545,8 +124394,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13572/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  91%|▉| 13572/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13568/14932 [19:12<01:55, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  91%|▉| 13568/14932 [19:12<01:55, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -124554,8 +124403,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13573/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13573/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13569/14932 [19:12<01:55, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  91%|▉| 13569/14932 [19:12<01:55, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -124563,8 +124412,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13574/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13574/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13570/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13570/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -124572,8 +124421,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13575/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13575/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  91%|▉| 13571/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  91%|▉| 13571/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124581,8 +124430,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13576/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  91%|▉| 13576/14932 [19:15<01:55, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13572/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13572/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -124590,8 +124439,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13577/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13577/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13573/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  91%|▉| 13573/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -124599,8 +124448,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13578/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13578/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13574/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  91%|▉| 13574/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -124608,8 +124457,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13579/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  91%|▉| 13579/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13575/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  91%|▉| 13575/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124617,8 +124466,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13580/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13580/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13576/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13576/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -124626,8 +124475,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13581/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13581/14932 [19:16<01:55, 11.74it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  91%|▉| 13577/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13577/14932 [19:12<01:55, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -124635,8 +124484,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13582/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  91%|▉| 13582/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13578/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  91%|▉| 13578/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -124644,8 +124493,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13583/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13583/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13579/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  91%|▉| 13579/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -124653,8 +124502,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13584/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13584/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  91%|▉| 13580/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13580/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -124662,8 +124511,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13585/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  91%|▉| 13585/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13581/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  91%|▉| 13581/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124671,8 +124520,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13586/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13586/14932 [19:16<01:54, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13582/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13582/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -124680,8 +124529,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13587/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13587/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13583/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  91%|▉| 13583/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -124689,8 +124538,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13588/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13588/14932 [19:16<01:54, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13584/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  91%|▉| 13584/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -124698,8 +124547,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13589/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13589/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13585/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13585/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -124707,8 +124556,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13590/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  91%|▉| 13590/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  91%|▉| 13586/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  91%|▉| 13586/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -124716,8 +124565,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13591/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  91%|▉| 13591/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13587/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  91%|▉| 13587/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -124725,8 +124574,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13592/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13592/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  91%|▉| 13588/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  91%|▉| 13588/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -124734,8 +124583,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13593/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  91%|▉| 13593/14932 [19:17<01:54, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13589/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  91%|▉| 13589/14932 [19:13<01:54, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124743,8 +124592,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13594/14932 [19:17<01:53, 11.74it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13594/14932 [19:17<01:53, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13590/14932 [19:13<01:53, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13590/14932 [19:13<01:53, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -124752,8 +124601,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13595/14932 [19:17<01:53, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13595/14932 [19:17<01:53, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13591/14932 [19:13<01:53, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  91%|▉| 13591/14932 [19:13<01:53, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -124761,7 +124610,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13596/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13592/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  91%|▉| 13592/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -124769,7 +124619,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13596/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13593/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13593/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -124777,8 +124628,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13597/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13597/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13594/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  91%|▉| 13594/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -124786,8 +124637,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13598/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13598/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  91%|▉| 13595/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  91%|▉| 13595/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -124795,8 +124646,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13599/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  91%|▉| 13599/14932 [19:17<01:53, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13596/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  91%|▉| 13596/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -124804,8 +124655,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13600/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13600/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13597/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13597/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -124813,8 +124664,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13601/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13601/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13598/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  91%|▉| 13598/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -124822,8 +124673,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13602/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13602/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  91%|▉| 13599/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  91%|▉| 13599/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -124831,8 +124682,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13603/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  91%|▉| 13603/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13600/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -124840,8 +124690,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13604/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13604/14932 [19:18<01:53, 11.74it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  91%|▉| 13600/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124849,8 +124698,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13605/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  91%|▉| 13605/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13601/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13601/14932 [19:14<01:53, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -124858,8 +124707,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13606/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13606/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13602/14932 [19:14<01:52, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  91%|▉| 13602/14932 [19:14<01:52, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -124867,8 +124716,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13607/14932 [19:18<01:52, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13607/14932 [19:18<01:52, 11.75it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  91%|▉| 13603/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -124876,8 +124724,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13608/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  91%|▉| 13608/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13603/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -124885,8 +124732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13609/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13609/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13604/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  91%|▉| 13604/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124894,8 +124741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13610/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13610/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13605/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13605/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -124903,8 +124750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13611/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13611/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  91%|▉| 13606/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13606/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -124912,8 +124759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13612/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  91%|▉| 13612/14932 [19:18<01:52, 11.74it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  91%|▉| 13607/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  91%|▉| 13607/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -124921,8 +124768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13613/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  91%|▉| 13613/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  91%|▉| 13608/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  91%|▉| 13608/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -124930,7 +124777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13614/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  91%|▉| 13609/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  91%|▉| 13609/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -124938,7 +124786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13614/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13610/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  91%|▉| 13610/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -124946,8 +124795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13615/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13615/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13611/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  91%|▉| 13611/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -124955,8 +124804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13616/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13616/14932 [19:19<01:52, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  91%|▉| 13612/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  91%|▉| 13612/14932 [19:15<01:52, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -124964,8 +124813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13617/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  91%|▉| 13617/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  91%|▉| 13613/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  91%|▉| 13613/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -124973,8 +124822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13618/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13618/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13614/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  91%|▉| 13614/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -124982,8 +124831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13619/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13619/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13615/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  91%|▉| 13615/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -124991,8 +124840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13620/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13620/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13616/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  91%|▉| 13616/14932 [19:15<01:51, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125000,8 +124849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13621/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13621/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  91%|▉| 13617/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13617/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -125009,8 +124858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13622/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  91%|▉| 13622/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13618/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  91%|▉| 13618/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -125018,8 +124867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13623/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13623/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13619/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  91%|▉| 13619/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -125027,8 +124876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13624/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13624/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13620/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13620/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -125036,8 +124885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13625/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13625/14932 [19:19<01:51, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13621/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  91%|▉| 13621/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -125045,8 +124894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13626/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13626/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  91%|▉| 13622/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  91%|▉| 13622/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -125054,7 +124903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13627/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  91%|▉| 13623/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  91%|▉| 13623/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -125062,7 +124912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13627/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13624/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13624/14932 [19:16<01:51, 11.78it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -125070,8 +124921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13628/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13628/14932 [19:20<01:51, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  91%|▉| 13625/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  91%|▉| 13625/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -125079,8 +124930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13629/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  91%|▉| 13629/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13626/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  91%|▉| 13626/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -125088,8 +124939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13630/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  91%|▉| 13630/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  91%|▉| 13627/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  91%|▉| 13627/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -125097,8 +124948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13631/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  91%|▉| 13631/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13628/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  91%|▉| 13628/14932 [19:16<01:50, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -125106,8 +124957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13632/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13632/14932 [19:20<01:50, 11.75it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  91%|▉| 13629/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  91%|▉| 13629/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -125115,8 +124966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13633/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  91%|▉| 13633/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  91%|▉| 13630/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  91%|▉| 13630/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -125124,8 +124975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13634/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  91%|▉| 13634/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  91%|▉| 13631/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  91%|▉| 13631/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -125133,8 +124984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13635/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  91%|▉| 13635/14932 [19:20<01:50, 11.74it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  91%|▉| 13632/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  91%|▉| 13632/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125142,8 +124993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13636/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  91%|▉| 13636/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  91%|▉| 13633/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13633/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125151,8 +125002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13637/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  91%|▉| 13637/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13634/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13634/14932 [19:17<01:50, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125160,8 +125011,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13638/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13638/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  91%|▉| 13635/14932 [19:18<01:50, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125169,8 +125019,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13639/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  91%|▉| 13639/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  91%|▉| 13635/14932 [19:18<01:50, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -125178,8 +125027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13640/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  91%|▉| 13640/14932 [19:21<01:50, 11.74it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13636/14932 [19:18<01:50, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  91%|▉| 13636/14932 [19:18<01:50, 11.77it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -125187,8 +125036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13641/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  91%|▉| 13641/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  91%|▉| 13637/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  91%|▉| 13637/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125196,8 +125045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13642/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  91%|▉| 13642/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13638/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13638/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -125205,8 +125054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13643/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13643/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13639/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  91%|▉| 13639/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -125214,8 +125063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13644/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  91%|▉| 13644/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  91%|▉| 13640/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  91%|▉| 13640/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125223,8 +125072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13645/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  91%|▉| 13645/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  91%|▉| 13641/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  91%|▉| 13641/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125232,8 +125081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13646/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  91%|▉| 13646/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  91%|▉| 13642/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13642/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125241,8 +125090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13647/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  91%|▉| 13647/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  91%|▉| 13643/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  91%|▉| 13643/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -125250,8 +125099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13648/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  91%|▉| 13648/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  91%|▉| 13644/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13644/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125259,8 +125108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13649/14932 [19:21<01:49, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  91%|▉| 13649/14932 [19:22<01:49, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  91%|▉| 13645/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  91%|▉| 13645/14932 [19:18<01:49, 11.77it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -125268,8 +125117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13650/14932 [19:22<01:49, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  91%|▉| 13650/14932 [19:22<01:49, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  91%|▉| 13646/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  91%|▉| 13646/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -125277,8 +125126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13651/14932 [19:22<01:49, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  91%|▉| 13651/14932 [19:22<01:49, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13647/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  91%|▉| 13647/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -125286,8 +125135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13652/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13652/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13648/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  91%|▉| 13648/14932 [19:19<01:49, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -125295,8 +125144,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13653/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  91%|▉| 13653/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  91%|▉| 13649/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -125304,8 +125152,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13654/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  91%|▉| 13654/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  91%|▉| 13649/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125313,8 +125160,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13655/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  91%|▉| 13655/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13650/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  91%|▉| 13650/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -125322,8 +125169,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13656/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13656/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  91%|▉| 13651/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  91%|▉| 13651/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125331,8 +125178,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13657/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  91%|▉| 13657/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13652/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13652/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -125340,8 +125187,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13658/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  91%|▉| 13658/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13653/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13653/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125349,8 +125196,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13659/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  91%|▉| 13659/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13654/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  91%|▉| 13654/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125358,8 +125205,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13660/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13660/14932 [19:22<01:48, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  91%|▉| 13655/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  91%|▉| 13655/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -125367,8 +125214,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13661/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  91%|▉| 13661/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  91%|▉| 13656/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  91%|▉| 13656/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125376,8 +125223,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  91%|▉| 13662/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  91%|▉| 13662/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  91%|▉| 13657/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  91%|▉| 13657/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -125385,8 +125232,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13663/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13663/14932 [19:23<01:48, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  91%|▉| 13658/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  91%|▉| 13658/14932 [19:19<01:48, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125394,8 +125241,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13664/14932 [19:23<01:47, 11.74it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  92%|▉| 13664/14932 [19:23<01:47, 11.74it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  91%|▉| 13659/14932 [19:20<01:48, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  91%|▉| 13659/14932 [19:20<01:48, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125403,8 +125250,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13665/14932 [19:23<01:47, 11.74it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13665/14932 [19:23<01:47, 11.74it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  91%|▉| 13660/14932 [19:20<01:48, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  91%|▉| 13660/14932 [19:20<01:48, 11.77it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -125412,8 +125259,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13666/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13666/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13661/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  91%|▉| 13661/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125421,7 +125268,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13667/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  91%|▉| 13662/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  91%|▉| 13662/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -125429,7 +125277,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13667/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13663/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  92%|▉| 13663/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125437,8 +125286,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13668/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13668/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13664/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125446,8 +125294,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13669/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13669/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13664/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -125455,8 +125302,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13670/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13670/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13665/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  92%|▉| 13665/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -125464,7 +125311,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13671/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13666/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  92%|▉| 13666/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -125472,7 +125320,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13671/14932 [19:23<01:47, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  92%|▉| 13667/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  92%|▉| 13667/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125480,8 +125329,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13672/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  92%|▉| 13672/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  92%|▉| 13668/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  92%|▉| 13668/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -125489,8 +125338,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13673/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  92%|▉| 13673/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13669/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  92%|▉| 13669/14932 [19:20<01:47, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125498,8 +125347,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13674/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13674/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  92%|▉| 13670/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13670/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -125507,8 +125356,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13675/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  92%|▉| 13675/14932 [19:24<01:47, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13671/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  92%|▉| 13671/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -125516,8 +125365,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13676/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13676/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  92%|▉| 13672/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  92%|▉| 13672/14932 [19:21<01:47, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125525,8 +125374,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13677/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  92%|▉| 13677/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13673/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13673/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125534,8 +125383,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13678/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13678/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13674/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13674/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -125543,8 +125392,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13679/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13679/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  92%|▉| 13675/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  92%|▉| 13675/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125552,8 +125401,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13680/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  92%|▉| 13680/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  92%|▉| 13676/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13676/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -125561,8 +125410,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13681/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  92%|▉| 13681/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13677/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13677/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -125570,8 +125419,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13682/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  92%|▉| 13682/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  92%|▉| 13678/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13678/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -125579,8 +125428,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13683/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  92%|▉| 13683/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  92%|▉| 13679/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  92%|▉| 13679/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -125588,8 +125437,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13684/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  92%|▉| 13684/14932 [19:24<01:46, 11.75it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  92%|▉| 13680/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  92%|▉| 13680/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -125597,8 +125446,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13685/14932 [19:25<01:46, 11.75it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  92%|▉| 13685/14932 [19:25<01:46, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  92%|▉| 13681/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  92%|▉| 13681/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -125606,8 +125455,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13686/14932 [19:25<01:46, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  92%|▉| 13686/14932 [19:25<01:46, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13682/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  92%|▉| 13682/14932 [19:21<01:46, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125615,8 +125464,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13687/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13687/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  92%|▉| 13683/14932 [19:22<01:46, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13683/14932 [19:22<01:46, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125624,8 +125473,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13688/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  92%|▉| 13688/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13684/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13684/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125633,8 +125482,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13689/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13689/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13685/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13685/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -125642,8 +125491,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13690/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  92%|▉| 13690/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  92%|▉| 13686/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13686/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -125651,8 +125500,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13691/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  92%|▉| 13691/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  92%|▉| 13687/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13687/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -125660,8 +125509,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13692/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  92%|▉| 13692/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  92%|▉| 13688/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  92%|▉| 13688/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125669,8 +125518,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13693/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  92%|▉| 13693/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13689/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13689/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -125678,8 +125527,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13694/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13694/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  92%|▉| 13690/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  92%|▉| 13690/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125687,8 +125536,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13695/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  92%|▉| 13695/14932 [19:25<01:45, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  92%|▉| 13691/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13691/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -125696,8 +125545,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13696/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  92%|▉| 13696/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13692/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  92%|▉| 13692/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -125705,8 +125554,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13697/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13697/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13693/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13693/14932 [19:22<01:45, 11.77it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -125714,8 +125563,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13698/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13698/14932 [19:26<01:45, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  92%|▉| 13694/14932 [19:23<01:45, 11.77it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  92%|▉| 13694/14932 [19:23<01:45, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -125723,8 +125572,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13699/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  92%|▉| 13699/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13695/14932 [19:23<01:45, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  92%|▉| 13695/14932 [19:23<01:45, 11.77it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125732,8 +125581,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13700/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13700/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13696/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13696/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -125741,8 +125590,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13701/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13701/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13697/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13697/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -125750,8 +125599,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13702/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  92%|▉| 13702/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13698/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  92%|▉| 13698/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -125759,8 +125608,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13703/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13703/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13699/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  92%|▉| 13699/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125768,8 +125617,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13704/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13704/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13700/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13700/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -125777,8 +125626,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13705/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13705/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  92%|▉| 13701/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  92%|▉| 13701/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125786,8 +125635,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13706/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  92%|▉| 13706/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13702/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -125795,8 +125643,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13707/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13707/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13702/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -125804,8 +125651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13708/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13708/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13703/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  92%|▉| 13703/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -125813,8 +125660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13709/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13709/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  92%|▉| 13704/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13704/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -125822,8 +125669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13710/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  92%|▉| 13710/14932 [19:26<01:44, 11.75it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  92%|▉| 13705/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13705/14932 [19:23<01:44, 11.77it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125831,8 +125678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13711/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  92%|▉| 13711/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13706/14932 [19:24<01:44, 11.77it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13706/14932 [19:24<01:44, 11.77it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -125840,8 +125687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13712/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13712/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  92%|▉| 13707/14932 [19:24<01:44, 11.77it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  92%|▉| 13707/14932 [19:24<01:44, 11.77it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -125849,8 +125696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13713/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  92%|▉| 13713/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13708/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  92%|▉| 13708/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -125858,8 +125705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13714/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13714/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  92%|▉| 13709/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13709/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -125867,8 +125714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13715/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  92%|▉| 13715/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13710/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13710/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -125876,8 +125723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13716/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13716/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  92%|▉| 13711/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  92%|▉| 13711/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -125885,8 +125732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13717/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  92%|▉| 13717/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13712/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  92%|▉| 13712/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=4.8"
      ]
     },
     {
@@ -125894,8 +125741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13718/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13718/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  92%|▉| 13713/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=4.8\r",
+      "Epoch 0:  92%|▉| 13713/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125903,8 +125750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13719/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  92%|▉| 13719/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  92%|▉| 13714/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13714/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -125912,8 +125759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13720/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  92%|▉| 13720/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  92%|▉| 13715/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  92%|▉| 13715/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -125921,8 +125768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13721/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  92%|▉| 13721/14932 [19:27<01:43, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13716/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  92%|▉| 13716/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -125930,8 +125777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13722/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  92%|▉| 13722/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  92%|▉| 13717/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  92%|▉| 13717/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -125939,8 +125786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13723/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  92%|▉| 13723/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13718/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  92%|▉| 13718/14932 [19:24<01:43, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -125948,8 +125795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13724/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13724/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13719/14932 [19:25<01:43, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  92%|▉| 13719/14932 [19:25<01:43, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -125957,8 +125804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13725/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13725/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13720/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  92%|▉| 13720/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -125966,8 +125813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13726/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13726/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  92%|▉| 13721/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13721/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -125975,8 +125822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13727/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  92%|▉| 13727/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  92%|▉| 13722/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  92%|▉| 13722/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -125984,8 +125831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13728/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  92%|▉| 13728/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  92%|▉| 13723/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  92%|▉| 13723/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -125993,8 +125840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13729/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  92%|▉| 13729/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13724/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13724/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -126002,8 +125849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13730/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13730/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13725/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  92%|▉| 13725/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -126011,8 +125858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13731/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13731/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13726/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  92%|▉| 13726/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -126020,8 +125867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13732/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13732/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  92%|▉| 13727/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  92%|▉| 13727/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -126029,8 +125876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13733/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  92%|▉| 13733/14932 [19:28<01:42, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13728/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  92%|▉| 13728/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126038,8 +125885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13734/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13734/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13729/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13729/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -126047,8 +125894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13735/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13735/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  92%|▉| 13730/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  92%|▉| 13730/14932 [19:25<01:42, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -126056,8 +125903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13736/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  92%|▉| 13736/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  92%|▉| 13731/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  92%|▉| 13731/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -126065,8 +125912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13737/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  92%|▉| 13737/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  92%|▉| 13732/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  92%|▉| 13732/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -126074,8 +125921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13738/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  92%|▉| 13738/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  92%|▉| 13733/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13733/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -126083,8 +125930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13739/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  92%|▉| 13739/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13734/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13734/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -126092,8 +125939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13740/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13740/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13735/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  92%|▉| 13735/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -126101,8 +125948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13741/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13741/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  92%|▉| 13736/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  92%|▉| 13736/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -126110,8 +125957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13742/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  92%|▉| 13742/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  92%|▉| 13737/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  92%|▉| 13737/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -126119,8 +125966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13743/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  92%|▉| 13743/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13738/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13738/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126128,8 +125975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13744/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13744/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  92%|▉| 13739/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13739/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -126137,8 +125984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13745/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  92%|▉| 13745/14932 [19:29<01:41, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  92%|▉| 13740/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  92%|▉| 13740/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126146,8 +125993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13746/14932 [19:29<01:40, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  92%|▉| 13746/14932 [19:29<01:40, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  92%|▉| 13741/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13741/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126155,8 +126002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13747/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  92%|▉| 13747/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  92%|▉| 13742/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13742/14932 [19:26<01:41, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -126164,8 +126011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13748/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  92%|▉| 13748/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  92%|▉| 13743/14932 [19:26<01:40, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  92%|▉| 13743/14932 [19:26<01:40, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -126173,8 +126020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13749/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  92%|▉| 13749/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  92%|▉| 13744/14932 [19:26<01:40, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  92%|▉| 13744/14932 [19:26<01:40, 11.78it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -126182,8 +126029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13750/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  92%|▉| 13750/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  92%|▉| 13745/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  92%|▉| 13745/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -126191,8 +126038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13751/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  92%|▉| 13751/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13746/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13746/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -126200,8 +126047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13752/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13752/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13747/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13747/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -126209,8 +126056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13753/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13753/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13748/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13748/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -126218,8 +126065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13754/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13754/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  92%|▉| 13749/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  92%|▉| 13749/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -126227,8 +126074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13755/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  92%|▉| 13755/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  92%|▉| 13750/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  92%|▉| 13750/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -126236,8 +126083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13756/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  92%|▉| 13756/14932 [19:30<01:40, 11.75it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  92%|▉| 13751/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13751/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -126245,8 +126092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13757/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  92%|▉| 13757/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  92%|▉| 13752/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  92%|▉| 13752/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -126254,8 +126101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13758/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  92%|▉| 13758/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13753/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  92%|▉| 13753/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -126263,8 +126110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13759/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13759/14932 [19:30<01:39, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13754/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  92%|▉| 13754/14932 [19:27<01:40, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126272,8 +126119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13760/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13760/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13755/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13755/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -126281,8 +126128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13761/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13761/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  92%|▉| 13756/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  92%|▉| 13756/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -126290,8 +126137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13762/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  92%|▉| 13762/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13757/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  92%|▉| 13757/14932 [19:27<01:39, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -126299,8 +126146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13763/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13763/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  92%|▉| 13758/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  92%|▉| 13758/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126308,8 +126155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13764/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  92%|▉| 13764/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13759/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13759/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -126317,8 +126164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13765/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13765/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  92%|▉| 13760/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  92%|▉| 13760/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -126326,8 +126173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13766/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  92%|▉| 13766/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  92%|▉| 13761/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  92%|▉| 13761/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -126335,8 +126182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13767/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  92%|▉| 13767/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  92%|▉| 13762/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  92%|▉| 13762/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -126344,8 +126191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13768/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  92%|▉| 13768/14932 [19:31<01:39, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  92%|▉| 13763/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  92%|▉| 13763/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126353,8 +126200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13769/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  92%|▉| 13769/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13764/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13764/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -126362,8 +126209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13770/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13770/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13765/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  92%|▉| 13765/14932 [19:28<01:39, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -126371,8 +126218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13771/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13771/14932 [19:31<01:38, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13766/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13766/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -126380,8 +126227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13772/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13772/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  92%|▉| 13767/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  92%|▉| 13767/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -126389,8 +126236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13773/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  92%|▉| 13773/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13768/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13768/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -126398,8 +126245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13774/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13774/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13769/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  92%|▉| 13769/14932 [19:28<01:38, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -126407,8 +126254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13775/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  92%|▉| 13775/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13770/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  92%|▉| 13770/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -126416,8 +126263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13776/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13776/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13771/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13771/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -126425,8 +126272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13777/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13777/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13772/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  92%|▉| 13772/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -126434,8 +126281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13778/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13778/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  92%|▉| 13773/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13773/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -126443,8 +126290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13779/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  92%|▉| 13779/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13774/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  92%|▉| 13774/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126452,8 +126299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13780/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13780/14932 [19:32<01:38, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13775/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13775/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -126461,8 +126308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13781/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13781/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  92%|▉| 13776/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  92%|▉| 13776/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -126470,8 +126317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13782/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  92%|▉| 13782/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  92%|▉| 13777/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  92%|▉| 13777/14932 [19:29<01:38, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -126479,8 +126326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13783/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  92%|▉| 13783/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  92%|▉| 13778/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  92%|▉| 13778/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -126488,8 +126335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13784/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  92%|▉| 13784/14932 [19:32<01:37, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  92%|▉| 13779/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  92%|▉| 13779/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -126497,8 +126344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13785/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  92%|▉| 13785/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  92%|▉| 13780/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  92%|▉| 13780/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -126506,8 +126353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13786/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  92%|▉| 13786/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13781/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  92%|▉| 13781/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126515,8 +126362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13787/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13787/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13782/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13782/14932 [19:29<01:37, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -126524,8 +126371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13788/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13788/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  92%|▉| 13783/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  92%|▉| 13783/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -126533,8 +126380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13789/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  92%|▉| 13789/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13784/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13784/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -126542,8 +126389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13790/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13790/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13785/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  92%|▉| 13785/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -126551,8 +126398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13791/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13791/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13786/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  92%|▉| 13786/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -126560,8 +126407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13792/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13792/14932 [19:33<01:37, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  92%|▉| 13787/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  92%|▉| 13787/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -126569,8 +126416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13793/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  92%|▉| 13793/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  92%|▉| 13788/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  92%|▉| 13788/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -126578,8 +126425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13794/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  92%|▉| 13794/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  92%|▉| 13789/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  92%|▉| 13789/14932 [19:30<01:37, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -126587,8 +126434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13795/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  92%|▉| 13795/14932 [19:33<01:36, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  92%|▉| 13790/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  92%|▉| 13790/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -126596,8 +126443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13796/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  92%|▉| 13796/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  92%|▉| 13791/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  92%|▉| 13791/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -126605,8 +126452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13797/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  92%|▉| 13797/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  92%|▉| 13792/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  92%|▉| 13792/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -126614,8 +126461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13798/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  92%|▉| 13798/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13793/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  92%|▉| 13793/14932 [19:30<01:36, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -126623,8 +126470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13799/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13799/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  92%|▉| 13794/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  92%|▉| 13794/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126632,8 +126479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13800/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  92%|▉| 13800/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13795/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13795/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -126641,8 +126488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13801/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13801/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  92%|▉| 13796/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  92%|▉| 13796/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126650,8 +126497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13802/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  92%|▉| 13802/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  92%|▉| 13797/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13797/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126659,8 +126506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13803/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  92%|▉| 13803/14932 [19:34<01:36, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13798/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13798/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126668,8 +126515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13804/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13804/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13799/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13799/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -126677,8 +126524,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13805/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13805/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13800/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  92%|▉| 13800/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -126686,8 +126533,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13806/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  92%|▉| 13806/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13801/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  92%|▉| 13801/14932 [19:31<01:36, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126695,8 +126542,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13807/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  92%|▉| 13807/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  92%|▉| 13802/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13802/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -126704,8 +126551,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13808/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  92%|▉| 13808/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  92%|▉| 13803/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  92%|▉| 13803/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -126713,8 +126560,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13809/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  92%|▉| 13809/14932 [19:34<01:35, 11.75it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  92%|▉| 13804/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  92%|▉| 13804/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -126722,8 +126569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13810/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  92%|▉| 13810/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  92%|▉| 13805/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  92%|▉| 13805/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126731,8 +126578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13811/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  92%|▉| 13811/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  92%|▉| 13806/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  92%|▉| 13806/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -126740,8 +126587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  92%|▉| 13812/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  92%|▉| 13812/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  92%|▉| 13807/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  92%|▉| 13807/14932 [19:31<01:35, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -126749,8 +126596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13813/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  93%|▉| 13813/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  92%|▉| 13808/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  92%|▉| 13808/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -126758,8 +126605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13814/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13814/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  92%|▉| 13809/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  92%|▉| 13809/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -126767,8 +126614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13815/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  93%|▉| 13815/14932 [19:35<01:35, 11.75it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  92%|▉| 13810/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  92%|▉| 13810/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126776,8 +126623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13816/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13816/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  92%|▉| 13811/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13811/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126785,8 +126632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13817/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  93%|▉| 13817/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  92%|▉| 13812/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  92%|▉| 13812/14932 [19:32<01:35, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -126794,8 +126641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13818/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13818/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13813/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  93%|▉| 13813/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -126803,8 +126650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13819/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  93%|▉| 13819/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13814/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  93%|▉| 13814/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -126812,8 +126659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13820/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13820/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  93%|▉| 13815/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  93%|▉| 13815/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -126821,8 +126668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13821/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  93%|▉| 13821/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  93%|▉| 13816/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  93%|▉| 13816/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -126830,8 +126677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13822/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  93%|▉| 13822/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13817/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13817/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -126839,8 +126686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13823/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13823/14932 [19:35<01:34, 11.75it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  93%|▉| 13818/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13818/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -126848,8 +126695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13824/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  93%|▉| 13824/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  93%|▉| 13819/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13819/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -126857,8 +126704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13825/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  93%|▉| 13825/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  93%|▉| 13820/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  93%|▉| 13820/14932 [19:32<01:34, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126866,8 +126713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13826/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  93%|▉| 13826/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  93%|▉| 13821/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13821/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -126875,8 +126722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13827/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  93%|▉| 13827/14932 [19:36<01:34, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13822/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  93%|▉| 13822/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -126884,8 +126731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13828/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13828/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  93%|▉| 13823/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13823/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -126893,8 +126740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13829/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  93%|▉| 13829/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13824/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  93%|▉| 13824/14932 [19:33<01:34, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -126902,8 +126749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13830/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13830/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  93%|▉| 13825/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  93%|▉| 13825/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -126911,8 +126758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13831/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  93%|▉| 13831/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13826/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13826/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126920,8 +126767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13832/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  93%|▉| 13832/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13827/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13827/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -126929,8 +126776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13833/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13833/14932 [19:36<01:33, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13828/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  93%|▉| 13828/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -126938,8 +126785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13834/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13834/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  93%|▉| 13829/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13829/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -126947,8 +126794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13835/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13835/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  93%|▉| 13830/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13830/14932 [19:33<01:33, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -126956,8 +126803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13836/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  93%|▉| 13836/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  93%|▉| 13831/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  93%|▉| 13831/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -126965,8 +126812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13837/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  93%|▉| 13837/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  93%|▉| 13832/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  93%|▉| 13832/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -126974,8 +126821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13838/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  93%|▉| 13838/14932 [19:37<01:33, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13833/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  93%|▉| 13833/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -126983,8 +126830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13839/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13839/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  93%|▉| 13834/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  93%|▉| 13834/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -126992,8 +126839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13840/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  93%|▉| 13840/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13835/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13835/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127001,8 +126848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13841/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13841/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  93%|▉| 13836/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13836/14932 [19:34<01:33, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127010,8 +126857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13842/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  93%|▉| 13842/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  93%|▉| 13837/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13837/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -127019,8 +126866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13843/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  93%|▉| 13843/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  93%|▉| 13838/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  93%|▉| 13838/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -127028,8 +126875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13844/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  93%|▉| 13844/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13839/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  93%|▉| 13839/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -127037,8 +126884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13845/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13845/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13840/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  93%|▉| 13840/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -127046,8 +126893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13846/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  93%|▉| 13846/14932 [19:37<01:32, 11.75it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  93%|▉| 13841/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  93%|▉| 13841/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -127055,8 +126902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13847/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  93%|▉| 13847/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  93%|▉| 13842/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13842/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127064,8 +126911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13848/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  93%|▉| 13848/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13843/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13843/14932 [19:34<01:32, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -127073,8 +126920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13849/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13849/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  93%|▉| 13844/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  93%|▉| 13844/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -127082,8 +126929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13850/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  93%|▉| 13850/14932 [19:38<01:32, 11.75it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  93%|▉| 13845/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  93%|▉| 13845/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -127091,8 +126938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13851/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  93%|▉| 13851/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13846/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  93%|▉| 13846/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -127100,8 +126947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13852/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13852/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  93%|▉| 13847/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  93%|▉| 13847/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -127109,8 +126956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13853/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  93%|▉| 13853/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13848/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  93%|▉| 13848/14932 [19:35<01:32, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127118,8 +126965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13854/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13854/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13849/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13849/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -127127,8 +126974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13855/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13855/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  93%|▉| 13850/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  93%|▉| 13850/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -127136,8 +126983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13856/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  93%|▉| 13856/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13851/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  93%|▉| 13851/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -127145,8 +126992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13857/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  93%|▉| 13857/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  93%|▉| 13852/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  93%|▉| 13852/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -127154,8 +127001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13858/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13858/14932 [19:38<01:31, 11.75it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  93%|▉| 13853/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  93%|▉| 13853/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -127163,8 +127010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13859/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  93%|▉| 13859/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13854/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  93%|▉| 13854/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127172,8 +127019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13860/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13860/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13855/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13855/14932 [19:35<01:31, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127181,8 +127028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13861/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  93%|▉| 13861/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13856/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13856/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127190,8 +127037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13862/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13862/14932 [19:39<01:31, 11.75it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13857/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13857/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -127199,8 +127046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13863/14932 [19:39<01:30, 11.75it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13863/14932 [19:39<01:30, 11.75it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13858/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  93%|▉| 13858/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127208,8 +127055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13864/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13864/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  93%|▉| 13859/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13859/14932 [19:36<01:31, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -127217,8 +127064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13865/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  93%|▉| 13865/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  93%|▉| 13860/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13860/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -127226,8 +127073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13866/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  93%|▉| 13866/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  93%|▉| 13861/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  93%|▉| 13861/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -127235,8 +127082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13867/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  93%|▉| 13867/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  93%|▉| 13862/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  93%|▉| 13862/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -127244,8 +127091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13868/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  93%|▉| 13868/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  93%|▉| 13863/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13863/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127253,8 +127100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13869/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  93%|▉| 13869/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13864/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13864/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127262,8 +127109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13870/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13870/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  93%|▉| 13865/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13865/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -127271,8 +127118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13871/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  93%|▉| 13871/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13866/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13866/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127280,8 +127127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13872/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13872/14932 [19:39<01:30, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13867/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13867/14932 [19:36<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127289,8 +127136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13873/14932 [19:40<01:30, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13873/14932 [19:40<01:30, 11.76it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  93%|▉| 13868/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13868/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -127298,8 +127145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13874/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  93%|▉| 13874/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  93%|▉| 13869/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  93%|▉| 13869/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127307,8 +127154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13875/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  93%|▉| 13875/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  93%|▉| 13870/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13870/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -127316,8 +127163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13876/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  93%|▉| 13876/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13871/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  93%|▉| 13871/14932 [19:37<01:30, 11.78it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -127325,8 +127172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13877/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13877/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  93%|▉| 13872/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  93%|▉| 13872/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -127334,8 +127181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13878/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  93%|▉| 13878/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13873/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  93%|▉| 13873/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -127343,8 +127190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13879/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13879/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  93%|▉| 13874/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  93%|▉| 13874/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127352,8 +127199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13880/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  93%|▉| 13880/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13875/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13875/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -127361,8 +127208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13881/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  93%|▉| 13881/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  93%|▉| 13876/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  93%|▉| 13876/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127370,8 +127217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13882/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  93%|▉| 13882/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13877/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13877/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -127379,7 +127226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13883/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13878/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  93%|▉| 13878/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -127387,7 +127235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13883/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13879/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  93%|▉| 13879/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127395,8 +127244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13884/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13884/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  93%|▉| 13880/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13880/14932 [19:37<01:29, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -127404,8 +127253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13885/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  93%|▉| 13885/14932 [19:40<01:29, 11.76it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  93%|▉| 13881/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  93%|▉| 13881/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -127413,8 +127262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13886/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  93%|▉| 13886/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13882/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13882/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127422,8 +127271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13887/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  93%|▉| 13887/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  93%|▉| 13883/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13883/14932 [19:38<01:29, 11.78it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -127431,8 +127280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13888/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  93%|▉| 13888/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13884/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  93%|▉| 13884/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127440,8 +127289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13889/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13889/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  93%|▉| 13885/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13885/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127449,8 +127298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13890/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  93%|▉| 13890/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13886/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13886/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -127458,8 +127307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13891/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13891/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  93%|▉| 13887/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  93%|▉| 13887/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -127467,8 +127316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13892/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  93%|▉| 13892/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  93%|▉| 13888/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13888/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -127476,8 +127325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13893/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  93%|▉| 13893/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  93%|▉| 13889/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  93%|▉| 13889/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -127485,8 +127334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13894/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  93%|▉| 13894/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  93%|▉| 13890/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13890/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127494,8 +127343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13895/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  93%|▉| 13895/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  93%|▉| 13891/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13891/14932 [19:38<01:28, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127503,8 +127352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13896/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  93%|▉| 13896/14932 [19:41<01:28, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13892/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13892/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -127512,8 +127361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13897/14932 [19:42<01:28, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13897/14932 [19:42<01:28, 11.76it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  93%|▉| 13893/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  93%|▉| 13893/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127521,8 +127370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13898/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  93%|▉| 13898/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13894/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13894/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127530,7 +127379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13899/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13895/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13895/14932 [19:39<01:28, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -127538,7 +127388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13899/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  93%|▉| 13896/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  93%|▉| 13896/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -127546,8 +127397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13900/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  93%|▉| 13900/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  93%|▉| 13897/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  93%|▉| 13897/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -127555,8 +127406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13901/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  93%|▉| 13901/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13898/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  93%|▉| 13898/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127564,8 +127415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13902/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13902/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  93%|▉| 13899/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13899/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127573,8 +127424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13903/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  93%|▉| 13903/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  93%|▉| 13900/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13900/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -127582,8 +127433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13904/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  93%|▉| 13904/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13901/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  93%|▉| 13901/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -127591,8 +127442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13905/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  93%|▉| 13905/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13902/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  93%|▉| 13902/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -127600,8 +127451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13906/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13906/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13903/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  93%|▉| 13903/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -127609,8 +127460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13907/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13907/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  93%|▉| 13904/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  93%|▉| 13904/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127618,8 +127469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13908/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  93%|▉| 13908/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13905/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13905/14932 [19:39<01:27, 11.78it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -127627,8 +127478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13909/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13909/14932 [19:42<01:27, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13906/14932 [19:40<01:27, 11.78it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  93%|▉| 13906/14932 [19:40<01:27, 11.78it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -127636,8 +127487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13910/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13910/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13907/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  93%|▉| 13907/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127645,8 +127496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13911/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13911/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13908/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13908/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -127654,8 +127505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13912/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13912/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13909/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  93%|▉| 13909/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -127663,8 +127514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13913/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13913/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  93%|▉| 13910/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13910/14932 [19:40<01:26, 11.78it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -127672,8 +127523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13914/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  93%|▉| 13914/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13911/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  93%|▉| 13911/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -127681,8 +127532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13915/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13915/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  93%|▉| 13912/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13912/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127690,8 +127541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13916/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  93%|▉| 13916/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13913/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13913/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127699,8 +127550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13917/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13917/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13914/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13914/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -127708,7 +127559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13918/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13915/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  93%|▉| 13915/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -127716,7 +127568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13918/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  93%|▉| 13916/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  93%|▉| 13916/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -127724,8 +127577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13919/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13919/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  93%|▉| 13917/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  93%|▉| 13917/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -127733,7 +127586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13920/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  93%|▉| 13918/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  93%|▉| 13918/14932 [19:40<01:26, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -127741,7 +127595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13920/14932 [19:43<01:26, 11.76it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  93%|▉| 13919/14932 [19:41<01:25, 11.79it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  93%|▉| 13919/14932 [19:41<01:25, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -127749,8 +127604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13921/14932 [19:43<01:25, 11.76it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  93%|▉| 13921/14932 [19:43<01:25, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13920/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13920/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -127758,8 +127613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13922/14932 [19:43<01:25, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13922/14932 [19:43<01:25, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  93%|▉| 13921/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  93%|▉| 13921/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -127767,8 +127622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13923/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  93%|▉| 13923/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13922/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13922/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -127776,8 +127631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13924/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13924/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  93%|▉| 13923/14932 [19:41<01:25, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  93%|▉| 13923/14932 [19:41<01:25, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127785,8 +127640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13925/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  93%|▉| 13925/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  93%|▉| 13924/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13924/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -127794,8 +127649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13926/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  93%|▉| 13926/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13925/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  93%|▉| 13925/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -127803,8 +127658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13927/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13927/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  93%|▉| 13926/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  93%|▉| 13926/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -127812,8 +127667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13928/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  93%|▉| 13928/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13927/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  93%|▉| 13927/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -127821,8 +127676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13929/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13929/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  93%|▉| 13928/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  93%|▉| 13928/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -127830,8 +127685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13930/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  93%|▉| 13930/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13929/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13929/14932 [19:41<01:25, 11.78it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -127839,8 +127694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13931/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  93%|▉| 13931/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  93%|▉| 13930/14932 [19:42<01:25, 11.78it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  93%|▉| 13930/14932 [19:42<01:25, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -127848,8 +127703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13932/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  93%|▉| 13932/14932 [19:44<01:25, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  93%|▉| 13931/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13931/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127857,8 +127712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13933/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  93%|▉| 13933/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  93%|▉| 13932/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13932/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -127866,8 +127721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13934/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  93%|▉| 13934/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=5.6"
+      "Epoch 0:  93%|▉| 13933/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  93%|▉| 13933/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127875,8 +127730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13935/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=5.6\r",
-      "Epoch 0:  93%|▉| 13935/14932 [19:44<01:24, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  93%|▉| 13934/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13934/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -127884,8 +127739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13936/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  93%|▉| 13936/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  93%|▉| 13935/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13935/14932 [19:42<01:24, 11.78it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -127893,8 +127748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13937/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  93%|▉| 13937/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13936/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13936/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -127902,8 +127757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13938/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13938/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13937/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13937/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127911,8 +127766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13939/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13939/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=5.5"
+      "Epoch 0:  93%|▉| 13938/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13938/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -127920,8 +127775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13940/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=5.5\r",
-      "Epoch 0:  93%|▉| 13940/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  93%|▉| 13939/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  93%|▉| 13939/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -127929,8 +127784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13941/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  93%|▉| 13941/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  93%|▉| 13940/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  93%|▉| 13940/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -127938,8 +127793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13942/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  93%|▉| 13942/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  93%|▉| 13941/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  93%|▉| 13941/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127947,8 +127802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13943/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  93%|▉| 13943/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  93%|▉| 13942/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13942/14932 [19:42<01:24, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127956,8 +127811,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13944/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  93%|▉| 13944/14932 [19:45<01:24, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  93%|▉| 13943/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -127965,8 +127819,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13945/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13945/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13943/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -127974,8 +127827,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13946/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  93%|▉| 13946/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  93%|▉| 13944/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13944/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -127983,8 +127836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13947/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  93%|▉| 13947/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  93%|▉| 13945/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  93%|▉| 13945/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -127992,8 +127845,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13948/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  93%|▉| 13948/14932 [19:45<01:23, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13946/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  93%|▉| 13946/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -128001,8 +127854,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13949/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13949/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  93%|▉| 13947/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  93%|▉| 13947/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128010,8 +127863,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13950/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  93%|▉| 13950/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  93%|▉| 13948/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  93%|▉| 13948/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128019,8 +127872,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13951/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  93%|▉| 13951/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13949/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  93%|▉| 13949/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -128028,8 +127881,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13952/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  93%|▉| 13952/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  93%|▉| 13950/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  93%|▉| 13950/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -128037,8 +127890,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13953/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  93%|▉| 13953/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  93%|▉| 13951/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  93%|▉| 13951/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128046,8 +127899,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13954/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  93%|▉| 13954/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  93%|▉| 13952/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  93%|▉| 13952/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -128055,8 +127908,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13955/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  93%|▉| 13955/14932 [19:46<01:23, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  93%|▉| 13953/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13953/14932 [19:43<01:23, 11.79it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -128064,8 +127917,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13956/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  93%|▉| 13956/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  93%|▉| 13954/14932 [19:43<01:22, 11.79it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  93%|▉| 13954/14932 [19:43<01:22, 11.79it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -128073,8 +127926,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13957/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  93%|▉| 13957/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  93%|▉| 13955/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  93%|▉| 13955/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -128082,8 +127935,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13958/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  93%|▉| 13958/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  93%|▉| 13956/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -128091,8 +127943,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13959/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  93%|▉| 13959/14932 [19:46<01:22, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13956/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128100,7 +127951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13960/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  93%|▉| 13957/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  93%|▉| 13957/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -128108,7 +127960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13960/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  93%|▉| 13958/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  93%|▉| 13958/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128116,8 +127969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  93%|▉| 13961/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  93%|▉| 13961/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  93%|▉| 13959/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  93%|▉| 13959/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -128125,8 +127978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13962/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 13962/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  93%|▉| 13960/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  93%|▉| 13960/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -128134,8 +127987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13963/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  94%|▉| 13963/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  93%|▉| 13961/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  93%|▉| 13961/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -128143,8 +127996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13964/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  94%|▉| 13964/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  94%|▉| 13962/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  94%|▉| 13962/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -128152,8 +128005,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13965/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  94%|▉| 13965/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  94%|▉| 13963/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -128161,8 +128013,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13966/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  94%|▉| 13966/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  94%|▉| 13963/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128170,8 +128021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13967/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  94%|▉| 13967/14932 [19:47<01:22, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 13964/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 13964/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128179,8 +128030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13968/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 13968/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 13965/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 13965/14932 [19:44<01:22, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128188,8 +128039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13969/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 13969/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  94%|▉| 13966/14932 [19:44<01:21, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 13966/14932 [19:44<01:21, 11.79it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -128197,8 +128048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13970/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  94%|▉| 13970/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  94%|▉| 13967/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  94%|���| 13967/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128206,8 +128057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13971/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  94%|▉| 13971/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  94%|▉| 13968/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 13968/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -128215,8 +128066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13972/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  94%|▉| 13972/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  94%|▉| 13969/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 13969/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128224,8 +128075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13973/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  94%|▉| 13973/14932 [19:47<01:21, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 13970/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13970/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -128233,8 +128084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13974/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 13974/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  94%|▉| 13971/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  94%|▉| 13971/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128242,8 +128093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13975/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  94%|▉| 13975/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  94%|▉| 13972/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 13972/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -128251,8 +128102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13976/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  94%|▉| 13976/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 13973/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  94%|▉| 13973/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -128260,8 +128111,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13977/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 13977/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  94%|▉| 13974/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  94%|▉| 13974/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -128269,8 +128120,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13978/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  94%|▉| 13978/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 13975/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 13975/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128278,8 +128129,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13979/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 13979/14932 [19:48<01:21, 11.76it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  94%|▉| 13976/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 13976/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -128287,8 +128138,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13980/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  94%|▉| 13980/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  94%|▉| 13977/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  94%|▉| 13977/14932 [19:45<01:21, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -128296,8 +128147,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13981/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  94%|▉| 13981/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 13978/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  94%|▉| 13978/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -128305,8 +128156,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13982/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 13982/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 13979/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 13979/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128314,8 +128165,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13983/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 13983/14932 [19:48<01:20, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 13980/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 13980/14932 [19:45<01:20, 11.79it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -128323,8 +128174,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13984/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 13984/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  94%|▉| 13981/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  94%|▉| 13981/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128332,8 +128183,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13985/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  94%|▉| 13985/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 13982/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 13982/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -128341,8 +128192,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13986/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 13986/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 13983/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 13983/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -128350,8 +128201,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13987/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 13987/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 13984/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 13984/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -128359,7 +128210,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13988/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 13985/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  94%|▉| 13985/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128367,7 +128219,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13988/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  94%|▉| 13986/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13986/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -128375,8 +128228,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13989/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  94%|▉| 13989/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  94%|▉| 13987/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  94%|▉| 13987/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -128384,8 +128237,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13990/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  94%|▉| 13990/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  94%|▉| 13988/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  94%|▉| 13988/14932 [19:46<01:20, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128393,8 +128246,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13991/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  94%|▉| 13991/14932 [19:49<01:20, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  94%|▉| 13989/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 13989/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -128402,8 +128255,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13992/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  94%|▉| 13992/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 13990/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  94%|▉| 13990/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128411,8 +128264,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13993/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 13993/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 13991/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13991/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128420,8 +128273,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13994/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 13994/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  94%|▉| 13992/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13992/14932 [19:46<01:19, 11.79it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -128429,8 +128282,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13995/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  94%|▉| 13995/14932 [19:49<01:19, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 13993/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  94%|▉| 13993/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128438,8 +128291,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13996/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 13996/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  94%|▉| 13994/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13994/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -128447,8 +128300,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13997/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  94%|▉| 13997/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 13995/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  94%|▉| 13995/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128456,8 +128309,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13998/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 13998/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 13996/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 13996/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128465,8 +128318,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 13999/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 13999/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  94%|▉| 13997/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13997/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -128474,8 +128327,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14000/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  94%|▉| 14000/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 13998/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  94%|▉| 13998/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128483,8 +128336,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14001/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 14001/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 13999/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 13999/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -128492,8 +128345,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14002/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14002/14932 [19:50<01:19, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14000/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  94%|▉| 14000/14932 [19:47<01:19, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -128501,8 +128354,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14003/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14003/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  94%|▉| 14001/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  94%|▉| 14001/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -128510,8 +128363,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14004/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  94%|▉| 14004/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  94%|▉| 14002/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  94%|▉| 14002/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -128519,8 +128372,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14005/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  94%|▉| 14005/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14003/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14003/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -128528,8 +128381,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14006/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14006/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  94%|▉| 14004/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  94%|▉| 14004/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -128537,8 +128390,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14007/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  94%|▉| 14007/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14005/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  94%|▉| 14005/14932 [19:47<01:18, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128546,8 +128399,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14008/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14008/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14006/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 14006/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -128555,8 +128408,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14009/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14009/14932 [19:50<01:18, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14007/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  94%|▉| 14007/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -128564,8 +128417,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14010/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14010/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 14008/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14008/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -128573,8 +128426,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14011/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14011/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  94%|▉| 14009/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14009/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128582,8 +128435,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14012/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  94%|▉| 14012/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14010/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14010/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128591,8 +128444,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14013/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14013/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  94%|▉| 14011/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 14011/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128600,8 +128453,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14014/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  94%|▉| 14014/14932 [19:51<01:18, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14012/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14012/14932 [19:48<01:18, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -128609,8 +128462,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14015/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14015/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 14013/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  94%|▉| 14013/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -128618,8 +128471,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14016/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14016/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  94%|▉| 14014/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  94%|▉| 14014/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -128627,8 +128480,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14017/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  94%|▉| 14017/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  94%|▉| 14015/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  94%|▉| 14015/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128636,8 +128489,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14018/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  94%|▉| 14018/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14016/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14016/14932 [19:48<01:17, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -128645,8 +128498,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14019/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14019/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  94%|▉| 14017/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14017/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -128654,8 +128507,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14020/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  94%|▉| 14020/14932 [19:51<01:17, 11.76it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  94%|▉| 14018/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  94%|▉| 14018/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -128663,8 +128516,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14021/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  94%|▉| 14021/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14019/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  94%|▉| 14019/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -128672,8 +128525,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14022/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14022/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14020/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  94%|▉| 14020/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128681,8 +128534,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14023/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14023/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 14021/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 14021/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128690,8 +128543,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14024/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14024/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  94%|▉| 14022/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 14022/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128699,8 +128552,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14025/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  94%|▉| 14025/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  94%|▉| 14023/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 14023/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128708,8 +128561,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14026/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  94%|▉| 14026/14932 [19:52<01:17, 11.76it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  94%|▉| 14024/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14024/14932 [19:49<01:17, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -128717,8 +128570,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14027/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  94%|▉| 14027/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  94%|▉| 14025/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  94%|▉| 14025/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -128726,8 +128579,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14028/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  94%|▉| 14028/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14026/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  94%|▉| 14026/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -128735,8 +128588,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14029/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14029/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  94%|▉| 14027/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  94%|▉| 14027/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128744,8 +128597,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14030/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  94%|▉| 14030/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 14028/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 14028/14932 [19:49<01:16, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -128753,8 +128606,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14031/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 14031/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=5.1"
+      "Epoch 0:  94%|▉| 14029/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  94%|▉| 14029/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128762,8 +128615,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14032/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=5.1\r",
-      "Epoch 0:  94%|▉| 14032/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 14030/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14030/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -128771,8 +128624,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14033/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 14033/14932 [19:52<01:16, 11.76it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  94%|▉| 14031/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  94%|▉| 14031/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128780,8 +128633,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14034/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  94%|▉| 14034/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  94%|▉| 14032/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14032/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -128789,8 +128642,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14035/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  94%|▉| 14035/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  94%|▉| 14033/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  94%|▉| 14033/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -128798,8 +128651,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14036/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  94%|▉| 14036/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  94%|▉| 14034/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  94%|▉| 14034/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -128807,7 +128660,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14037/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  94%|▉| 14035/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14035/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128815,7 +128669,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14037/14932 [19:53<01:16, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14036/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14036/14932 [19:50<01:16, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -128823,8 +128678,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14038/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14038/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14037/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14037/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -128832,8 +128687,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14039/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14039/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  94%|▉| 14038/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14038/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -128841,8 +128696,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14040/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  94%|▉| 14040/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14039/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  94%|▉| 14039/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -128850,8 +128705,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14041/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14041/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14040/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  94%|▉| 14040/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -128859,8 +128714,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14042/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14042/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  94%|▉| 14041/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 14041/14932 [19:50<01:15, 11.79it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -128868,8 +128723,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14043/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  94%|▉| 14043/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  94%|▉| 14042/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  94%|▉| 14042/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -128877,8 +128732,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14044/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  94%|▉| 14044/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14043/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  94%|▉| 14043/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128886,8 +128741,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14045/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14045/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14044/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14044/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -128895,8 +128750,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14046/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14046/14932 [19:53<01:15, 11.76it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14045/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14045/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -128904,8 +128759,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14047/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14047/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  94%|▉| 14046/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 14046/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -128913,8 +128768,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14048/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  94%|▉| 14048/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  94%|▉| 14047/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  94%|▉| 14047/14932 [19:51<01:15, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -128922,8 +128777,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14049/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  94%|▉| 14049/14932 [19:54<01:15, 11.76it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  94%|▉| 14048/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  94%|▉| 14048/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -128931,8 +128786,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14050/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  94%|▉| 14050/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 14049/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  94%|▉| 14049/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -128940,8 +128795,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14051/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 14051/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14050/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  94%|▉| 14050/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -128949,8 +128804,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14052/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14052/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  94%|▉| 14051/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14051/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -128958,8 +128813,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14053/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  94%|▉| 14053/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  94%|▉| 14052/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14052/14932 [19:51<01:14, 11.79it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -128967,8 +128822,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14054/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  94%|▉| 14054/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  94%|▉| 14053/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  94%|▉| 14053/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -128976,8 +128831,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14055/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  94%|▉| 14055/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  94%|▉| 14054/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  94%|▉| 14054/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -128985,8 +128840,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14056/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  94%|▉| 14056/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  94%|▉| 14055/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  94%|▉| 14055/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -128994,8 +128849,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14057/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  94%|▉| 14057/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  94%|▉| 14056/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14056/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -129003,8 +128858,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14058/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  94%|▉| 14058/14932 [19:54<01:14, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14057/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 14057/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -129012,8 +128867,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14059/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14059/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14058/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  94%|▉| 14058/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -129021,8 +128876,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14060/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14060/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14059/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  94%|▉| 14059/14932 [19:52<01:14, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129030,8 +128885,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14061/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14061/14932 [19:55<01:14, 11.76it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  94%|▉| 14060/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14060/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -129039,8 +128894,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14062/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  94%|▉| 14062/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 14061/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  94%|▉| 14061/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -129048,8 +128903,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14063/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 14063/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  94%|▉| 14062/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  94%|▉| 14062/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -129057,8 +128912,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14064/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  94%|▉| 14064/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14063/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  94%|▉| 14063/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -129066,8 +128921,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14065/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14065/14932 [19:55<01:13, 11.76it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  94%|▉| 14064/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  94%|▉| 14064/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -129075,8 +128930,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14066/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  94%|▉| 14066/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14065/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  94%|▉| 14065/14932 [19:52<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129084,8 +128939,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14067/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14067/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14066/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14066/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -129093,8 +128948,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14068/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14068/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14067/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 14067/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129102,8 +128957,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14069/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14069/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  94%|▉| 14068/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  94%|▉| 14068/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129111,8 +128966,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14070/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  94%|▉| 14070/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  94%|▉| 14069/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14069/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129120,8 +128975,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14071/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  94%|▉| 14071/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14070/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14070/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -129129,8 +128984,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14072/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14072/14932 [19:55<01:13, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14071/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  94%|▉| 14071/14932 [19:53<01:13, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129138,8 +128993,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14073/14932 [19:56<01:13, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14073/14932 [19:56<01:13, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14072/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14072/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129147,8 +129002,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14074/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14074/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14073/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14073/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -129156,8 +129011,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14075/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14075/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14074/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  94%|▉| 14074/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -129165,8 +129020,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14076/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14076/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  94%|▉| 14075/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  94%|▉| 14075/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -129174,8 +129029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14077/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  94%|▉| 14077/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14076/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14076/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -129183,8 +129038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14078/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14078/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 14077/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14077/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129192,8 +129047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14079/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14079/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  94%|▉| 14078/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14078/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -129201,8 +129056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14080/14932 [19:56<01:12, 11.76it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  94%|▉| 14080/14932 [19:56<01:12, 11.76it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14079/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  94%|▉| 14079/14932 [19:53<01:12, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -129210,8 +129065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14081/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14081/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  94%|▉| 14080/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14080/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129219,8 +129074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14082/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  94%|▉| 14082/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  94%|▉| 14081/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14081/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129228,8 +129083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14083/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  94%|▉| 14083/14932 [19:56<01:12, 11.77it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  94%|▉| 14082/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14082/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -129237,8 +129092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14084/14932 [19:57<01:12, 11.77it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  94%|▉| 14084/14932 [19:57<01:12, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  94%|▉| 14083/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  94%|▉| 14083/14932 [19:54<01:12, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -129246,8 +129101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14085/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  94%|▉| 14085/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  94%|▉| 14084/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  94%|▉| 14084/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129255,8 +129110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14086/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  94%|▉| 14086/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14085/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14085/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129264,8 +129119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14087/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14087/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  94%|▉| 14086/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  94%|▉| 14086/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -129273,8 +129128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14088/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  94%|▉| 14088/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  94%|▉| 14087/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  94%|▉| 14087/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -129282,8 +129137,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14089/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  94%|▉| 14089/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  94%|▉| 14088/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -129291,8 +129145,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14090/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  94%|▉| 14090/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14088/14932 [19:54<01:11, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -129300,8 +129153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14091/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14091/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  94%|▉| 14089/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  94%|▉| 14089/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129309,8 +129162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14092/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  94%|▉| 14092/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  94%|▉| 14090/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14090/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129318,8 +129171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14093/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  94%|▉| 14093/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14091/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  94%|▉| 14091/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -129327,8 +129180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14094/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14094/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  94%|▉| 14092/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  94%|▉| 14092/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -129336,8 +129189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14095/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  94%|▉| 14095/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  94%|▉| 14093/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  94%|▉| 14093/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129345,8 +129198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14096/14932 [19:57<01:11, 11.77it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  94%|▉| 14096/14932 [19:58<01:11, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  94%|▉| 14094/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14094/14932 [19:55<01:11, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129354,8 +129207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14097/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  94%|▉| 14097/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14095/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  94%|▉| 14095/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -129363,8 +129216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14098/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14098/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  94%|▉| 14096/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  94%|▉| 14096/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129372,8 +129225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14099/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  94%|▉| 14099/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  94%|▉| 14097/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  94%|▉| 14097/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -129381,8 +129234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14100/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  94%|▉| 14100/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  94%|▉| 14098/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  94%|▉| 14098/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -129390,8 +129243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14101/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  94%|▉| 14101/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14099/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  94%|▉| 14099/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129399,8 +129252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14102/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14102/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  94%|▉| 14100/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14100/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -129408,8 +129261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14103/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  94%|▉| 14103/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  94%|▉| 14101/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  94%|▉| 14101/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129417,8 +129270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14104/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  94%|▉| 14104/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 14102/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14102/14932 [19:55<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129426,8 +129279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14105/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  94%|▉| 14105/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  94%|▉| 14103/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  94%|▉| 14103/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -129435,8 +129288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14106/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  94%|▉| 14106/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  94%|▉| 14104/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  94%|▉| 14104/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129444,7 +129297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14107/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  94%|▉| 14105/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  94%|▉| 14105/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -129452,7 +129306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14107/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  94%|▉| 14106/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  94%|▉| 14106/14932 [19:56<01:10, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -129460,8 +129315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14108/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  94%|▉| 14108/14932 [19:58<01:10, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  94%|▉| 14107/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  94%|▉| 14107/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -129469,8 +129324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14109/14932 [19:58<01:09, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  94%|▉| 14109/14932 [19:58<01:09, 11.77it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  94%|▉| 14108/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  94%|▉| 14108/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -129478,8 +129333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  94%|▉| 14110/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  94%|▉| 14110/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  94%|▉| 14109/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  94%|▉| 14109/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -129487,8 +129342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14111/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14111/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  94%|▉| 14110/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  94%|▉| 14110/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -129496,8 +129351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14112/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  95%|▉| 14112/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14111/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  95%|▉| 14111/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -129505,8 +129360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14113/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14113/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  95%|▉| 14112/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14112/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129514,8 +129369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14114/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  95%|▉| 14114/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14113/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14113/14932 [19:56<01:09, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -129523,8 +129378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14115/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14115/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14114/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14114/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -129532,8 +129387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14116/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14116/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14115/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14115/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -129541,8 +129396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14117/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14117/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  95%|▉| 14116/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14116/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -129550,8 +129405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14118/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  95%|▉| 14118/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14117/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  95%|▉| 14117/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -129559,8 +129414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14119/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14119/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14118/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14118/14932 [19:57<01:09, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -129568,8 +129423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14120/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14120/14932 [19:59<01:09, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14119/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14119/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -129577,8 +129432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14121/14932 [19:59<01:08, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14121/14932 [19:59<01:08, 11.77it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  95%|▉| 14120/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  95%|▉| 14120/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -129586,8 +129441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14122/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  95%|▉| 14122/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  95%|▉| 14121/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  95%|▉| 14121/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129595,8 +129450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14123/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  95%|▉| 14123/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14122/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14122/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -129604,8 +129459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14124/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14124/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  95%|▉| 14123/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  95%|▉| 14123/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -129613,8 +129468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14125/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14125/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  95%|▉| 14124/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  95%|▉| 14124/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -129622,8 +129477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14126/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  95%|▉| 14126/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14125/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  95%|▉| 14125/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -129631,8 +129486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14127/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14127/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14126/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  95%|▉| 14126/14932 [19:57<01:08, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -129640,8 +129495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14128/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14128/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14127/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  95%|▉| 14127/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129649,8 +129504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14129/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14129/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  95%|▉| 14128/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14128/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -129658,8 +129513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14130/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  95%|▉| 14130/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14129/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14129/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -129667,8 +129522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14131/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14131/14932 [20:00<01:08, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14130/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14130/14932 [19:58<01:08, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -129676,8 +129531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14132/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14132/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  95%|▉| 14131/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  95%|▉| 14131/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129685,8 +129540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14133/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  95%|▉| 14133/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  95%|▉| 14132/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  95%|▉| 14132/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129694,8 +129549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14134/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  95%|▉| 14134/14932 [20:00<01:07, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  95%|▉| 14133/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14133/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -129703,8 +129558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14135/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  95%|▉| 14135/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  95%|▉| 14134/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  95%|▉| 14134/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -129712,8 +129567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14136/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  95%|▉| 14136/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  95%|▉| 14135/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14135/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129721,8 +129576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14137/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  95%|▉| 14137/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14136/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14136/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -129730,8 +129585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14138/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  95%|▉| 14138/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14137/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  95%|▉| 14137/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129739,8 +129594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14139/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14139/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14138/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14138/14932 [19:58<01:07, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129748,8 +129603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14140/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14140/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  95%|▉| 14139/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14139/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -129757,8 +129612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14141/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  95%|▉| 14141/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  95%|▉| 14140/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  95%|▉| 14140/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -129766,8 +129621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14142/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  95%|▉| 14142/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14141/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  95%|▉| 14141/14932 [19:59<01:07, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -129775,8 +129630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14143/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14143/14932 [20:01<01:07, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14142/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  95%|▉| 14142/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -129784,8 +129639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14144/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14144/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14143/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14143/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129793,8 +129648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14145/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14145/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14144/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  95%|▉| 14144/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -129802,8 +129657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14146/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14146/14932 [20:01<01:06, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  95%|▉| 14145/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14145/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -129811,8 +129666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14147/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  95%|▉| 14147/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14146/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  95%|▉| 14146/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -129820,8 +129675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14148/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14148/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  95%|▉| 14147/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14147/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -129829,8 +129684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14149/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  95%|▉| 14149/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14148/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14148/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -129838,7 +129693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14150/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14149/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  95%|▉| 14149/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -129846,7 +129702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14150/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  95%|▉| 14150/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14150/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -129854,8 +129711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14151/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  95%|▉| 14151/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14151/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  95%|▉| 14151/14932 [19:59<01:06, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -129863,8 +129720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14152/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  95%|▉| 14152/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14152/14932 [20:00<01:06, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  95%|▉| 14152/14932 [20:00<01:06, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129872,8 +129729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14153/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14153/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14153/14932 [20:00<01:06, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  95%|▉| 14153/14932 [20:00<01:06, 11.79it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -129881,7 +129738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14154/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14154/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  95%|▉| 14154/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -129889,7 +129747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14154/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  95%|▉| 14155/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  95%|▉| 14155/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -129897,8 +129756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14155/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  95%|▉| 14155/14932 [20:02<01:06, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  95%|▉| 14156/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  95%|▉| 14156/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -129906,8 +129765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14156/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  95%|▉| 14156/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14157/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  95%|▉| 14157/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -129915,8 +129774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14157/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14157/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14158/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14158/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -129924,8 +129783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14158/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14158/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14159/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14159/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -129933,8 +129792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14159/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14159/14932 [20:02<01:05, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14160/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  95%|▉| 14160/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -129942,8 +129801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14160/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14160/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  95%|▉| 14161/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14161/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -129951,8 +129810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14161/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  95%|▉| 14161/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14162/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14162/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -129960,8 +129819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14162/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14162/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14163/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  95%|▉| 14163/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -129969,8 +129828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14163/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14163/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14164/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  95%|▉| 14164/14932 [20:00<01:05, 11.79it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -129978,8 +129837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14164/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14164/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14165/14932 [20:01<01:05, 11.79it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  95%|▉| 14165/14932 [20:01<01:05, 11.79it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -129987,8 +129846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14165/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14165/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14166/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  95%|▉| 14166/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -129996,8 +129855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14166/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14166/14932 [20:03<01:05, 11.77it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  95%|▉| 14167/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14167/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -130005,8 +129864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14167/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  95%|▉| 14167/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  95%|▉| 14168/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14168/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -130014,8 +129873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14168/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  95%|▉| 14168/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  95%|▉| 14169/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  95%|▉| 14169/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -130023,8 +129882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14169/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  95%|▉| 14169/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  95%|▉| 14170/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  95%|▉| 14170/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130032,8 +129891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14170/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  95%|▉| 14170/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14171/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14171/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130041,8 +129900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14171/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14171/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14172/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14172/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -130050,8 +129909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14172/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14172/14932 [20:03<01:04, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14173/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  95%|▉| 14173/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130059,8 +129918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14173/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14173/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14174/14932 [20:01<01:04, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  95%|▉| 14174/14932 [20:01<01:04, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130068,8 +129927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14174/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14174/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  95%|▉| 14175/14932 [20:01<01:04, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14175/14932 [20:01<01:04, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130077,8 +129936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14175/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  95%|▉| 14175/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14176/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14176/14932 [20:01<01:04, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130086,8 +129945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14176/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14176/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  95%|▉| 14177/14932 [20:02<01:04, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14177/14932 [20:02<01:04, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -130095,8 +129954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14177/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  95%|▉| 14177/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14178/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14178/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -130104,8 +129963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14178/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14178/14932 [20:04<01:04, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14179/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14179/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -130113,8 +129972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14179/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14179/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14180/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14180/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -130122,8 +129981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14180/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14180/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14181/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14181/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -130131,8 +129990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14181/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14181/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  95%|▉| 14182/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14182/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130140,8 +129999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14182/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  95%|▉| 14182/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  95%|▉| 14183/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14183/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -130149,8 +130008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14183/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  95%|▉| 14183/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  95%|▉| 14184/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14184/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -130158,8 +130017,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14184/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  95%|▉| 14184/14932 [20:04<01:03, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14185/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  95%|▉| 14185/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -130167,8 +130026,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14185/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14185/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  95%|▉| 14186/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  95%|▉| 14186/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130176,8 +130035,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14186/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  95%|▉| 14186/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14187/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14187/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130185,8 +130044,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14187/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  95%|▉| 14187/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  95%|▉| 14188/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14188/14932 [20:02<01:03, 11.79it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -130194,8 +130053,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14188/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  95%|▉| 14188/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14189/14932 [20:02<01:02, 11.79it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  95%|▉| 14189/14932 [20:02<01:02, 11.79it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130203,8 +130062,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14189/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14189/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14190/14932 [20:03<01:02, 11.79it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14190/14932 [20:03<01:02, 11.79it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130212,8 +130071,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14190/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14190/14932 [20:05<01:03, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14191/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14191/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -130221,8 +130080,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14191/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14191/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  95%|▉| 14192/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14192/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -130230,8 +130089,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14192/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  95%|▉| 14192/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  95%|▉| 14193/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  95%|▉| 14193/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -130239,8 +130098,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14193/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  95%|▉| 14193/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14194/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14194/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130248,8 +130107,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14194/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14194/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14195/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  95%|▉| 14195/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -130257,8 +130116,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14195/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14195/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  95%|▉| 14196/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  95%|▉| 14196/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -130266,8 +130125,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14196/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  95%|▉| 14196/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  95%|▉| 14197/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  95%|▉| 14197/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -130275,8 +130134,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14197/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  95%|▉| 14197/14932 [20:05<01:02, 11.77it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  95%|▉| 14198/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  95%|▉| 14198/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130284,8 +130143,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14198/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  95%|▉| 14198/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  95%|▉| 14199/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  95%|▉| 14199/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130293,8 +130152,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14199/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  95%|▉| 14199/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  95%|▉| 14200/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14200/14932 [20:03<01:02, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -130302,8 +130161,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14200/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14200/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  95%|▉| 14201/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14201/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -130311,8 +130170,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14201/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  95%|▉| 14201/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  95%|▉| 14202/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  95%|▉| 14202/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130320,8 +130179,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14202/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  95%|▉| 14202/14932 [20:06<01:02, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  95%|▉| 14203/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  95%|▉| 14203/14932 [20:03<01:01, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130329,8 +130188,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14203/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14203/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14204/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130338,8 +130196,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14204/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14204/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  95%|▉| 14204/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -130347,8 +130204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14205/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  95%|▉| 14205/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14205/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  95%|▉| 14205/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130356,8 +130213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14206/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14206/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  95%|▉| 14206/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14206/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130365,8 +130222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14207/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  95%|▉| 14207/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  95%|▉| 14207/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14207/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -130374,8 +130231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14208/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  95%|▉| 14208/14932 [20:06<01:01, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14208/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  95%|▉| 14208/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130383,8 +130240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14209/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14209/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14209/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14209/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130392,8 +130249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14210/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14210/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14210/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14210/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -130401,8 +130258,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14211/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14211/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14211/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  95%|▉| 14211/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -130410,8 +130267,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14212/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14212/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  95%|▉| 14212/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  95%|▉| 14212/14932 [20:04<01:01, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -130419,8 +130276,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14213/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  95%|▉| 14213/14932 [20:07<01:01, 11.77it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  95%|▉| 14213/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14213/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -130428,8 +130285,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14214/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  95%|▉| 14214/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14214/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  95%|▉| 14214/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130437,8 +130294,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14215/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14215/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  95%|▉| 14215/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14215/14932 [20:04<01:00, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130446,8 +130303,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14216/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  95%|▉| 14216/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14216/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14216/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130455,8 +130312,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14217/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14217/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  95%|▉| 14217/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14217/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -130464,8 +130321,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14218/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  95%|▉| 14218/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14218/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  95%|▉| 14218/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -130473,8 +130330,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14219/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14219/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  95%|▉| 14219/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14219/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -130482,8 +130339,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14220/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  95%|▉| 14220/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14220/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  95%|▉| 14220/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -130491,8 +130348,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14221/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14221/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14221/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  95%|▉| 14221/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130500,8 +130357,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14222/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14222/14932 [20:07<01:00, 11.77it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14222/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14222/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -130509,8 +130366,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14223/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14223/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  95%|▉| 14223/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14223/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130518,8 +130375,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14224/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  95%|▉| 14224/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  95%|▉| 14224/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14224/14932 [20:05<01:00, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130527,8 +130384,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14225/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  95%|▉| 14225/14932 [20:08<01:00, 11.77it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  95%|▉| 14225/14932 [20:05<00:59, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14225/14932 [20:05<00:59, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130536,8 +130393,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14226/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  95%|▉| 14226/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14226/14932 [20:05<00:59, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14226/14932 [20:05<00:59, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -130545,8 +130402,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14227/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14227/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  95%|▉| 14227/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  95%|▉| 14227/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130554,8 +130411,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14228/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  95%|▉| 14228/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14228/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  95%|▉| 14228/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130563,8 +130420,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14229/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14229/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14229/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14229/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130572,8 +130429,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14230/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14230/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14230/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14230/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -130581,8 +130438,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14231/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14231/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  95%|▉| 14231/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  95%|▉| 14231/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -130590,8 +130447,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14232/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  95%|▉| 14232/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  95%|▉| 14232/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  95%|▉| 14232/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -130599,7 +130456,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14233/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  95%|▉| 14233/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  95%|▉| 14233/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -130607,7 +130465,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14233/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  95%|▉| 14234/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  95%|▉| 14234/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -130615,8 +130474,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14234/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14234/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14235/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  95%|▉| 14235/14932 [20:06<00:59, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130624,8 +130483,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14235/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14235/14932 [20:08<00:59, 11.77it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  95%|▉| 14236/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14236/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -130633,8 +130492,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14236/14932 [20:09<00:59, 11.77it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  95%|▉| 14236/14932 [20:09<00:59, 11.77it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  95%|▉| 14237/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  95%|▉| 14237/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130642,8 +130501,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14237/14932 [20:09<00:59, 11.77it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  95%|▉| 14237/14932 [20:09<00:59, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14238/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14238/14932 [20:06<00:58, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -130651,8 +130510,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14238/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14238/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14239/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  95%|▉| 14239/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -130660,8 +130519,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14239/14932 [20:09<00:58, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14239/14932 [20:09<00:58, 11.78it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  95%|▉| 14240/14932 [20:07<00:58, 11.79it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -130669,8 +130527,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14240/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  95%|▉| 14240/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  95%|▉| 14240/14932 [20:07<00:58, 11.79it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -130678,8 +130535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14241/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  95%|▉| 14241/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14241/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  95%|▉| 14241/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130687,8 +130544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14242/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14242/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  95%|▉| 14242/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14242/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130696,8 +130553,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14243/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  95%|▉| 14243/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  95%|▉| 14243/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -130705,8 +130561,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14244/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  95%|▉| 14244/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  95%|▉| 14243/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -130714,8 +130569,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14245/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  95%|▉| 14245/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14244/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  95%|▉| 14244/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -130723,8 +130578,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14246/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  95%|▉| 14246/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14245/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  95%|▉| 14245/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130732,8 +130587,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14247/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14247/14932 [20:09<00:58, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  95%|▉| 14246/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  95%|▉| 14246/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130741,8 +130596,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14248/14932 [20:10<00:58, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  95%|▉| 14248/14932 [20:10<00:58, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14247/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14247/14932 [20:07<00:58, 11.80it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -130750,8 +130605,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14249/14932 [20:10<00:58, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  95%|▉| 14249/14932 [20:10<00:58, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  95%|▉| 14248/14932 [20:07<00:57, 11.80it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  95%|▉| 14248/14932 [20:07<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130759,8 +130614,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14250/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  95%|▉| 14250/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  95%|▉| 14249/14932 [20:07<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14249/14932 [20:07<00:57, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130768,8 +130623,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14251/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  95%|▉| 14251/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  95%|▉| 14250/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  95%|▉| 14250/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -130777,8 +130632,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14252/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  95%|▉| 14252/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14251/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  95%|▉| 14251/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130786,8 +130641,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14253/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14253/14932 [20:10<00:57, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14252/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14252/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -130795,8 +130650,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14254/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14254/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  95%|▉| 14253/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  95%|▉| 14253/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130804,8 +130659,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14255/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  95%|▉| 14255/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  95%|▉| 14254/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14254/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -130813,8 +130668,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14256/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  95%|▉| 14256/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  95%|▉| 14255/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  95%|▉| 14255/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -130822,8 +130677,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14257/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  95%|▉| 14257/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  95%|▉| 14256/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  95%|▉| 14256/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -130831,8 +130686,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14258/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  95%|▉| 14258/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  95%|▉| 14257/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  95%|▉| 14257/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130840,8 +130695,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14259/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  95%|▉| 14259/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  95%|▉| 14258/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  95%|▉| 14258/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -130849,8 +130704,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  95%|▉| 14260/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  95%|▉| 14260/14932 [20:10<00:57, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  95%|▉| 14259/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  95%|▉| 14259/14932 [20:08<00:57, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -130858,8 +130713,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14261/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14261/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  95%|▉| 14260/14932 [20:08<00:56, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  95%|▉| 14260/14932 [20:08<00:56, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130867,8 +130722,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14262/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  96%|▉| 14262/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  96%|▉| 14261/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14261/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130876,8 +130731,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14263/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  96%|▉| 14263/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  96%|▉| 14262/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14262/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130885,8 +130740,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14264/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  96%|▉| 14264/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  96%|▉| 14263/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  96%|▉| 14263/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130894,8 +130749,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14265/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  96%|▉| 14265/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14264/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14264/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -130903,8 +130758,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14266/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14266/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14265/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14265/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -130912,8 +130767,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14267/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14267/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14266/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14266/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -130921,8 +130776,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14268/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14268/14932 [20:11<00:56, 11.77it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14267/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14267/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -130930,8 +130785,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14269/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14269/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  96%|▉| 14268/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14268/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -130939,8 +130794,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14270/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  96%|▉| 14270/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14269/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  96%|▉| 14269/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -130948,8 +130803,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14271/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14271/14932 [20:11<00:56, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14270/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14270/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -130957,8 +130812,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14272/14932 [20:12<00:56, 11.77it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14272/14932 [20:12<00:56, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14271/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  96%|▉| 14271/14932 [20:09<00:56, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -130966,7 +130821,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14273/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14272/14932 [20:09<00:55, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  96%|▉| 14272/14932 [20:09<00:55, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -130974,7 +130830,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14273/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  96%|▉| 14273/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14273/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -130982,8 +130839,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14274/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  96%|▉| 14274/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=5.0"
+      "Epoch 0:  96%|▉| 14274/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14274/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -130991,8 +130848,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14275/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=5.0\r",
-      "Epoch 0:  96%|▉| 14275/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14275/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14275/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131000,8 +130857,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14276/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14276/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  96%|▉| 14276/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14276/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131009,8 +130866,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14277/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  96%|▉| 14277/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  96%|▉| 14277/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14277/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131018,8 +130875,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14278/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  96%|▉| 14278/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  96%|▉| 14278/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14278/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -131027,8 +130884,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14279/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  96%|▉| 14279/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  96%|▉| 14279/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  96%|▉| 14279/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -131036,8 +130893,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14280/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  96%|▉| 14280/14932 [20:12<00:55, 11.77it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  96%|▉| 14280/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  96%|▉| 14280/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -131045,8 +130902,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14281/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  96%|▉| 14281/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  96%|▉| 14281/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  96%|▉| 14281/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -131054,8 +130911,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14282/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  96%|▉| 14282/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14282/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14282/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131063,8 +130920,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14283/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14283/14932 [20:12<00:55, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14283/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14283/14932 [20:10<00:55, 11.80it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -131072,8 +130929,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14284/14932 [20:13<00:55, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14284/14932 [20:13<00:55, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14284/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  96%|▉| 14284/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -131081,8 +130938,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14285/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14285/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14285/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  96%|▉| 14285/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131090,8 +130947,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14286/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14286/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14286/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14286/14932 [20:10<00:54, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131099,8 +130956,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14287/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14287/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  96%|▉| 14287/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14287/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131108,8 +130965,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14288/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  96%|▉| 14288/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  96%|▉| 14288/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14288/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -131117,8 +130974,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14289/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  96%|▉| 14289/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14289/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  96%|▉| 14289/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -131126,8 +130983,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14290/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14290/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14290/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  96%|▉| 14290/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -131135,8 +130992,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14291/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14291/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14291/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  96%|▉| 14291/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -131144,8 +131001,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14292/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14292/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  96%|▉| 14292/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14292/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -131153,8 +131010,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14293/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  96%|▉| 14293/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  96%|▉| 14293/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  96%|▉| 14293/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131162,8 +131019,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14294/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  96%|▉| 14294/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  96%|▉| 14294/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14294/14932 [20:11<00:54, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -131171,8 +131028,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14295/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  96%|▉| 14295/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14295/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  96%|▉| 14295/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -131180,8 +131037,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14296/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14296/14932 [20:13<00:54, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  96%|▉| 14296/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  96%|▉| 14296/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -131189,8 +131046,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14297/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  96%|▉| 14297/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14297/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  96%|▉| 14297/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131198,8 +131055,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14298/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14298/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14298/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14298/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -131207,8 +131064,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14299/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14299/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14299/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  96%|▉| 14299/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -131216,8 +131073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14300/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14300/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  96%|▉| 14300/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  96%|▉| 14300/14932 [20:11<00:53, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -131225,8 +131082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14301/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  96%|▉| 14301/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  96%|▉| 14301/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  96%|▉| 14301/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -131234,8 +131091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14302/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  96%|▉| 14302/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14302/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  96%|▉| 14302/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131243,8 +131100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14303/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14303/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  96%|▉| 14303/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14303/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131252,8 +131109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14304/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  96%|▉| 14304/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  96%|▉| 14304/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14304/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -131261,8 +131118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14305/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  96%|▉| 14305/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14305/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  96%|▉| 14305/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131270,7 +131127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14306/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14306/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14306/14932 [20:12<00:53, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -131278,7 +131136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14306/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  96%|▉| 14307/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14307/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -131286,8 +131145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14307/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  96%|▉| 14307/14932 [20:14<00:53, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14308/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  96%|▉| 14308/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -131295,8 +131154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14308/14932 [20:14<00:52, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14308/14932 [20:14<00:52, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  96%|▉| 14309/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14309/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131304,8 +131163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14309/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  96%|▉| 14309/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  96%|▉| 14310/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14310/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -131313,8 +131172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14310/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  96%|▉| 14310/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  96%|▉| 14311/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14311/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131322,8 +131181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14311/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  96%|▉| 14311/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14312/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14312/14932 [20:12<00:52, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131331,8 +131190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14312/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14312/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14313/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14313/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -131340,8 +131199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14313/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14313/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14314/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14314/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -131349,8 +131208,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14314/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14314/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  96%|▉| 14315/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -131358,8 +131216,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14315/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  96%|▉| 14315/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14315/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -131367,8 +131224,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14316/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  96%|▉| 14316/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  96%|▉| 14316/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14316/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -131376,8 +131233,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14317/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  96%|▉| 14317/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  96%|▉| 14317/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  96%|▉| 14317/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -131385,8 +131242,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14318/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  96%|▉| 14318/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14318/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  96%|▉| 14318/14932 [20:13<00:52, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -131394,8 +131251,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14319/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14319/14932 [20:15<00:52, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14319/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  96%|▉| 14319/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131403,7 +131260,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14320/14932 [20:15<00:51, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14320/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14320/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -131411,7 +131269,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14320/14932 [20:15<00:51, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14321/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14321/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131419,8 +131278,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14321/14932 [20:15<00:51, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14321/14932 [20:15<00:51, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  96%|▉| 14322/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14322/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -131428,8 +131287,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14322/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  96%|▉| 14322/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14323/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  96%|▉| 14323/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131437,8 +131296,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14323/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14323/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  96%|▉| 14324/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14324/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -131446,7 +131305,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14324/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  96%|▉| 14325/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  96%|▉| 14325/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131454,7 +131314,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14324/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  96%|▉| 14326/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14326/14932 [20:13<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131462,8 +131323,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14325/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  96%|▉| 14325/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14327/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14327/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -131471,8 +131332,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14326/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14326/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14328/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  96%|▉| 14328/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -131480,8 +131341,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14327/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14327/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  96%|▉| 14329/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14329/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131489,8 +131350,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14328/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  96%|▉| 14328/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14330/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14330/14932 [20:14<00:51, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131498,8 +131359,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14329/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14329/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  96%|▉| 14331/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14331/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -131507,8 +131368,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14330/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  96%|▉| 14330/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  96%|▉| 14332/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  96%|▉| 14332/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131516,8 +131377,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14331/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  96%|▉| 14331/14932 [20:16<00:51, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14333/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14333/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -131525,8 +131386,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14332/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14332/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  96%|▉| 14334/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  96%|▉| 14334/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131534,7 +131395,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14333/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  96%|▉| 14335/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14335/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -131542,7 +131404,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14333/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14336/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  96%|▉| 14336/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -131550,8 +131413,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14334/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14334/14932 [20:16<00:50, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14337/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14337/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=0.7"
      ]
     },
     {
@@ -131559,8 +131422,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14335/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14335/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  96%|▉| 14338/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=0.7\r",
+      "Epoch 0:  96%|▉| 14338/14932 [20:14<00:50, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -131568,8 +131431,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14336/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  96%|▉| 14336/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  96%|▉| 14339/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  96%|▉| 14339/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131577,8 +131440,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14337/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  96%|▉| 14337/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  96%|▉| 14340/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14340/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -131586,8 +131449,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14338/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  96%|▉| 14338/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  96%|▉| 14341/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  96%|▉| 14341/14932 [20:15<00:50, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131595,8 +131458,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14339/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  96%|▉| 14339/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  96%|▉| 14342/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14342/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -131604,8 +131467,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14340/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  96%|▉| 14340/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14343/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  96%|▉| 14343/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -131613,8 +131476,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14341/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14341/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  96%|▉| 14344/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14344/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -131622,8 +131485,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14342/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  96%|▉| 14342/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14345/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  96%|▉| 14345/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131631,8 +131494,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14343/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  96%|▉| 14343/14932 [20:17<00:50, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14346/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14346/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131640,8 +131503,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14344/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14344/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  96%|▉| 14347/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14347/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131649,8 +131512,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14345/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  96%|▉| 14345/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14348/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14348/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -131658,8 +131521,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14346/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14346/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  96%|▉| 14349/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14349/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -131667,8 +131530,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14347/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  96%|▉| 14347/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  96%|▉| 14350/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  96%|▉| 14350/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -131676,8 +131539,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14348/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  96%|▉| 14348/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  96%|▉| 14351/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  96%|▉| 14351/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131685,8 +131548,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14349/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  96%|▉| 14349/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14352/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14352/14932 [20:15<00:49, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -131694,8 +131557,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14350/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14350/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14353/14932 [20:16<00:49, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  96%|▉| 14353/14932 [20:16<00:49, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -131703,8 +131566,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14351/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14351/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  96%|▉| 14354/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14354/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -131712,8 +131575,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14352/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  96%|▉| 14352/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  96%|▉| 14355/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  96%|▉| 14355/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131721,8 +131584,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14353/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  96%|▉| 14353/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  96%|▉| 14356/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14356/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -131730,8 +131593,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14354/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  96%|▉| 14354/14932 [20:18<00:49, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14357/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14357/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -131739,8 +131602,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14355/14932 [20:18<00:48, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14355/14932 [20:18<00:48, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  96%|▉| 14358/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  96%|▉| 14358/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131748,8 +131611,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14356/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  96%|▉| 14356/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14359/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14359/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -131757,8 +131620,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14357/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14357/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  96%|▉| 14360/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  96%|▉| 14360/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -131766,8 +131629,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14358/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  96%|▉| 14358/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  96%|▉| 14361/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14361/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -131775,8 +131638,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14359/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  96%|▉| 14359/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14362/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  96%|▉| 14362/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -131784,8 +131647,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14360/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14360/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14363/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14363/14932 [20:16<00:48, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -131793,8 +131656,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14361/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14361/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  96%|▉| 14364/14932 [20:17<00:48, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  96%|▉| 14364/14932 [20:17<00:48, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -131802,8 +131665,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14362/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  96%|▉| 14362/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14365/14932 [20:17<00:48, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  96%|▉| 14365/14932 [20:17<00:48, 11.80it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -131811,8 +131674,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14363/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14363/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  96%|▉| 14366/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  96%|▉| 14366/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -131820,8 +131683,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14364/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  96%|▉| 14364/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  96%|▉| 14367/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14367/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -131829,8 +131692,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14365/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  96%|▉| 14365/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14368/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  96%|▉| 14368/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -131838,8 +131701,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14366/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14366/14932 [20:19<00:48, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  96%|▉| 14369/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14369/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -131847,8 +131710,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14367/14932 [20:19<00:47, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  96%|▉| 14367/14932 [20:19<00:47, 11.78it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  96%|▉| 14370/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -131856,8 +131718,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14368/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  96%|▉| 14368/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  96%|▉| 14370/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -131865,8 +131726,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14369/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  96%|▉| 14369/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14371/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14371/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -131874,8 +131735,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14370/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14370/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14372/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  96%|▉| 14372/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -131883,8 +131744,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14371/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  96%|▉| 14371/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  96%|▉| 14373/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  96%|▉| 14373/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -131892,8 +131753,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14372/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  96%|▉| 14372/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  96%|▉| 14374/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14374/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -131901,8 +131762,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14373/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  96%|▉| 14373/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14375/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  96%|▉| 14375/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -131910,8 +131771,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14374/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14374/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14376/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  96%|▉| 14376/14932 [20:17<00:47, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -131919,8 +131780,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14375/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14375/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  96%|▉| 14377/14932 [20:18<00:47, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  96%|▉| 14377/14932 [20:18<00:47, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131928,8 +131789,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14376/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  96%|▉| 14376/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14378/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14378/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -131937,8 +131798,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14377/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  96%|▉| 14377/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  96%|▉| 14379/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  96%|▉| 14379/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131946,8 +131807,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14378/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  96%|▉| 14378/14932 [20:20<00:47, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  96%|▉| 14380/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14380/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -131955,8 +131816,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14379/14932 [20:20<00:46, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  96%|▉| 14379/14932 [20:20<00:46, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  96%|▉| 14381/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  96%|▉| 14381/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -131964,8 +131825,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14380/14932 [20:20<00:46, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  96%|▉| 14380/14932 [20:20<00:46, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  96%|▉| 14382/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  96%|▉| 14382/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -131973,8 +131834,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14381/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  96%|▉| 14381/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14383/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  96%|▉| 14383/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -131982,8 +131843,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14382/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14382/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  96%|▉| 14384/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14384/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -131991,8 +131852,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14383/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  96%|▉| 14383/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  96%|▉| 14385/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  96%|▉| 14385/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132000,8 +131861,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14384/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  96%|▉| 14384/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  96%|▉| 14386/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  96%|▉| 14386/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -132009,8 +131870,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14385/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  96%|▉| 14385/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  96%|▉| 14387/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  96%|▉| 14387/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -132018,8 +131879,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14386/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  96%|▉| 14386/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  96%|▉| 14388/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  96%|▉| 14388/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132027,8 +131888,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14387/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  96%|▉| 14387/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  96%|▉| 14389/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  96%|▉| 14389/14932 [20:18<00:46, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -132036,8 +131897,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14388/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  96%|▉| 14388/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  96%|▉| 14390/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  96%|▉| 14390/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132045,8 +131906,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14389/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  96%|▉| 14389/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  96%|▉| 14391/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  96%|▉| 14391/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132054,8 +131915,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14390/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  96%|▉| 14390/14932 [20:21<00:46, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  96%|▉| 14392/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14392/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132063,8 +131924,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14391/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  96%|▉| 14391/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14393/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  96%|▉| 14393/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -132072,8 +131933,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14392/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14392/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  96%|▉| 14394/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  96%|▉| 14394/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -132081,8 +131942,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14393/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  96%|▉| 14393/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  96%|▉| 14395/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  96%|▉| 14395/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -132090,8 +131951,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14394/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  96%|▉| 14394/14932 [20:21<00:45, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  96%|▉| 14396/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  96%|▉| 14396/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -132099,8 +131960,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14395/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  96%|▉| 14395/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14397/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  96%|▉| 14397/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -132108,8 +131969,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14396/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14396/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  96%|▉| 14398/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  96%|▉| 14398/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132117,8 +131978,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14397/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  96%|▉| 14397/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  96%|▉| 14399/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  96%|▉| 14399/14932 [20:19<00:45, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132126,8 +131987,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14398/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  96%|▉| 14398/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  96%|▉| 14400/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  96%|▉| 14400/14932 [20:19<00:45, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -132135,8 +131996,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14399/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  96%|▉| 14399/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  96%|▉| 14401/14932 [20:19<00:44, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  96%|▉| 14401/14932 [20:19<00:44, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -132144,8 +132005,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14400/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  96%|▉| 14400/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14402/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  96%|▉| 14402/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -132153,8 +132014,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14401/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14401/14932 [20:22<00:45, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  96%|▉| 14403/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  96%|▉| 14403/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -132162,7 +132023,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14402/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  96%|▉| 14404/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -132170,7 +132031,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14402/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  96%|▉| 14404/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -132178,8 +132039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14403/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  96%|▉| 14403/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  96%|▉| 14405/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  96%|▉| 14405/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132187,8 +132048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14404/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  96%|▉| 14404/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  96%|▉| 14406/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  96%|▉| 14406/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132196,8 +132057,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14405/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  96%|▉| 14405/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  96%|▉| 14407/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132205,8 +132065,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14406/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  96%|▉| 14406/14932 [20:22<00:44, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  96%|▉| 14407/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -132214,8 +132073,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14407/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  96%|▉| 14407/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  96%|▉| 14408/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  96%|▉| 14408/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -132223,8 +132082,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14408/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  96%|▉| 14408/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  96%|▉| 14409/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  96%|▉| 14409/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -132232,8 +132091,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  96%|▉| 14409/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  96%|▉| 14409/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14410/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  97%|▉| 14410/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -132241,8 +132100,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14410/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14410/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14411/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  97%|▉| 14411/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132250,8 +132109,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14411/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14411/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  97%|▉| 14412/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14412/14932 [20:20<00:44, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132259,8 +132118,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14412/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  97%|▉| 14412/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14413/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14413/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132268,8 +132127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14413/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14413/14932 [20:23<00:44, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14414/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  97%|▉| 14414/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -132277,8 +132136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14414/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14414/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  97%|▉| 14415/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14415/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132286,8 +132145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14415/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  97%|▉| 14415/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14416/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14416/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132295,8 +132154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14416/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14416/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14417/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14417/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -132304,8 +132163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14417/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14417/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  97%|▉| 14418/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14418/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -132313,8 +132172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14418/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  97%|▉| 14418/14932 [20:23<00:43, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  97%|▉| 14419/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14419/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -132322,8 +132181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14419/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  97%|▉| 14419/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14420/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  97%|▉| 14420/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -132331,8 +132190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14420/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14420/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14421/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14421/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -132340,8 +132199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14421/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14421/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14422/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  97%|▉| 14422/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -132349,8 +132208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14422/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14422/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14423/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14423/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -132358,8 +132217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14423/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14423/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14424/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  97%|▉| 14424/14932 [20:21<00:43, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -132367,8 +132226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14424/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14424/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=0.6"
+      "Epoch 0:  97%|▉| 14425/14932 [20:21<00:42, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14425/14932 [20:21<00:42, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -132376,8 +132235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14425/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=0.6\r",
-      "Epoch 0:  97%|▉| 14425/14932 [20:24<00:43, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  97%|▉| 14426/14932 [20:21<00:42, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  97%|▉| 14426/14932 [20:21<00:42, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132385,8 +132244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14426/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  97%|▉| 14426/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14427/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14427/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132394,8 +132253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14427/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14427/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  97%|▉| 14428/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14428/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -132403,8 +132262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14428/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  97%|▉| 14428/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  97%|▉| 14429/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  97%|▉| 14429/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -132412,8 +132271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14429/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  97%|▉| 14429/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14430/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  97%|▉| 14430/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132421,8 +132280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14430/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14430/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  97%|▉| 14431/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14431/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -132430,8 +132289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14431/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  97%|▉| 14431/14932 [20:24<00:42, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14432/14932 [20:22<00:42, 11.80it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  97%|▉| 14432/14932 [20:22<00:42, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -132439,8 +132298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14432/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14432/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  97%|▉| 14433/14932 [20:22<00:42, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  97%|▉| 14433/14932 [20:22<00:42, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132448,8 +132307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14433/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  97%|▉| 14433/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14434/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14434/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -132457,8 +132316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14434/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14434/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14435/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  97%|▉| 14435/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -132466,8 +132325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14435/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14435/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14436/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14436/14932 [20:22<00:42, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -132475,8 +132334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14436/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14436/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  97%|▉| 14437/14932 [20:22<00:41, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14437/14932 [20:22<00:41, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -132484,8 +132343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14437/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  97%|▉| 14437/14932 [20:25<00:42, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14438/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  97%|▉| 14438/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -132493,8 +132352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14438/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14438/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14439/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  97%|▉| 14439/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132502,8 +132361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14439/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14439/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  97%|▉| 14440/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14440/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -132511,8 +132370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14440/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  97%|▉| 14440/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14441/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  97%|▉| 14441/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -132520,8 +132379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14441/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14441/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14442/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14442/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -132529,8 +132388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14442/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14442/14932 [20:25<00:41, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14443/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14443/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -132538,8 +132397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14443/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14443/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14444/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  97%|▉| 14444/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132547,8 +132406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14444/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14444/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14445/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14445/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -132556,8 +132415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14445/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14445/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  97%|▉| 14446/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14446/14932 [20:23<00:41, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -132565,8 +132424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14446/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  97%|▉| 14446/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14447/14932 [20:23<00:41, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  97%|▉| 14447/14932 [20:23<00:41, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -132574,8 +132433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14447/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14447/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14448/14932 [20:23<00:40, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  97%|▉| 14448/14932 [20:23<00:40, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -132583,8 +132442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14448/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14448/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  97%|▉| 14449/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  97%|▉| 14449/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -132592,8 +132451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14449/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  97%|▉| 14449/14932 [20:26<00:41, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14450/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14450/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132601,8 +132460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14450/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14450/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14451/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  97%|▉| 14451/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -132610,8 +132469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14451/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14451/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14452/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  97%|▉| 14452/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132619,8 +132478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14452/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14452/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14453/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14453/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -132628,8 +132487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14453/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14453/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14454/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14454/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -132637,8 +132496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14454/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14454/14932 [20:26<00:40, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14455/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  97%|▉| 14455/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -132646,8 +132505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14455/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14455/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  97%|▉| 14456/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  97%|▉| 14456/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132655,8 +132514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14456/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14456/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14457/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  97%|▉| 14457/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132664,8 +132523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14457/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14457/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14458/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14458/14932 [20:24<00:40, 11.80it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -132673,8 +132532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14458/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14458/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14459/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  97%|▉| 14459/14932 [20:24<00:40, 11.81it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -132682,8 +132541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14459/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14459/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14460/14932 [20:24<00:39, 11.81it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  97%|▉| 14460/14932 [20:24<00:39, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132691,8 +132550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14460/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14460/14932 [20:27<00:40, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14461/14932 [20:24<00:39, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14461/14932 [20:24<00:39, 11.81it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -132700,8 +132559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14461/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14461/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  97%|▉| 14462/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  97%|▉| 14462/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -132709,8 +132568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14462/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  97%|▉| 14462/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14463/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  97%|▉| 14463/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -132718,8 +132577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14463/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14463/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14464/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  97%|▉| 14464/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132727,8 +132586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14464/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14464/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14465/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14465/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132736,8 +132595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14465/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14465/14932 [20:27<00:39, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  97%|▉| 14466/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14466/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132745,8 +132604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14466/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  97%|▉| 14466/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14467/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  97%|▉| 14467/14932 [20:25<00:39, 11.80it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -132754,8 +132613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14467/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14467/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  97%|▉| 14468/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  97%|▉| 14468/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132763,8 +132622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14468/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  97%|▉| 14468/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14469/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14469/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132772,8 +132631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14469/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  97%|▉| 14469/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  97%|▉| 14470/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  97%|▉| 14470/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -132781,8 +132640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14470/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14470/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14471/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  97%|▉| 14471/14932 [20:25<00:39, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -132790,8 +132649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14471/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14471/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14472/14932 [20:25<00:38, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  97%|▉| 14472/14932 [20:25<00:38, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -132799,8 +132658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14472/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14472/14932 [20:28<00:39, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14473/14932 [20:25<00:38, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  97%|▉| 14473/14932 [20:25<00:38, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -132808,8 +132667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14473/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14473/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  97%|▉| 14474/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14474/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -132817,8 +132676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14474/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  97%|▉| 14474/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14475/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  97%|▉| 14475/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -132826,8 +132685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14475/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14475/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14476/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  97%|▉| 14476/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -132835,8 +132694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14476/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14476/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  97%|▉| 14477/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  97%|▉| 14477/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -132844,8 +132703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14477/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  97%|▉| 14477/14932 [20:28<00:38, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  97%|▉| 14478/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14478/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132853,8 +132712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14478/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  97%|▉| 14478/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  97%|▉| 14479/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  97%|▉| 14479/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -132862,8 +132721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14479/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14479/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14480/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14480/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -132871,8 +132730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14480/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  97%|▉| 14480/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  97%|▉| 14481/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14481/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -132880,8 +132739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14481/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  97%|▉| 14481/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14482/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  97%|▉| 14482/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -132889,8 +132748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14482/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14482/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  97%|▉| 14483/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14483/14932 [20:26<00:38, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -132898,8 +132757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14483/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  97%|▉| 14483/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14484/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14484/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -132907,8 +132766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14484/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14484/14932 [20:29<00:38, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14485/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14485/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -132916,7 +132775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14485/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14486/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14486/14932 [20:26<00:37, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -132924,7 +132784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14485/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14487/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  97%|▉| 14487/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -132932,8 +132793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14486/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14486/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  97%|▉| 14488/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  97%|▉| 14488/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -132941,8 +132802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14487/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  97%|▉| 14487/14932 [20:29<00:37, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14489/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14489/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -132950,8 +132811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14488/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14488/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  97%|▉| 14490/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  97%|▉| 14490/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -132959,8 +132820,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14489/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  97%|▉| 14489/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  97%|▉| 14491/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14491/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -132968,8 +132829,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14490/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  97%|▉| 14490/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14492/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14492/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -132977,8 +132838,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14491/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  97%|▉| 14491/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14493/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14493/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -132986,8 +132847,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14492/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14492/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  97%|▉| 14494/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  97%|▉| 14494/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -132995,8 +132856,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14493/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  97%|▉| 14493/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14495/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14495/14932 [20:27<00:37, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133004,8 +132865,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14494/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14494/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14496/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14496/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133013,8 +132874,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14495/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14495/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14497/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14497/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -133022,8 +132883,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14496/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14496/14932 [20:30<00:37, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  97%|▉| 14498/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  97%|▉| 14498/14932 [20:27<00:36, 11.81it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -133031,8 +132892,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14497/14932 [20:30<00:36, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  97%|▉| 14497/14932 [20:30<00:36, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14499/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  97%|▉| 14499/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133040,8 +132901,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14498/14932 [20:30<00:36, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14498/14932 [20:30<00:36, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14500/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  97%|▉| 14500/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133049,8 +132910,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14499/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14499/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14501/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14501/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -133058,8 +132919,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14500/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  97%|▉| 14500/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14502/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14502/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -133067,8 +132928,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14501/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14501/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14503/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  97%|▉| 14503/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -133076,8 +132937,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14502/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14502/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  97%|▉| 14504/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  97%|▉| 14504/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -133085,8 +132946,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14503/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  97%|▉| 14503/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14505/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  97%|▉| 14505/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -133094,8 +132955,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14504/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14504/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14506/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  97%|▉| 14506/14932 [20:28<00:36, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -133103,8 +132964,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14505/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14505/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  97%|▉| 14507/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  97%|▉| 14507/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -133112,8 +132973,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14506/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  97%|▉| 14506/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14508/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  97%|▉| 14508/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133121,8 +132982,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14507/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14507/14932 [20:31<00:36, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  97%|▉| 14509/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  97%|▉| 14509/14932 [20:28<00:35, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -133130,8 +132991,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14508/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  97%|▉| 14508/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14510/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  97%|▉| 14510/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133139,7 +133000,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14509/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  97%|▉| 14511/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14511/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133147,7 +133009,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14509/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14512/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14512/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133155,8 +133018,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14510/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14510/14932 [20:31<00:35, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14513/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14513/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -133164,8 +133027,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14511/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14511/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14514/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  97%|▉| 14514/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133173,8 +133036,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14512/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14512/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14515/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14515/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133182,8 +133045,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14513/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14513/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  97%|▉| 14516/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14516/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -133191,8 +133054,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14514/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  97%|▉| 14514/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14517/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  97%|▉| 14517/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133200,8 +133063,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14515/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14515/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14518/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14518/14932 [20:29<00:35, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -133209,8 +133072,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14516/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14516/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14519/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14519/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133218,8 +133081,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14517/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14517/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14520/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14520/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133227,8 +133090,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14518/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14518/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  97%|▉| 14521/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  97%|▉| 14521/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133236,8 +133099,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14519/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  97%|▉| 14519/14932 [20:32<00:35, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  97%|▉| 14522/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14522/14932 [20:29<00:34, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133245,8 +133108,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14520/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  97%|▉| 14520/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  97%|▉| 14523/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14523/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -133254,8 +133117,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14521/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  97%|▉| 14521/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  97%|▉| 14524/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  97%|▉| 14524/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -133263,8 +133126,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14522/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  97%|▉| 14522/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14525/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14525/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133272,8 +133135,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14523/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14523/14932 [20:32<00:34, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14526/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  97%|▉| 14526/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133281,8 +133144,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14524/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14524/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14527/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14527/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -133290,8 +133153,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14525/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14525/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14528/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  97%|▉| 14528/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -133299,8 +133162,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14526/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14526/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14529/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  97%|▉| 14529/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -133308,8 +133171,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14527/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14527/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  97%|▉| 14530/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  97%|▉| 14530/14932 [20:30<00:34, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133317,8 +133180,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14528/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  97%|▉| 14528/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14531/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14531/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133326,8 +133189,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14529/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14529/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  97%|▉| 14532/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14532/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133335,8 +133198,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14530/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  97%|▉| 14530/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14533/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  97%|▉| 14533/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -133344,8 +133207,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14531/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14531/14932 [20:33<00:34, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  97%|▉| 14534/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  97%|▉| 14534/14932 [20:30<00:33, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133353,8 +133216,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14532/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14532/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14535/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  97%|▉| 14535/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -133362,8 +133225,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14533/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14533/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  97%|▉| 14536/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  97%|▉| 14536/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -133371,8 +133234,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14534/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  97%|▉| 14534/14932 [20:33<00:33, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14537/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  97%|▉| 14537/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133380,8 +133243,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14535/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14535/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0:  97%|▉| 14538/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14538/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -133389,8 +133252,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14536/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0:  97%|▉| 14536/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  97%|▉| 14539/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  97%|▉| 14539/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133398,8 +133261,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14537/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  97%|▉| 14537/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  97%|▉| 14540/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  97%|▉| 14540/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133407,8 +133270,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14538/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  97%|▉| 14538/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14541/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14541/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -133416,8 +133279,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14539/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14539/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  97%|▉| 14542/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  97%|▉| 14542/14932 [20:31<00:33, 11.81it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -133425,8 +133288,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14540/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  97%|▉| 14540/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14543/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  97%|▉| 14543/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -133434,8 +133297,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14541/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14541/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  97%|▉| 14544/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  97%|▉| 14544/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -133443,8 +133306,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14542/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  97%|▉| 14542/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  97%|▉| 14545/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  97%|▉| 14545/14932 [20:31<00:32, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133452,8 +133315,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14543/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  97%|▉| 14543/14932 [20:34<00:33, 11.78it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  97%|▉| 14546/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14546/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -133461,8 +133324,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14544/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  97%|▉| 14544/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  97%|▉| 14547/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  97%|▉| 14547/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -133470,8 +133333,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14545/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  97%|▉| 14545/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  97%|▉| 14548/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14548/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -133479,8 +133342,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14546/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  97%|▉| 14546/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  97%|▉| 14549/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  97%|▉| 14549/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133488,8 +133351,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14547/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  97%|▉| 14547/14932 [20:34<00:32, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14550/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  97%|▉| 14550/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -133497,8 +133360,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14548/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14548/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  97%|▉| 14551/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  97%|▉| 14551/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133506,8 +133369,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14549/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  97%|▉| 14549/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0:  97%|▉| 14552/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14552/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133515,8 +133378,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14550/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0:  97%|▉| 14550/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  97%|▉| 14553/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  97%|▉| 14553/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -133524,8 +133387,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14551/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  97%|▉| 14551/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  97%|▉| 14554/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  97%|▉| 14554/14932 [20:32<00:32, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133533,8 +133396,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14552/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14552/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  97%|▉| 14555/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  97%|▉| 14555/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -133542,8 +133405,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14553/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  97%|▉| 14553/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  97%|▉| 14556/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  97%|▉| 14556/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -133551,8 +133414,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14554/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  97%|▉| 14554/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  97%|▉| 14557/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  97%|▉| 14557/14932 [20:32<00:31, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133560,8 +133423,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14555/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  97%|▉| 14555/14932 [20:35<00:32, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  97%|▉| 14558/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  97%|▉| 14558/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -133569,8 +133432,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14556/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  97%|▉| 14556/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14559/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14559/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133578,8 +133441,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14557/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  97%|▉| 14557/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  98%|▉| 14560/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14560/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133587,8 +133450,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  97%|▉| 14558/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  97%|▉| 14558/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14561/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14561/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -133596,8 +133459,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14559/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14559/14932 [20:35<00:31, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14562/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  98%|▉| 14562/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133605,8 +133468,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14560/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14560/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14563/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14563/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -133614,8 +133477,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14561/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14561/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14564/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14564/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133623,8 +133486,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14562/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14562/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14565/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14565/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133632,8 +133495,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14563/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14563/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  98%|▉| 14566/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14566/14932 [20:33<00:31, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133641,8 +133504,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14564/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  98%|▉| 14564/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14567/14932 [20:33<00:30, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14567/14932 [20:33<00:30, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -133650,8 +133513,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14565/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  98%|▉| 14565/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  98%|▉| 14568/14932 [20:33<00:30, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  98%|▉| 14568/14932 [20:33<00:30, 11.81it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -133659,8 +133522,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14566/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  98%|▉| 14566/14932 [20:36<00:31, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14569/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  98%|▉| 14569/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -133668,8 +133531,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14567/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14567/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14570/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14570/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -133677,8 +133540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14568/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14568/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=4.7"
+      "Epoch 0:  98%|▉| 14571/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  98%|▉| 14571/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -133686,8 +133549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14569/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=4.7\r",
-      "Epoch 0:  98%|▉| 14569/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14572/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  98%|▉| 14572/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -133695,8 +133558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14570/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14570/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  98%|▉| 14573/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  98%|▉| 14573/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -133704,8 +133567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14571/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  98%|▉| 14571/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14574/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  98%|▉| 14574/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133713,8 +133576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14572/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14572/14932 [20:36<00:30, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  98%|▉| 14575/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  98%|▉| 14575/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -133722,8 +133585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14573/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  98%|▉| 14573/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14576/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  98%|▉| 14576/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -133731,8 +133594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14574/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14574/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  98%|▉| 14577/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  98%|▉| 14577/14932 [20:34<00:30, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133740,8 +133603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14575/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  98%|▉| 14575/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14578/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  98%|▉| 14578/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -133749,8 +133612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14576/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14576/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  98%|▉| 14579/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  98%|▉| 14579/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -133758,8 +133621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14577/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  98%|▉| 14577/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14580/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14580/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -133767,8 +133630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14578/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14578/14932 [20:37<00:30, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  98%|▉| 14581/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14581/14932 [20:34<00:29, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -133776,8 +133639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14579/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  98%|▉| 14579/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  98%|▉| 14582/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  98%|▉| 14582/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -133785,8 +133648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14580/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  98%|▉| 14580/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  98%|▉| 14583/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  98%|▉| 14583/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133794,8 +133657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14581/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  98%|▉| 14581/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14584/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14584/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -133803,8 +133666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14582/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14582/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14585/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  98%|▉| 14585/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133812,8 +133675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14583/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14583/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  98%|▉| 14586/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14586/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133821,8 +133684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14584/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  98%|▉| 14584/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  98%|▉| 14587/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  98%|▉| 14587/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -133830,8 +133693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14585/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  98%|▉| 14585/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14588/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14588/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=5.0"
      ]
     },
     {
@@ -133839,8 +133702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14586/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14586/14932 [20:37<00:29, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14589/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=5.0\r",
+      "Epoch 0:  98%|▉| 14589/14932 [20:35<00:29, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -133848,8 +133711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14587/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14587/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  98%|▉| 14590/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  98%|▉| 14590/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -133857,8 +133720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14588/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  98%|▉| 14588/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  98%|▉| 14591/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  98%|▉| 14591/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -133866,8 +133729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14589/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  98%|▉| 14589/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  98%|▉| 14592/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  98%|▉| 14592/14932 [20:35<00:28, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -133875,7 +133738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14590/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  98%|▉| 14593/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  98%|▉| 14593/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -133883,7 +133747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14590/14932 [20:38<00:29, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  98%|▉| 14594/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  98%|▉| 14594/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -133891,8 +133756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14591/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  98%|▉| 14591/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  98%|▉| 14595/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  98%|▉| 14595/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -133900,8 +133765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14592/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  98%|▉| 14592/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14596/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  98%|▉| 14596/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -133909,8 +133774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14593/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14593/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  98%|▉| 14597/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  98%|▉| 14597/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133918,8 +133783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14594/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  98%|▉| 14594/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  98%|▉| 14598/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14598/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -133927,8 +133792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14595/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  98%|▉| 14595/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  98%|▉| 14599/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14599/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -133936,8 +133801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14596/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  98%|▉| 14596/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14600/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14600/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -133945,7 +133810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14597/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14601/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  98%|▉| 14601/14932 [20:36<00:28, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133953,7 +133819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14597/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  98%|▉| 14602/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14602/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133961,8 +133828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14598/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  98%|▉| 14598/14932 [20:38<00:28, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  98%|▉| 14603/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14603/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -133970,8 +133837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14599/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  98%|▉| 14599/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14604/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14604/14932 [20:36<00:27, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -133979,8 +133846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14600/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14600/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14605/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14605/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -133988,8 +133855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14601/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14601/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  98%|▉| 14606/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  98%|▉| 14606/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -133997,8 +133864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14602/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  98%|▉| 14602/14932 [20:39<00:28, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  98%|▉| 14607/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14607/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134006,8 +133873,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14603/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  98%|▉| 14603/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  98%|▉| 14608/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134015,8 +133881,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14604/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  98%|▉| 14604/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14608/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134024,8 +133889,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14605/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14605/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14609/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14609/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134033,8 +133898,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14606/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14606/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14610/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14610/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134042,8 +133907,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14607/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14607/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  98%|▉| 14611/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14611/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -134051,8 +133916,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14608/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  98%|▉| 14608/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  98%|▉| 14612/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  98%|▉| 14612/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134060,8 +133925,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14609/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  98%|▉| 14609/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  98%|▉| 14613/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14613/14932 [20:37<00:27, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -134069,8 +133934,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14610/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14610/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14614/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  98%|▉| 14614/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -134078,8 +133943,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14611/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14611/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  98%|▉| 14615/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14615/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134087,8 +133952,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14612/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  98%|▉| 14612/14932 [20:39<00:27, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  98%|▉| 14616/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134096,8 +133960,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14613/14932 [20:40<00:27, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  98%|▉| 14613/14932 [20:40<00:27, 11.78it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  98%|▉| 14616/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134105,8 +133968,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14614/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  98%|▉| 14614/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14617/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14617/14932 [20:37<00:26, 11.81it/s, v_num=ui8w, train/loss=1.1"
      ]
     },
     {
@@ -134114,8 +133977,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14615/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14615/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  98%|▉| 14618/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=1.1\r",
+      "Epoch 0:  98%|▉| 14618/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -134123,8 +133986,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14616/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14616/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14619/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  98%|▉| 14619/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134132,8 +133995,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14617/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14617/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14620/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14620/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -134141,8 +134004,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14618/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14618/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14621/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  98%|▉| 14621/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -134150,8 +134013,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14619/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14619/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  98%|▉| 14622/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -134159,8 +134021,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14620/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  98%|▉| 14620/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14622/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134168,8 +134029,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14621/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14621/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14623/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14623/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134177,8 +134038,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14622/14932 [20:40<00:26, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14622/14932 [20:40<00:26, 11.79it/s, v_num=o30c, train/loss=1.4"
+      "Epoch 0:  98%|▉| 14624/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14624/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -134186,8 +134047,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14623/14932 [20:40<00:26, 11.79it/s, v_num=o30c, train/loss=1.4\r",
-      "Epoch 0:  98%|▉| 14623/14932 [20:40<00:26, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  98%|▉| 14625/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  98%|▉| 14625/14932 [20:38<00:26, 11.81it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -134195,8 +134056,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14624/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  98%|▉| 14624/14932 [20:40<00:26, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14626/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  98%|▉| 14626/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134204,8 +134065,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14625/14932 [20:41<00:26, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14625/14932 [20:41<00:26, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  98%|▉| 14627/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14627/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134213,8 +134074,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14626/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  98%|▉| 14626/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  98%|▉| 14628/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14628/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134222,8 +134083,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14627/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  98%|▉| 14627/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14629/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14629/14932 [20:38<00:25, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134231,8 +134092,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14628/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14628/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14630/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14630/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134240,8 +134101,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14629/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14629/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14631/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14631/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134249,8 +134110,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14630/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14630/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14632/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14632/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -134258,8 +134119,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14631/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14631/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  98%|▉| 14633/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14633/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -134267,8 +134128,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14632/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  98%|▉| 14632/14932 [20:41<00:25, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14634/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14634/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134276,8 +134137,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14633/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  98%|▉| 14633/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14635/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14635/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -134285,8 +134146,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14634/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14634/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14636/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  98%|▉| 14636/14932 [20:39<00:25, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -134294,8 +134155,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14635/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14635/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  98%|▉| 14637/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14637/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134303,8 +134164,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14636/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  98%|▉| 14636/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14638/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  98%|▉| 14638/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134312,8 +134173,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14637/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14637/14932 [20:41<00:25, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14639/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14639/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134321,8 +134182,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14638/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14638/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14640/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14640/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -134330,8 +134191,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14639/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14639/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14641/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14641/14932 [20:39<00:24, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -134339,8 +134200,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14640/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  98%|▉| 14640/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14642/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  98%|▉| 14642/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134348,8 +134209,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14641/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14641/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14643/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14643/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -134357,8 +134218,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14642/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14642/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  98%|▉| 14644/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  98%|▉| 14644/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -134366,8 +134227,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14643/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  98%|▉| 14643/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  98%|▉| 14645/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  98%|▉| 14645/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -134375,8 +134236,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14644/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  98%|▉| 14644/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14646/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  98%|▉| 14646/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134384,8 +134245,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14645/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14645/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  98%|▉| 14647/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14647/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -134393,8 +134254,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14646/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  98%|▉| 14646/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  98%|▉| 14648/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  98%|▉| 14648/14932 [20:40<00:24, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -134402,8 +134263,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14647/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  98%|▉| 14647/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14649/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  98%|▉| 14649/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134411,7 +134272,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14648/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14650/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14650/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -134419,7 +134281,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14648/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  98%|▉| 14651/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  98%|▉| 14651/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -134427,8 +134290,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14649/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  98%|▉| 14649/14932 [20:42<00:24, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14652/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  98%|▉| 14652/14932 [20:40<00:23, 11.81it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -134436,8 +134299,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14650/14932 [20:42<00:23, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14650/14932 [20:42<00:23, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  98%|▉| 14653/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  98%|▉| 14653/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -134445,8 +134308,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14651/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14651/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  98%|▉| 14654/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  98%|▉| 14654/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -134454,8 +134317,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14652/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14652/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  98%|▉| 14655/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  98%|▉| 14655/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -134463,8 +134326,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14653/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  98%|▉| 14653/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  98%|▉| 14656/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  98%|▉| 14656/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134472,8 +134335,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14654/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  98%|▉| 14654/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  98%|▉| 14657/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14657/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -134481,8 +134344,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14655/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  98%|▉| 14655/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14658/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14658/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -134490,8 +134353,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14656/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14656/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  98%|▉| 14659/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  98%|▉| 14659/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -134499,8 +134362,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14657/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  98%|▉| 14657/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14660/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  98%|▉| 14660/14932 [20:41<00:23, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -134508,7 +134371,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14658/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14661/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  98%|▉| 14661/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -134516,7 +134380,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14658/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14662/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  98%|▉| 14662/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134524,8 +134389,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14659/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14659/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  98%|▉| 14663/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14663/14932 [20:41<00:22, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -134533,8 +134398,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14660/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  98%|▉| 14660/14932 [20:43<00:23, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14664/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  98%|▉| 14664/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -134542,8 +134407,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14661/14932 [20:43<00:22, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14661/14932 [20:43<00:22, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  98%|▉| 14665/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  98%|▉| 14665/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -134551,8 +134416,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14662/14932 [20:43<00:22, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  98%|▉| 14662/14932 [20:43<00:22, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  98%|▉| 14666/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14666/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -134560,8 +134425,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14663/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  98%|▉| 14663/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  98%|▉| 14667/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  98%|▉| 14667/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -134569,8 +134434,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14664/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  98%|▉| 14664/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  98%|▉| 14668/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  98%|▉| 14668/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134578,8 +134443,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14665/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  98%|▉| 14665/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  98%|▉| 14669/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14669/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134587,8 +134452,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14666/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14666/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14670/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14670/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -134596,8 +134461,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14667/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14667/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14671/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  98%|▉| 14671/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=0.8"
      ]
     },
     {
@@ -134605,8 +134470,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14668/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14668/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  98%|▉| 14672/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=0.8\r",
+      "Epoch 0:  98%|▉| 14672/14932 [20:42<00:22, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134614,8 +134479,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14669/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  98%|▉| 14669/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  98%|▉| 14673/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14673/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=1.4"
      ]
     },
     {
@@ -134623,8 +134488,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14670/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  98%|▉| 14670/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14674/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=1.4\r",
+      "Epoch 0:  98%|▉| 14674/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134632,8 +134497,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14671/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14671/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  98%|▉| 14675/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14675/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -134641,8 +134506,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14672/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  98%|▉| 14672/14932 [20:44<00:22, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  98%|▉| 14676/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14676/14932 [20:42<00:21, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -134650,8 +134515,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14673/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  98%|▉| 14673/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  98%|▉| 14677/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0:  98%|▉| 14677/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -134659,8 +134524,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14674/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  98%|▉| 14674/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14678/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -134668,8 +134532,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14675/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14675/14932 [20:44<00:21, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  98%|▉| 14678/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134677,8 +134540,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14676/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  98%|▉| 14676/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14679/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14679/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -134686,8 +134549,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14677/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14677/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  98%|▉| 14680/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14680/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -134695,8 +134558,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14678/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  98%|▉| 14678/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14681/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14681/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134704,8 +134567,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14679/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14679/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14682/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14682/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134713,8 +134576,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14680/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14680/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  98%|▉| 14683/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14683/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -134722,8 +134585,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14681/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  98%|▉| 14681/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14684/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  98%|▉| 14684/14932 [20:43<00:21, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134731,8 +134594,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14682/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14682/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14685/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14685/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -134740,8 +134603,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14683/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14683/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  98%|▉| 14686/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  98%|▉| 14686/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134749,8 +134612,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14684/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  98%|▉| 14684/14932 [20:45<00:21, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14687/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14687/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -134758,8 +134621,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14685/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14685/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  98%|▉| 14688/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  98%|▉| 14688/14932 [20:43<00:20, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -134767,8 +134630,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14686/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14686/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14689/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  98%|▉| 14689/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -134776,8 +134639,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14687/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14687/14932 [20:45<00:20, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  98%|▉| 14690/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14690/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -134785,8 +134648,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14688/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  98%|▉| 14688/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14691/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14691/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -134794,8 +134657,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14689/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14689/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14692/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  98%|▉| 14692/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134803,7 +134666,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14690/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14693/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14693/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -134811,7 +134675,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14690/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  98%|▉| 14694/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  98%|▉| 14694/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -134819,8 +134684,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14691/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  98%|▉| 14691/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  98%|▉| 14695/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  98%|▉| 14695/14932 [20:44<00:20, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -134828,8 +134693,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14692/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  98%|▉| 14692/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14696/14932 [20:44<00:19, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  98%|▉| 14696/14932 [20:44<00:19, 11.80it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -134837,8 +134702,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14693/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14693/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  98%|▉| 14697/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  98%|▉| 14697/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -134846,8 +134711,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14694/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  98%|▉| 14694/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  98%|▉| 14698/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14698/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -134855,8 +134720,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14695/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  98%|▉| 14695/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  98%|▉| 14699/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  98%|▉| 14699/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -134864,8 +134729,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14696/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  98%|▉| 14696/14932 [20:46<00:20, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  98%|▉| 14700/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  98%|▉| 14700/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134873,8 +134738,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14697/14932 [20:46<00:19, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  98%|▉| 14697/14932 [20:46<00:19, 11.79it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  98%|▉| 14701/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  98%|▉| 14701/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -134882,8 +134747,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14698/14932 [20:46<00:19, 11.79it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  98%|▉| 14698/14932 [20:46<00:19, 11.79it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  98%|▉| 14702/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  98%|▉| 14702/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -134891,8 +134756,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14699/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  98%|▉| 14699/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  98%|▉| 14703/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  98%|▉| 14703/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -134900,8 +134765,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14700/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  98%|▉| 14700/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  98%|▉| 14704/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  98%|▉| 14704/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -134909,8 +134774,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14701/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  98%|▉| 14701/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  98%|▉| 14705/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  98%|▉| 14705/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -134918,8 +134783,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14702/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  98%|▉| 14702/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  98%|▉| 14706/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  98%|▉| 14706/14932 [20:45<00:19, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -134927,8 +134792,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14703/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  98%|▉| 14703/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  98%|▉| 14707/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  98%|▉| 14707/14932 [20:45<00:19, 11.80it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -134936,8 +134801,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14704/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  98%|▉| 14704/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  98%|▉| 14708/14932 [20:45<00:18, 11.80it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  98%|▉| 14708/14932 [20:45<00:18, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134945,8 +134810,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14705/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  98%|▉| 14705/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14709/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14709/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -134954,8 +134819,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14706/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  98%|▉| 14706/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14710/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14710/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -134963,8 +134828,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14707/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  98%|▉| 14707/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14711/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14711/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -134972,8 +134837,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  98%|▉| 14708/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  98%|▉| 14708/14932 [20:47<00:19, 11.79it/s, v_num=o30c, train/loss=2.1"
+      "Epoch 0:  99%|▉| 14712/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  99%|▉| 14712/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -134981,8 +134846,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14709/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=2.1\r",
-      "Epoch 0:  99%|▉| 14709/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14713/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14713/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -134990,8 +134855,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14710/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14710/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14714/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  99%|▉| 14714/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -134999,8 +134864,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14711/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14711/14932 [20:47<00:18, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14715/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  99%|▉| 14715/14932 [20:46<00:18, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -135008,8 +134873,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14712/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14712/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14716/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14716/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135017,8 +134882,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14713/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14713/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=0.9"
+      "Epoch 0:  99%|▉| 14717/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14717/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -135026,8 +134891,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14714/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=0.9\r",
-      "Epoch 0:  99%|▉| 14714/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14718/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  99%|▉| 14718/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135035,8 +134900,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14715/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14715/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14719/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14719/14932 [20:46<00:18, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135044,7 +134909,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14716/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14720/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14720/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -135052,7 +134918,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14716/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14721/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  99%|▉| 14721/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -135060,8 +134927,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14717/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14717/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0:  99%|▉| 14722/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  99%|▉| 14722/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -135069,8 +134936,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14718/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0:  99%|▉| 14718/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14723/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  99%|▉| 14723/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135078,8 +134945,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14719/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14719/14932 [20:48<00:18, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14724/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14724/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135087,8 +134954,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14720/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14720/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14725/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14725/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=0.6"
      ]
     },
     {
@@ -135096,8 +134963,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14721/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14721/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14726/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=0.6\r",
+      "Epoch 0:  99%|▉| 14726/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -135105,8 +134972,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14722/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  99%|▉| 14722/14932 [20:48<00:17, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  99%|▉| 14727/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14727/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135114,8 +134981,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14723/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  99%|▉| 14723/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14728/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14728/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135123,8 +134990,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14724/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  99%|▉| 14724/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14729/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14729/14932 [20:47<00:17, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -135132,8 +134999,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14725/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14725/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  99%|▉| 14730/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14730/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -135141,8 +135008,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14726/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  99%|▉| 14726/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14731/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14731/14932 [20:47<00:17, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -135150,8 +135017,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14727/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14727/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14732/14932 [20:47<00:16, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -135159,8 +135025,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14728/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14728/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  99%|▉| 14732/14932 [20:47<00:16, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -135168,8 +135033,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14729/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  99%|▉| 14729/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14733/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14733/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -135177,8 +135042,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14730/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14730/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14734/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  99%|▉| 14734/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135186,8 +135051,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14731/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14731/14932 [20:49<00:17, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  99%|▉| 14735/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14735/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135195,8 +135060,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14732/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  99%|▉| 14732/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  99%|▉| 14736/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14736/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135204,8 +135069,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14733/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  99%|▉| 14733/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  99%|▉| 14737/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14737/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -135213,8 +135078,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14734/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  99%|▉| 14734/14932 [20:49<00:16, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  99%|▉| 14738/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  99%|▉| 14738/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135222,8 +135087,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14735/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  99%|▉| 14735/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  99%|▉| 14739/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14739/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -135231,8 +135096,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14736/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  99%|▉| 14736/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  99%|▉| 14740/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14740/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135240,8 +135105,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14737/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  99%|▉| 14737/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14741/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14741/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -135249,8 +135114,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14738/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14738/14932 [20:50<00:16, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14742/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14742/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135258,8 +135123,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14739/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14739/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14743/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14743/14932 [20:48<00:16, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -135267,8 +135132,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14740/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  99%|▉| 14740/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  99%|▉| 14744/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14744/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135276,8 +135141,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14741/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  99%|▉| 14741/14932 [20:50<00:16, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14745/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14745/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135285,8 +135150,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14742/14932 [20:51<00:16, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  99%|▉| 14742/14932 [20:51<00:16, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  99%|▉| 14746/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14746/14932 [20:48<00:15, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -135294,8 +135159,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14743/14932 [20:51<00:16, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  99%|▉| 14743/14932 [20:51<00:16, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  99%|▉| 14747/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14747/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -135303,8 +135168,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14744/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  99%|▉| 14744/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14748/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  99%|▉| 14748/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -135312,8 +135177,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14745/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14745/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14749/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14749/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.1"
      ]
     },
     {
@@ -135321,8 +135186,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14746/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14746/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  99%|▉| 14750/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.1\r",
+      "Epoch 0:  99%|▉| 14750/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135330,8 +135195,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14747/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  99%|▉| 14747/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=4.4"
+      "Epoch 0:  99%|▉| 14751/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14751/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -135339,8 +135204,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14748/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=4.4\r",
-      "Epoch 0:  99%|▉| 14748/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  99%|▉| 14752/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  99%|▉| 14752/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135348,8 +135213,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14749/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  99%|▉| 14749/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14753/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14753/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -135357,8 +135222,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14750/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  99%|▉| 14750/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14754/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  99%|▉| 14754/14932 [20:49<00:15, 11.81it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -135366,8 +135231,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14751/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  99%|▉| 14751/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14755/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0:  99%|▉| 14755/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -135375,8 +135240,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14752/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14752/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14756/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  99%|▉| 14756/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -135384,8 +135249,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14753/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14753/14932 [20:51<00:15, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14757/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14757/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -135393,8 +135258,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14754/14932 [20:52<00:15, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14754/14932 [20:52<00:15, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14758/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -135402,8 +135266,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14755/14932 [20:52<00:15, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14755/14932 [20:52<00:15, 11.78it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  99%|▉| 14758/14932 [20:49<00:14, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -135411,8 +135274,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14756/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  99%|▉| 14756/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14759/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14759/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135420,8 +135283,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14757/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14757/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14760/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14760/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135429,8 +135292,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14758/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14758/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14761/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14761/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -135438,8 +135301,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14759/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  99%|▉| 14759/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  99%|▉| 14762/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  99%|▉| 14762/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -135447,8 +135310,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14760/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  99%|▉| 14760/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14763/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14763/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -135456,8 +135319,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14761/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14761/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14764/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14764/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -135465,8 +135328,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14762/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14762/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  99%|▉| 14765/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14765/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -135474,8 +135337,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14763/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  99%|▉| 14763/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14766/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  99%|▉| 14766/14932 [20:50<00:14, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135483,8 +135346,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14764/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14764/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  99%|▉| 14767/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14767/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -135492,8 +135355,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14765/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  99%|▉| 14765/14932 [20:52<00:14, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14768/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  99%|▉| 14768/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -135501,8 +135364,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14766/14932 [20:53<00:14, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14766/14932 [20:53<00:14, 11.78it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14769/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  99%|▉| 14769/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135510,8 +135373,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14767/14932 [20:53<00:14, 11.78it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14767/14932 [20:53<00:14, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14770/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14770/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -135519,8 +135382,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14768/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  99%|▉| 14768/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14771/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14771/14932 [20:50<00:13, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135528,8 +135391,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14769/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14769/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=1.6"
+      "Epoch 0:  99%|▉| 14772/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14772/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=1.0"
      ]
     },
     {
@@ -135537,8 +135400,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14770/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=1.6\r",
-      "Epoch 0:  99%|▉| 14770/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14773/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=1.0\r",
+      "Epoch 0:  99%|▉| 14773/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=4.6"
      ]
     },
     {
@@ -135546,8 +135409,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14771/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  99%|▉| 14771/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  99%|▉| 14774/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=4.6\r",
+      "Epoch 0:  99%|▉| 14774/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -135555,8 +135418,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14772/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  99%|▉| 14772/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  99%|▉| 14775/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14775/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135564,8 +135427,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14773/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  99%|▉| 14773/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  99%|▉| 14776/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14776/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135573,8 +135436,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14774/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  99%|▉| 14774/14932 [20:53<00:13, 11.78it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0:  99%|▉| 14777/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14777/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135582,8 +135445,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14775/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0:  99%|▉| 14775/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14778/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14778/14932 [20:51<00:13, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -135591,8 +135454,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14776/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14776/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  99%|▉| 14779/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  99%|▉| 14779/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -135600,8 +135463,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14777/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  99%|▉| 14777/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14780/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0:  99%|▉| 14780/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135609,8 +135472,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14778/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14778/14932 [20:53<00:13, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14781/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14781/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135618,8 +135481,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14779/14932 [20:53<00:12, 11.79it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14779/14932 [20:53<00:12, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  99%|▉| 14782/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14782/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -135627,8 +135490,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14780/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  99%|▉| 14780/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  99%|▉| 14783/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0:  99%|▉| 14783/14932 [20:51<00:12, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -135636,8 +135499,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14781/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  99%|▉| 14781/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14784/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  99%|▉| 14784/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135645,8 +135508,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14782/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14782/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14785/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14785/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -135654,8 +135517,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14783/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14783/14932 [20:54<00:12, 11.79it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  99%|▉| 14786/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14786/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135663,8 +135526,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14784/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  99%|▉| 14784/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14787/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14787/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -135672,8 +135535,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14785/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14785/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14788/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  99%|▉| 14788/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135681,8 +135544,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14786/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14786/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  99%|▉| 14789/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14789/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -135690,8 +135553,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14787/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  99%|▉| 14787/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14790/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  99%|▉| 14790/14932 [20:52<00:12, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135699,8 +135562,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14788/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14788/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  99%|▉| 14791/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14791/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -135708,8 +135571,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14789/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  99%|▉| 14789/14932 [20:54<00:12, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14792/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  99%|▉| 14792/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135717,8 +135580,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14790/14932 [20:55<00:12, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14790/14932 [20:55<00:12, 11.78it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  99%|▉| 14793/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14793/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -135726,8 +135589,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14791/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  99%|▉| 14791/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14794/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14794/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -135735,8 +135598,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14792/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  99%|▉| 14792/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  99%|▉| 14795/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  99%|▉| 14795/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -135744,8 +135607,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14793/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  99%|▉| 14793/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  99%|▉| 14796/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14796/14932 [20:52<00:11, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -135753,8 +135616,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14794/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  99%|▉| 14794/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14797/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  99%|▉| 14797/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135762,8 +135625,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14795/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14795/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0:  99%|▉| 14798/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14798/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -135771,8 +135634,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14796/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0:  99%|▉| 14796/14932 [20:55<00:11, 11.78it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0:  99%|▉| 14799/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0:  99%|▉| 14799/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -135780,8 +135643,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14797/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0:  99%|▉| 14797/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  99%|▉| 14800/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14800/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=1.2"
      ]
     },
     {
@@ -135789,8 +135652,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14798/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  99%|▉| 14798/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14801/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=1.2\r",
+      "Epoch 0:  99%|▉| 14801/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -135798,8 +135661,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14799/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14799/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  99%|▉| 14802/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14802/14932 [20:53<00:11, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -135807,8 +135670,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14800/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  99%|▉| 14800/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  99%|▉| 14803/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0:  99%|▉| 14803/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135816,8 +135679,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14801/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  99%|▉| 14801/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14804/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14804/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -135825,8 +135688,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14802/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14802/14932 [20:55<00:11, 11.79it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0:  99%|▉| 14805/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  99%|▉| 14805/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135834,8 +135697,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14803/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0:  99%|▉| 14803/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14806/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14806/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -135843,8 +135706,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14804/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14804/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0:  99%|▉| 14807/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0:  99%|▉| 14807/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -135852,8 +135715,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14805/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0:  99%|▉| 14805/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14808/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0:  99%|▉| 14808/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135861,8 +135724,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14806/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14806/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  99%|▉| 14809/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14809/14932 [20:53<00:10, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -135870,8 +135733,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14807/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  99%|▉| 14807/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=0.7"
+      "Epoch 0:  99%|▉| 14810/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14810/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -135879,8 +135742,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14808/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=0.7\r",
-      "Epoch 0:  99%|▉| 14808/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  99%|▉| 14811/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  99%|▉| 14811/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -135888,8 +135751,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14809/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  99%|▉| 14809/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0:  99%|▉| 14812/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14812/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -135897,8 +135760,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14810/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0:  99%|▉| 14810/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  99%|▉| 14813/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14813/14932 [20:54<00:10, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -135906,8 +135769,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14811/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  99%|▉| 14811/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  99%|▉| 14814/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0:  99%|▉| 14814/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -135915,8 +135778,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14812/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  99%|▉| 14812/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0:  99%|▉| 14815/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14815/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135924,8 +135787,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14813/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0:  99%|▉| 14813/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14816/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14816/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=4.4"
      ]
     },
     {
@@ -135933,8 +135796,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14814/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14814/14932 [20:56<00:10, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0:  99%|▉| 14817/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=4.4\r",
+      "Epoch 0:  99%|▉| 14817/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -135942,8 +135805,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14815/14932 [20:56<00:09, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0:  99%|▉| 14815/14932 [20:56<00:09, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14818/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0:  99%|▉| 14818/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.9"
      ]
     },
     {
@@ -135951,8 +135814,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14816/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14816/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  99%|▉| 14819/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=3.9\r",
+      "Epoch 0:  99%|▉| 14819/14932 [20:54<00:09, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -135960,8 +135823,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14817/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  99%|▉| 14817/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14820/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  99%|▉| 14820/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -135969,8 +135832,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14818/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14818/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14821/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0:  99%|▉| 14821/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135978,8 +135841,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14819/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14819/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0:  99%|▉| 14822/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14822/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -135987,8 +135850,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14820/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0:  99%|▉| 14820/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14823/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0:  99%|▉| 14823/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -135996,8 +135859,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14821/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14821/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  99%|▉| 14824/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0:  99%|▉| 14824/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -136005,8 +135868,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14822/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  99%|▉| 14822/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0:  99%|▉| 14825/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14825/14932 [20:55<00:09, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -136014,8 +135877,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14823/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0:  99%|▉| 14823/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0:  99%|▉| 14826/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  99%|▉| 14826/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136023,8 +135886,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14824/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0:  99%|▉| 14824/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  99%|▉| 14827/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14827/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136032,8 +135895,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14825/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  99%|▉| 14825/14932 [20:57<00:09, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0:  99%|▉| 14828/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14828/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -136041,8 +135904,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14826/14932 [20:57<00:08, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0:  99%|▉| 14826/14932 [20:57<00:08, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  99%|▉| 14829/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14829/14932 [20:55<00:08, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -136050,8 +135913,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14827/14932 [20:57<00:08, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  99%|▉| 14827/14932 [20:57<00:08, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14830/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0:  99%|▉| 14830/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -136059,8 +135922,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14828/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  99%|▉| 14828/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  99%|▉| 14831/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14831/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -136068,8 +135931,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14829/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  99%|▉| 14829/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14832/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  99%|▉| 14832/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136077,8 +135940,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14830/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  99%|▉| 14830/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0:  99%|▉| 14833/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14833/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136086,8 +135949,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14831/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0:  99%|▉| 14831/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  99%|▉| 14834/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14834/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -136095,8 +135958,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14832/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  99%|▉| 14832/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0:  99%|▉| 14835/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14835/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136104,8 +135967,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14833/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0:  99%|▉| 14833/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0:  99%|▉| 14836/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14836/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -136113,8 +135976,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14834/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0:  99%|▉| 14834/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14837/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0:  99%|▉| 14837/14932 [20:56<00:08, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -136122,8 +135985,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14835/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14835/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14838/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  99%|▉| 14838/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -136131,8 +135994,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14836/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14836/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=0.8"
+      "Epoch 0:  99%|▉| 14839/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  99%|▉| 14839/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136140,8 +136003,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14837/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=0.8\r",
-      "Epoch 0:  99%|▉| 14837/14932 [20:58<00:08, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  99%|▉| 14840/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0:  99%|▉| 14840/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -136149,8 +136012,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14838/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  99%|▉| 14838/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0:  99%|▉| 14841/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0:  99%|▉| 14841/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136158,8 +136021,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14839/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0:  99%|▉| 14839/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14842/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14842/14932 [20:56<00:07, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136167,8 +136030,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14840/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14840/14932 [20:58<00:07, 11.79it/s, v_num=o30c, train/loss=1.1"
+      "Epoch 0:  99%|▉| 14843/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14843/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=4.5"
      ]
     },
     {
@@ -136176,8 +136039,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14841/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=1.1\r",
-      "Epoch 0:  99%|▉| 14841/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14844/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=4.5\r",
+      "Epoch 0:  99%|▉| 14844/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=1.3"
      ]
     },
     {
@@ -136185,8 +136048,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14842/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14842/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0:  99%|▉| 14845/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=1.3\r",
+      "Epoch 0:  99%|▉| 14845/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -136194,8 +136057,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14843/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0:  99%|▉| 14843/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0:  99%|▉| 14846/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0:  99%|▉| 14846/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136203,8 +136066,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14844/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0:  99%|▉| 14844/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0:  99%|▉| 14847/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0:  99%|▉| 14847/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -136212,8 +136075,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14845/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0:  99%|▉| 14845/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0:  99%|▉| 14848/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0:  99%|▉| 14848/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136221,8 +136084,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14846/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0:  99%|▉| 14846/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0:  99%|▉| 14849/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0:  99%|▉| 14849/14932 [20:57<00:07, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136230,8 +136093,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14847/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0:  99%|▉| 14847/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14850/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0:  99%|▉| 14850/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -136239,8 +136102,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14848/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14848/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0:  99%|▉| 14851/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0:  99%|▉| 14851/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -136248,8 +136111,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14849/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  99%|▉| 14849/14932 [20:59<00:07, 11.79it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0:  99%|▉| 14852/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -136257,8 +136119,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14850/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0:  99%|▉| 14850/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=1.0"
+      "Epoch 0:  99%|▉| 14852/14932 [20:57<00:06, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -136266,8 +136127,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14851/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=1.0\r",
-      "Epoch 0:  99%|▉| 14851/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0:  99%|▉| 14853/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0:  99%|▉| 14853/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -136275,8 +136136,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14852/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0:  99%|▉| 14852/14932 [20:59<00:06, 11.79it/s, v_num=o30c, train/loss=3.3"
+      "Epoch 0:  99%|▉| 14854/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0:  99%|▉| 14854/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -136284,8 +136145,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14853/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=3.3\r",
-      "Epoch 0:  99%|▉| 14853/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0:  99%|▉| 14855/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0:  99%|▉| 14855/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -136293,8 +136154,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14854/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0:  99%|▉| 14854/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0:  99%|▉| 14856/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0:  99%|▉| 14856/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.8"
      ]
     },
     {
@@ -136302,8 +136163,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14855/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0:  99%|▉| 14855/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0:  99%|▉| 14857/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.8\r",
+      "Epoch 0:  99%|▉| 14857/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -136311,8 +136172,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14856/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0:  99%|▉| 14856/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0: 100%|▉| 14858/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0: 100%|▉| 14858/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -136320,8 +136181,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0:  99%|▉| 14857/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0:  99%|▉| 14857/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0: 100%|▉| 14859/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0: 100%|▉| 14859/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136329,8 +136190,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14858/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0: 100%|▉| 14858/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0: 100%|▉| 14860/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14860/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -136338,8 +136199,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14859/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0: 100%|▉| 14859/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0: 100%|▉| 14861/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0: 100%|▉| 14861/14932 [20:58<00:06, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -136347,8 +136208,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14860/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|▉| 14860/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0: 100%|▉| 14862/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0: 100%|▉| 14862/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -136356,8 +136217,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14861/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0: 100%|▉| 14861/14932 [21:00<00:06, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|▉| 14863/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0: 100%|▉| 14863/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -136365,8 +136226,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14862/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0: 100%|▉| 14862/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0: 100%|▉| 14864/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0: 100%|▉| 14864/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136374,8 +136235,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14863/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0: 100%|▉| 14863/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0: 100%|▉| 14865/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0: 100%|▉| 14865/14932 [20:58<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136383,8 +136244,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14864/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0: 100%|▉| 14864/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0: 100%|▉| 14866/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14866/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -136392,8 +136253,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14865/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0: 100%|▉| 14865/14932 [21:00<00:05, 11.79it/s, v_num=o30c, train/loss=4.5"
+      "Epoch 0: 100%|���| 14867/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0: 100%|▉| 14867/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136401,8 +136262,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14866/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=4.5\r",
-      "Epoch 0: 100%|▉| 14866/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0: 100%|▉| 14868/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14868/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -136410,8 +136271,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14867/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0: 100%|▉| 14867/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0: 100%|▉| 14869/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0: 100%|▉| 14869/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -136419,8 +136280,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14868/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0: 100%|▉| 14868/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0: 100%|▉| 14870/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0: 100%|▉| 14870/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136428,8 +136289,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14869/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0: 100%|▉| 14869/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0: 100%|▉| 14871/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14871/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136437,8 +136298,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14870/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0: 100%|▉| 14870/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=1.8"
+      "Epoch 0: 100%|▉| 14872/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14872/14932 [20:59<00:05, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136446,8 +136307,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14871/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=1.8\r",
-      "Epoch 0: 100%|▉| 14871/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0: 100%|▉| 14873/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14873/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -136455,8 +136316,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14872/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0: 100%|▉| 14872/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|▉| 14874/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0: 100%|▉| 14874/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -136464,8 +136325,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14873/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0: 100%|▉| 14873/14932 [21:01<00:05, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0: 100%|▉| 14875/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0: 100%|▉| 14875/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -136473,8 +136334,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14874/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|▉| 14874/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0: 100%|▉| 14876/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0: 100%|▉| 14876/14932 [20:59<00:04, 11.81it/s, v_num=ui8w, train/loss=4.2"
      ]
     },
     {
@@ -136482,8 +136343,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14875/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0: 100%|▉| 14875/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0: 100%|▉| 14877/14932 [21:00<00:04, 11.81it/s, v_num=ui8w, train/loss=4.2\r",
+      "Epoch 0: 100%|▉| 14877/14932 [21:00<00:04, 11.81it/s, v_num=ui8w, train/loss=4.0"
      ]
     },
     {
@@ -136491,8 +136352,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14876/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0: 100%|▉| 14876/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0: 100%|▉| 14878/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=4.0\r",
+      "Epoch 0: 100%|▉| 14878/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -136500,8 +136361,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14877/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|▉| 14877/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0: 100%|▉| 14879/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0: 100%|▉| 14879/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136509,8 +136370,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14878/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0: 100%|▉| 14878/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.0"
+      "Epoch 0: 100%|▉| 14880/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0: 100%|▉| 14880/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -136518,8 +136379,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14879/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0: 100%|▉| 14879/14932 [21:01<00:04, 11.79it/s, v_num=o30c, train/loss=3.2"
+      "Epoch 0: 100%|▉| 14881/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0: 100%|▉| 14881/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -136527,8 +136388,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14880/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=3.2\r",
-      "Epoch 0: 100%|▉| 14880/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=1.3"
+      "Epoch 0: 100%|▉| 14882/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0: 100%|▉| 14882/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -136536,8 +136397,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14881/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=1.3\r",
-      "Epoch 0: 100%|▉| 14881/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=2.9"
+      "Epoch 0: 100%|▉| 14883/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0: 100%|▉| 14883/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -136545,8 +136406,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14882/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=2.9\r",
-      "Epoch 0: 100%|▉| 14882/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=2.5"
+      "Epoch 0: 100%|▉| 14884/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0: 100%|▉| 14884/14932 [21:00<00:04, 11.80it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -136554,8 +136415,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14883/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=2.5\r",
-      "Epoch 0: 100%|▉| 14883/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=4.1"
+      "Epoch 0: 100%|▉| 14885/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0: 100%|▉| 14885/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -136563,8 +136424,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14884/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=4.1\r",
-      "Epoch 0: 100%|▉| 14884/14932 [21:02<00:04, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0: 100%|▉| 14886/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0: 100%|▉| 14886/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136572,8 +136433,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14885/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0: 100%|▉| 14885/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|▉| 14887/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0: 100%|▉| 14887/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -136581,8 +136442,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14886/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0: 100%|▉| 14886/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0: 100%|▉| 14888/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0: 100%|▉| 14888/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -136590,8 +136451,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14887/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0: 100%|▉| 14887/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0: 100%|▉| 14889/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0: 100%|▉| 14889/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -136599,8 +136460,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14888/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0: 100%|▉| 14888/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0: 100%|▉| 14890/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0: 100%|▉| 14890/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136608,8 +136469,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14889/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|▉| 14889/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0: 100%|▉| 14891/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14891/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136617,8 +136478,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14890/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0: 100%|▉| 14890/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0: 100%|▉| 14892/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0: 100%|▉| 14892/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -136626,8 +136487,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14891/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0: 100%|▉| 14891/14932 [21:02<00:03, 11.79it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0: 100%|▉| 14893/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0: 100%|▉| 14893/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=1.8"
      ]
     },
     {
@@ -136635,8 +136496,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14892/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0: 100%|▉| 14892/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0: 100%|▉| 14894/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=1.8\r",
+      "Epoch 0: 100%|▉| 14894/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -136644,8 +136505,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14893/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0: 100%|▉| 14893/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.9"
+      "Epoch 0: 100%|▉| 14895/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0: 100%|▉| 14895/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.0"
      ]
     },
     {
@@ -136653,8 +136514,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14894/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.9\r",
-      "Epoch 0: 100%|▉| 14894/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0: 100%|▉| 14896/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=2.0\r",
+      "Epoch 0: 100%|▉| 14896/14932 [21:01<00:03, 11.80it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136662,7 +136523,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14895/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0: 100%|▉| 14897/14932 [21:01<00:02, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14897/14932 [21:01<00:02, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -136670,7 +136532,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14895/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0: 100%|▉| 14898/14932 [21:01<00:02, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0: 100%|▉| 14898/14932 [21:01<00:02, 11.81it/s, v_num=ui8w, train/loss=1.7"
      ]
     },
     {
@@ -136678,8 +136541,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14896/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0: 100%|▉| 14896/14932 [21:03<00:03, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0: 100%|▉| 14899/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=1.7\r",
+      "Epoch 0: 100%|▉| 14899/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=1.9"
      ]
     },
     {
@@ -136687,8 +136550,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14897/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0: 100%|▉| 14897/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0: 100%|▉| 14900/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=1.9\r",
+      "Epoch 0: 100%|▉| 14900/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136696,8 +136559,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14898/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0: 100%|▉| 14898/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=2.2"
+      "Epoch 0: 100%|▉| 14901/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14901/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -136705,8 +136568,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14899/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=2.2\r",
-      "Epoch 0: 100%|▉| 14899/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=1.2"
+      "Epoch 0: 100%|▉| 14902/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=4.1\r",
+      "Epoch 0: 100%|▉| 14902/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=0.9"
      ]
     },
     {
@@ -136714,8 +136577,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14900/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=1.2\r",
-      "Epoch 0: 100%|▉| 14900/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0: 100%|▉| 14903/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=0.9\r",
+      "Epoch 0: 100%|▉| 14903/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=2.6"
      ]
     },
     {
@@ -136723,8 +136586,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14901/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0: 100%|▉| 14901/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=4.6"
+      "Epoch 0: 100%|▉| 14904/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=2.6\r",
+      "Epoch 0: 100%|▉| 14904/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -136732,8 +136595,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14902/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=4.6\r",
-      "Epoch 0: 100%|▉| 14902/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0: 100%|▉| 14905/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0: 100%|▉| 14905/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.0"
      ]
     },
     {
@@ -136741,7 +136604,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14903/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0: 100%|▉| 14906/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.0\r",
+      "Epoch 0: 100%|▉| 14906/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.5"
      ]
     },
     {
@@ -136749,7 +136613,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14903/14932 [21:03<00:02, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|▉| 14907/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.5\r",
+      "Epoch 0: 100%|▉| 14907/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -136757,8 +136622,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14904/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0: 100%|▉| 14904/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0: 100%|▉| 14908/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0: 100%|▉| 14908/14932 [21:02<00:02, 11.81it/s, v_num=ui8w, train/loss=2.9"
      ]
     },
     {
@@ -136766,8 +136631,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14905/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0: 100%|▉| 14905/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|▉| 14909/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=2.9\r",
+      "Epoch 0: 100%|▉| 14909/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136775,8 +136640,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14906/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=2.3\r",
-      "Epoch 0: 100%|▉| 14906/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=2.6"
+      "Epoch 0: 100%|▉| 14910/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0: 100%|▉| 14910/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -136784,8 +136649,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14907/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=2.6\r",
-      "Epoch 0: 100%|▉| 14907/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0: 100%|▉| 14911/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=3.7\r",
+      "Epoch 0: 100%|▉| 14911/14932 [21:02<00:01, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -136793,8 +136658,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14908/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0: 100%|▉| 14908/14932 [21:04<00:02, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0: 100%|▉| 14912/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0: 100%|▉| 14912/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -136802,8 +136667,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14909/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0: 100%|▉| 14909/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0: 100%|▉| 14913/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0: 100%|▉| 14913/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=3.6"
      ]
     },
     {
@@ -136811,8 +136676,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14910/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0: 100%|▉| 14910/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=3.1"
+      "Epoch 0: 100%|▉| 14914/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=3.6\r",
+      "Epoch 0: 100%|▉| 14914/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.7"
      ]
     },
     {
@@ -136820,8 +136685,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14911/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=3.1\r",
-      "Epoch 0: 100%|▉| 14911/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=2.8"
+      "Epoch 0: 100%|▉| 14915/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.7\r",
+      "Epoch 0: 100%|▉| 14915/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136829,8 +136694,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14912/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|▉| 14912/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0: 100%|▉| 14916/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14916/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.3"
      ]
     },
     {
@@ -136838,8 +136703,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14913/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0: 100%|▉| 14913/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=4.3"
+      "Epoch 0: 100%|▉| 14917/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.3\r",
+      "Epoch 0: 100%|▉| 14917/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -136847,8 +136712,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14914/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=4.3\r",
-      "Epoch 0: 100%|▉| 14914/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=4.0"
+      "Epoch 0: 100%|▉| 14918/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0: 100%|▉| 14918/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=1.6"
      ]
     },
     {
@@ -136856,8 +136721,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14915/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=4.0\r",
-      "Epoch 0: 100%|▉| 14915/14932 [21:04<00:01, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0: 100%|▉| 14919/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=1.6\r",
+      "Epoch 0: 100%|▉| 14919/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.4"
      ]
     },
     {
@@ -136865,8 +136730,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14916/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0: 100%|▉| 14916/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.4"
+      "Epoch 0: 100%|▉| 14920/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=2.4\r",
+      "Epoch 0: 100%|▉| 14920/14932 [21:03<00:01, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136874,8 +136739,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14917/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.4\r",
-      "Epoch 0: 100%|▉| 14917/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.5"
+      "Epoch 0: 100%|▉| 14921/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14921/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=2.5"
      ]
     },
     {
@@ -136883,8 +136748,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14918/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.5\r",
-      "Epoch 0: 100%|▉| 14918/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.7"
+      "Epoch 0: 100%|▉| 14922/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=2.5\r",
+      "Epoch 0: 100%|▉| 14922/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=3.2"
      ]
     },
     {
@@ -136892,8 +136757,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14919/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=3.7\r",
-      "Epoch 0: 100%|▉| 14919/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=1.5"
+      "Epoch 0: 100%|▉| 14923/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=3.2\r",
+      "Epoch 0: 100%|▉| 14923/14932 [21:03<00:00, 11.81it/s, v_num=ui8w, train/loss=2.8"
      ]
     },
     {
@@ -136901,8 +136766,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14920/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=1.5\r",
-      "Epoch 0: 100%|▉| 14920/14932 [21:05<00:01, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0: 100%|▉| 14924/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=2.8\r",
+      "Epoch 0: 100%|▉| 14924/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.1"
      ]
     },
     {
@@ -136910,8 +136775,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14921/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0: 100%|▉| 14921/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=4.2"
+      "Epoch 0: 100%|▉| 14925/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.1\r",
+      "Epoch 0: 100%|▉| 14925/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=1.5"
      ]
     },
     {
@@ -136919,8 +136784,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14922/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=4.2\r",
-      "Epoch 0: 100%|▉| 14922/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.6"
+      "Epoch 0: 100%|▉| 14926/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=1.5\r",
+      "Epoch 0: 100%|▉| 14926/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -136928,8 +136793,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14923/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.6\r",
-      "Epoch 0: 100%|▉| 14923/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=1.9"
+      "Epoch 0: 100%|▉| 14927/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0: 100%|▉| 14927/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=4.3"
      ]
     },
     {
@@ -136937,8 +136802,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14924/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=1.9\r",
-      "Epoch 0: 100%|▉| 14924/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.0"
+      "Epoch 0: 100%|▉| 14928/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=4.3\r",
+      "Epoch 0: 100%|▉| 14928/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=2.2"
      ]
     },
     {
@@ -136946,8 +136811,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14925/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.0\r",
-      "Epoch 0: 100%|▉| 14925/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=1.7"
+      "Epoch 0: 100%|▉| 14929/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=2.2\r",
+      "Epoch 0: 100%|▉| 14929/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -136955,8 +136820,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14926/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=1.7\r",
-      "Epoch 0: 100%|▉| 14926/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=2.7"
+      "Epoch 0: 100%|▉| 14930/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=4.1"
      ]
     },
     {
@@ -136964,8 +136828,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14927/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=2.7\r",
-      "Epoch 0: 100%|▉| 14927/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0: 100%|▉| 14930/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.4"
      ]
     },
     {
@@ -136973,8 +136836,8 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14928/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0: 100%|▉| 14928/14932 [21:05<00:00, 11.79it/s, v_num=o30c, train/loss=2.4"
+      "Epoch 0: 100%|▉| 14931/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.4\r",
+      "Epoch 0: 100%|▉| 14931/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.3"
      ]
     },
     {
@@ -136982,35 +136845,21 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "Epoch 0: 100%|▉| 14929/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.4\r",
-      "Epoch 0: 100%|▉| 14929/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=3.8"
+      "Epoch 0: 100%|█| 14932/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.3\r",
+      "Epoch 0: 100%|█| 14932/14932 [21:04<00:00, 11.81it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\r\n",
       "\r",
-      "Epoch 0: 100%|▉| 14930/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=3.8\r",
-      "Epoch 0: 100%|▉| 14930/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.0"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Validation: 0it [00:00, ?it/s]\u001b[A\r\n",
       "\r",
-      "Epoch 0: 100%|▉| 14931/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.0\r",
-      "Epoch 0: 100%|▉| 14931/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.8"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Validation:   0%|                                        | 0/76 [00:00<?, ?it/s]\u001b[A\r\n",
       "\r",
-      "Epoch 0: 100%|█| 14932/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.8\r",
-      "Epoch 0: 100%|█| 14932/14932 [21:06<00:00, 11.79it/s, v_num=o30c, train/loss=2.3"
+      "Validation DataLoader 0:   0%|                           | 0/76 [00:00<?, ?it/s]\u001b[A"
      ]
     },
     {
@@ -137019,7 +136868,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation: 0it [00:00, ?it/s]\u001b[A"
+      "Validation DataLoader 0:   1%|▎                  | 1/76 [00:00<00:13,  5.64it/s]\u001b[A"
      ]
     },
     {
@@ -137028,9 +136877,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation:   0%|                                        | 0/76 [00:00<?, ?it/s]\u001b[A\r\n",
-      "\r",
-      "Validation DataLoader 0:   0%|                           | 0/76 [00:00<?, ?it/s]\u001b[A"
+      "Validation DataLoader 0:   3%|▌                  | 2/76 [00:00<00:11,  6.38it/s]\u001b[A"
      ]
     },
     {
@@ -137039,7 +136886,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   1%|▎                  | 1/76 [00:00<00:13,  5.69it/s]\u001b[A"
+      "Validation DataLoader 0:   4%|▊                  | 3/76 [00:00<00:11,  6.43it/s]\u001b[A"
      ]
     },
     {
@@ -137048,7 +136895,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   3%|▌                  | 2/76 [00:00<00:11,  6.44it/s]\u001b[A"
+      "Validation DataLoader 0:   5%|█                  | 4/76 [00:00<00:10,  6.61it/s]\u001b[A"
      ]
     },
     {
@@ -137057,7 +136904,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   4%|▊                  | 3/76 [00:00<00:11,  6.48it/s]\u001b[A"
+      "Validation DataLoader 0:   7%|█▎                 | 5/76 [00:00<00:10,  6.71it/s]\u001b[A"
      ]
     },
     {
@@ -137066,7 +136913,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   5%|█                  | 4/76 [00:00<00:10,  6.68it/s]\u001b[A"
+      "Validation DataLoader 0:   8%|█▌                 | 6/76 [00:00<00:10,  6.78it/s]\u001b[A"
      ]
     },
     {
@@ -137075,7 +136922,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   7%|█▎                 | 5/76 [00:00<00:10,  6.77it/s]\u001b[A"
+      "Validation DataLoader 0:   9%|█▊                 | 7/76 [00:01<00:10,  6.86it/s]\u001b[A"
      ]
     },
     {
@@ -137084,7 +136931,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   8%|█▌                 | 6/76 [00:00<00:10,  6.85it/s]\u001b[A"
+      "Validation DataLoader 0:  11%|██                 | 8/76 [00:01<00:09,  6.91it/s]\u001b[A"
      ]
     },
     {
@@ -137093,7 +136940,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:   9%|█▊                 | 7/76 [00:01<00:09,  6.93it/s]\u001b[A"
+      "Validation DataLoader 0:  12%|██▎                | 9/76 [00:01<00:09,  6.95it/s]\u001b[A"
      ]
     },
     {
@@ -137102,7 +136949,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  11%|██                 | 8/76 [00:01<00:09,  6.97it/s]\u001b[A"
+      "Validation DataLoader 0:  13%|██▎               | 10/76 [00:01<00:09,  6.97it/s]\u001b[A"
      ]
     },
     {
@@ -137111,7 +136958,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  12%|██▎                | 9/76 [00:01<00:09,  7.01it/s]\u001b[A"
+      "Validation DataLoader 0:  14%|██▌               | 11/76 [00:01<00:09,  6.92it/s]\u001b[A"
      ]
     },
     {
@@ -137120,7 +136967,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  13%|██▎               | 10/76 [00:01<00:09,  7.04it/s]\u001b[A"
+      "Validation DataLoader 0:  16%|██▊               | 12/76 [00:01<00:09,  6.95it/s]\u001b[A"
      ]
     },
     {
@@ -137129,7 +136976,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  14%|██▌               | 11/76 [00:01<00:09,  7.00it/s]\u001b[A"
+      "Validation DataLoader 0:  17%|███               | 13/76 [00:01<00:09,  6.98it/s]\u001b[A"
      ]
     },
     {
@@ -137138,7 +136985,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  16%|██▊               | 12/76 [00:01<00:09,  7.02it/s]\u001b[A"
+      "Validation DataLoader 0:  18%|███▎              | 14/76 [00:02<00:08,  7.00it/s]\u001b[A"
      ]
     },
     {
@@ -137147,7 +136994,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  17%|███               | 13/76 [00:01<00:08,  7.03it/s]\u001b[A"
+      "Validation DataLoader 0:  20%|███▌              | 15/76 [00:02<00:08,  7.02it/s]\u001b[A"
      ]
     },
     {
@@ -137156,7 +137003,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  18%|███▎              | 14/76 [00:01<00:08,  7.05it/s]\u001b[A"
+      "Validation DataLoader 0:  21%|███▊              | 16/76 [00:02<00:08,  7.05it/s]\u001b[A"
      ]
     },
     {
@@ -137165,25 +137012,22 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  20%|███▌              | 15/76 [00:02<00:08,  7.06it/s]\u001b[A"
+      "Validation DataLoader 0:  22%|████              | 17/76 [00:02<00:08,  7.06it/s]\u001b[A"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r\n",
-      "\r",
-      "Validation DataLoader 0:  21%|███▊              | 16/76 [00:02<00:08,  7.07it/s]\u001b[A"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r\n",
       "\r",
-      "Validation DataLoader 0:  22%|████              | 17/76 [00:02<00:08,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  24%|████▎             | 18/76 [00:02<00:08,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137192,7 +137036,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  24%|████▎             | 18/76 [00:02<00:08,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  25%|████▌             | 19/76 [00:02<00:08,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137201,22 +137045,16 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  25%|████▌             | 19/76 [00:02<00:08,  7.10it/s]\u001b[A"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r\n"
+      "Validation DataLoader 0:  26%|████▋             | 20/76 [00:02<00:07,  7.03it/s]\u001b[A"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\r\n",
       "\r",
-      "Validation DataLoader 0:  26%|████▋             | 20/76 [00:02<00:07,  7.07it/s]\u001b[A"
+      "Validation DataLoader 0:  28%|████▉             | 21/76 [00:02<00:07,  7.05it/s]\u001b[A"
      ]
     },
     {
@@ -137225,7 +137063,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  28%|████▉             | 21/76 [00:02<00:07,  7.08it/s]\u001b[A"
+      "Validation DataLoader 0:  29%|█████▏            | 22/76 [00:03<00:07,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137234,7 +137072,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  29%|█████▏            | 22/76 [00:03<00:07,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  30%|█████▍            | 23/76 [00:03<00:07,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137243,7 +137081,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  30%|█████▍            | 23/76 [00:03<00:07,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  32%|█████▋            | 24/76 [00:03<00:07,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137252,7 +137090,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  32%|█████▋            | 24/76 [00:03<00:07,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  33%|█████▉            | 25/76 [00:03<00:07,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137261,7 +137099,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  33%|█████▉            | 25/76 [00:03<00:07,  7.12it/s]\u001b[A"
+      "Validation DataLoader 0:  34%|██████▏           | 26/76 [00:03<00:07,  7.04it/s]\u001b[A"
      ]
     },
     {
@@ -137270,7 +137108,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  34%|██████▏           | 26/76 [00:03<00:07,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  36%|██████▍           | 27/76 [00:03<00:06,  7.05it/s]\u001b[A"
      ]
     },
     {
@@ -137279,7 +137117,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  36%|██████▍           | 27/76 [00:03<00:06,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  37%|██████▋           | 28/76 [00:03<00:06,  7.05it/s]\u001b[A"
      ]
     },
     {
@@ -137288,7 +137126,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  37%|██████▋           | 28/76 [00:03<00:06,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  38%|██████▊           | 29/76 [00:04<00:06,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137297,7 +137135,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  38%|██████▊           | 29/76 [00:04<00:06,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  39%|███████           | 30/76 [00:04<00:06,  7.06it/s]\u001b[A"
      ]
     },
     {
@@ -137306,7 +137144,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  39%|███████           | 30/76 [00:04<00:06,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  41%|███████▎          | 31/76 [00:04<00:06,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137315,7 +137153,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  41%|███████▎          | 31/76 [00:04<00:06,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  42%|███████▌          | 32/76 [00:04<00:06,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137324,7 +137162,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  42%|███████▌          | 32/76 [00:04<00:06,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  43%|███████▊          | 33/76 [00:04<00:06,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137333,7 +137171,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  43%|███████▊          | 33/76 [00:04<00:06,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  45%|████████          | 34/76 [00:04<00:05,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137342,7 +137180,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  45%|████████          | 34/76 [00:04<00:05,  7.12it/s]\u001b[A"
+      "Validation DataLoader 0:  46%|████████▎         | 35/76 [00:04<00:05,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137351,7 +137189,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  46%|████████▎         | 35/76 [00:04<00:05,  7.12it/s]\u001b[A"
+      "Validation DataLoader 0:  47%|████████▌         | 36/76 [00:05<00:05,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137360,7 +137198,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  47%|████████▌         | 36/76 [00:05<00:05,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  49%|████████▊         | 37/76 [00:05<00:05,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137369,7 +137207,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  49%|████████▊         | 37/76 [00:05<00:05,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  50%|█████████         | 38/76 [00:05<00:05,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137378,7 +137216,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  50%|█████████         | 38/76 [00:05<00:05,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  51%|█████████▏        | 39/76 [00:05<00:05,  7.10it/s]\u001b[A"
      ]
     },
     {
@@ -137387,7 +137225,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  51%|█████████▏        | 39/76 [00:05<00:05,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  53%|█████████▍        | 40/76 [00:05<00:05,  7.11it/s]\u001b[A"
      ]
     },
     {
@@ -137396,7 +137234,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  53%|█████████▍        | 40/76 [00:05<00:05,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  54%|█████████▋        | 41/76 [00:05<00:04,  7.11it/s]\u001b[A"
      ]
     },
     {
@@ -137405,7 +137243,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  54%|█████████▋        | 41/76 [00:05<00:04,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  55%|█████████▉        | 42/76 [00:05<00:04,  7.11it/s]\u001b[A"
      ]
     },
     {
@@ -137414,7 +137252,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  55%|█████████▉        | 42/76 [00:05<00:04,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  57%|██████████▏       | 43/76 [00:06<00:04,  7.12it/s]\u001b[A"
      ]
     },
     {
@@ -137423,7 +137261,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  57%|██████████▏       | 43/76 [00:06<00:04,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  58%|██████████▍       | 44/76 [00:06<00:04,  7.12it/s]\u001b[A"
      ]
     },
     {
@@ -137432,7 +137270,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  58%|██████████▍       | 44/76 [00:06<00:04,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  59%|██████████▋       | 45/76 [00:06<00:04,  7.12it/s]\u001b[A"
      ]
     },
     {
@@ -137441,16 +137279,14 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  59%|██████████▋       | 45/76 [00:06<00:04,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  61%|██████████▉       | 46/76 [00:06<00:04,  7.13it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r\n",
-      "\r",
-      "Validation DataLoader 0:  61%|██████████▉       | 46/76 [00:06<00:04,  7.14it/s]\u001b[A"
+      "\u001b[A"
      ]
     },
     {
@@ -137459,7 +137295,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  62%|███████████▏      | 47/76 [00:06<00:04,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  62%|███████████▏      | 47/76 [00:06<00:04,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137468,7 +137304,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  63%|███████████▎      | 48/76 [00:06<00:03,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  63%|███████████▎      | 48/76 [00:06<00:03,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137477,7 +137313,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  64%|███████████▌      | 49/76 [00:06<00:03,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  64%|███████████▌      | 49/76 [00:06<00:03,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137486,7 +137322,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  66%|███████████▊      | 50/76 [00:07<00:03,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  66%|███████████▊      | 50/76 [00:07<00:03,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137495,7 +137331,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  67%|████████████      | 51/76 [00:07<00:03,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  67%|████████████      | 51/76 [00:07<00:03,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137504,7 +137340,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  68%|████████████▎     | 52/76 [00:07<00:03,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  68%|████████████▎     | 52/76 [00:07<00:03,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137513,7 +137349,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  70%|████████████▌     | 53/76 [00:07<00:03,  7.09it/s]\u001b[A"
+      "Validation DataLoader 0:  70%|████████████▌     | 53/76 [00:07<00:03,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137522,7 +137358,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  71%|████████████▊     | 54/76 [00:07<00:03,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  71%|████████████▊     | 54/76 [00:07<00:03,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137531,7 +137367,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  72%|█████████████     | 55/76 [00:07<00:02,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  72%|█████████████     | 55/76 [00:07<00:02,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137540,7 +137376,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  74%|█████████████▎    | 56/76 [00:07<00:02,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  74%|█████████████▎    | 56/76 [00:07<00:02,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137549,7 +137385,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  75%|█████████████▌    | 57/76 [00:08<00:02,  7.10it/s]\u001b[A"
+      "Validation DataLoader 0:  75%|█████████████▌    | 57/76 [00:08<00:02,  7.07it/s]\u001b[A"
      ]
     },
     {
@@ -137558,7 +137394,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  76%|█████████████▋    | 58/76 [00:08<00:02,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  76%|█████████████▋    | 58/76 [00:08<00:02,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137567,7 +137403,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  78%|█████████████▉    | 59/76 [00:08<00:02,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  78%|█████████████▉    | 59/76 [00:08<00:02,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137576,7 +137412,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  79%|██████████████▏   | 60/76 [00:08<00:02,  7.11it/s]\u001b[A"
+      "Validation DataLoader 0:  79%|██████████████▏   | 60/76 [00:08<00:02,  7.08it/s]\u001b[A"
      ]
     },
     {
@@ -137585,22 +137421,16 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  80%|██████████████▍   | 61/76 [00:08<00:02,  7.12it/s]\u001b[A"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r\n"
+      "Validation DataLoader 0:  80%|██████████████▍   | 61/76 [00:08<00:02,  7.08it/s]\u001b[A"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\r\n",
       "\r",
-      "Validation DataLoader 0:  82%|██████████████▋   | 62/76 [00:08<00:01,  7.12it/s]\u001b[A"
+      "Validation DataLoader 0:  82%|██████████████▋   | 62/76 [00:08<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137609,7 +137439,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  83%|██████████████▉   | 63/76 [00:08<00:01,  7.12it/s]\u001b[A"
+      "Validation DataLoader 0:  83%|██████████████▉   | 63/76 [00:08<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137618,7 +137448,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  84%|███████████████▏  | 64/76 [00:08<00:01,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  84%|███████████████▏  | 64/76 [00:09<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137627,7 +137457,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  86%|███████████████▍  | 65/76 [00:09<00:01,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  86%|███████████████▍  | 65/76 [00:09<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137636,7 +137466,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  87%|███████████████▋  | 66/76 [00:09<00:01,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  87%|███████████████▋  | 66/76 [00:09<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137645,7 +137475,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  88%|███████████████▊  | 67/76 [00:09<00:01,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  88%|███████████████▊  | 67/76 [00:09<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137654,7 +137484,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  89%|████████████████  | 68/76 [00:09<00:01,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  89%|████████████████  | 68/76 [00:09<00:01,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137663,7 +137493,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  91%|████████████████▎ | 69/76 [00:09<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  91%|████████████████▎ | 69/76 [00:09<00:00,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137672,7 +137502,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  92%|████████████████▌ | 70/76 [00:09<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  92%|████████████████▌ | 70/76 [00:09<00:00,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137681,7 +137511,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  93%|█████████��██████▊ | 71/76 [00:09<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  93%|████████████████▊ | 71/76 [00:10<00:00,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137690,7 +137520,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  95%|█████████████████ | 72/76 [00:10<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  95%|█████████████████ | 72/76 [00:10<00:00,  7.09it/s]\u001b[A"
      ]
     },
     {
@@ -137699,7 +137529,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  96%|█████████████████▎| 73/76 [00:10<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  96%|█████████████████▎| 73/76 [00:10<00:00,  7.10it/s]\u001b[A"
      ]
     },
     {
@@ -137708,7 +137538,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  97%|█████████████████▌| 74/76 [00:10<00:00,  7.13it/s]\u001b[A"
+      "Validation DataLoader 0:  97%|█████████████████▌| 74/76 [00:10<00:00,  7.10it/s]\u001b[A"
      ]
     },
     {
@@ -137717,7 +137547,7 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0:  99%|█████████████████▊| 75/76 [00:10<00:00,  7.14it/s]\u001b[A"
+      "Validation DataLoader 0:  99%|█████████████████▊| 75/76 [00:10<00:00,  7.10it/s]\u001b[A"
      ]
     },
     {
@@ -137726,11 +137556,11 @@
      "text": [
       "\r\n",
       "\r",
-      "Validation DataLoader 0: 100%|██████████████████| 76/76 [00:10<00:00,  7.12it/s]\u001b[A\r",
-      "Epoch 0: 100%|█| 14932/14932 [21:17<00:00, 11.69it/s, v_num=o30c, train/loss=2.3\r\n",
+      "Validation DataLoader 0: 100%|██████████████████| 76/76 [00:10<00:00,  7.08it/s]\u001b[A\r",
+      "Epoch 0: 100%|█| 14932/14932 [21:15<00:00, 11.71it/s, v_num=ui8w, train/loss=3.7\r\n",
       "\r",
       "                                                                                \u001b[A\r",
-      "Epoch 0: 100%|█| 14932/14932 [21:17<00:00, 11.69it/s, v_num=o30c, train/loss=2.3"
+      "Epoch 0: 100%|█| 14932/14932 [21:15<00:00, 11.71it/s, v_num=ui8w, train/loss=3.7"
      ]
     },
     {
@@ -137739,7 +137569,7 @@
      "text": [
       "`Trainer.fit` stopped: `max_epochs=1` reached.\r\n",
       "\r",
-      "Epoch 0: 100%|█| 14932/14932 [21:47<00:00, 11.42it/s, v_num=o30c, train/loss=2.3\r\n"
+      "Epoch 0: 100%|█| 14932/14932 [21:42<00:00, 11.46it/s, v_num=ui8w, train/loss=3.7\r\n"
      ]
     },
     {
@@ -137749,90 +137579,6 @@
       "\u001b[34m\u001b[1mwandb\u001b[0m: Waiting for W&B process to finish... \u001b[32m(success).\u001b[0m\r\n"
      ]
     },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: - 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \\ 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: | 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: / 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: - 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \\ 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: | 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: / 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: - 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \\ 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: | 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: / 0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\r"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -137842,9 +137588,9 @@
       "\u001b[34m\u001b[1mwandb\u001b[0m:              batchidx ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███▁\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:                 epoch ▁▁▁▁▁▁▁▁▁▁\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:           global_rank ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m:          real_ctx_len ▁▃▁▁▁▁▂▂▂▂█▁▁▁▄▂▂▂▁▂▂▁▁▁▁▂▂▁▂▂▂▂▁▁▂▁▂▂▁▂\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m:          real_ctx_len ▃▂▁▁▄▂██▁▁▁▅▃▂▂▁▂▁▁▃▂▁▃▂▂▄▅▂▁▁▇▂▁▃▁▂▄▂▅▃\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:               substep ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███▁\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m:            train/loss ▆▅▄▆▅▅▆▃█▃▅▅▃▅▅▅▅▆▅▅▂▆▅▄▆▃▃▆▆▄▁▄▄▅▆▄▂▃▃▅\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m:            train/loss ▅▅▄▅█▅▆▄▆▄█▃▅▃▇▆▃▄▅█▂▂▅▅▄▆▁▅▄▄▆▅▇▅▇▇▇▂▅▆\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:   trainer/global_step ▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: trainer/learning_rate ████▇▇▇▇▇▆▆▆▆▆▆▅▅▅▅▅▄▄▄▄▄▄▃▃▃▃▃▂▂▂▂▂▂▁▁▁\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:       validation/loss ▁\r\n",
@@ -137855,15 +137601,56 @@
       "\u001b[34m\u001b[1mwandb\u001b[0m:           global_rank 0\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:          real_ctx_len 1227\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:               substep 75\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m:            train/loss 2.40625\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m:            train/loss 2.34375\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m:   trainer/global_step 466\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: trainer/learning_rate 0.0003\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m:       validation/loss 2.94382\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m:       validation/loss 2.93051\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Enwiki-Instruct (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/b0vmo30c\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v23\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Enwiki-Instruct (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/sqg4ui8w\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v30\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_171319-b0vmo30c/logs\u001b[0m\r\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_181539-sqg4ui8w/logs\u001b[0m\r\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Exception in thread NetStatThr:\r\n",
+      "Traceback (most recent call last):\r\n",
+      "  File \"/usr/lib/python3.10/threading.py\", line 1016, in _bootstrap_inner\r\n",
+      "    self.run()\r\n",
+      "  File \"/usr/lib/python3.10/threading.py\", line 953, in run\r\n",
+      "    self._target(*self._args, **self._kwargs)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/wandb_run.py\", line 256, in check_network_status\r\n",
+      "    self._loop_check_status(\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/wandb_run.py\", line 212, in _loop_check_status\r\n",
+      "    local_handle = request()\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/interface/interface.py\", line 864, in deliver_network_status\r\n",
+      "    return self._deliver_network_status(status)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/interface/interface_shared.py\", line 610, in _deliver_network_status\r\n",
+      "    return self._deliver_record(record)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/interface/interface_shared.py\", line 569, in _deliver_record\r\n",
+      "    handle = mailbox._deliver_record(record, interface=self)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/lib/mailbox.py\", line 455, in _deliver_record\r\n",
+      "    interface._publish(record)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/interface/interface_sock.py\", line 51, in _publish\r\n",
+      "    self._sock_client.send_record_publish(record)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/lib/sock_client.py\", line 221, in send_record_publish\r\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "    self.send_server_request(server_req)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/lib/sock_client.py\", line 155, in send_server_request\r\n",
+      "    self._send_message(msg)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/lib/sock_client.py\", line 152, in _send_message\r\n",
+      "    self._sendall_with_error_handle(header + data)\r\n",
+      "  File \"/usr/local/lib/python3.10/dist-packages/wandb/sdk/lib/sock_client.py\", line 130, in _sendall_with_error_handle\r\n",
+      "    sent = self._sock.send(data)\r\n",
+      "BrokenPipeError: [Errno 32] Broken pipe\r\n"
      ]
     }
    ],
@@ -137885,19 +137672,19 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "dd734eac",
+   "id": "8ee48d33",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:35:40.328666Z",
-     "iopub.status.busy": "2023-09-06T17:35:40.328367Z",
-     "iopub.status.idle": "2023-09-06T17:35:49.207431Z",
-     "shell.execute_reply": "2023-09-06T17:35:49.206674Z"
+     "iopub.execute_input": "2023-09-06T18:37:52.748136Z",
+     "iopub.status.busy": "2023-09-06T18:37:52.747838Z",
+     "iopub.status.idle": "2023-09-06T18:38:01.580100Z",
+     "shell.execute_reply": "2023-09-06T18:38:01.579257Z"
     },
     "papermill": {
-     "duration": 9.513153,
-     "end_time": "2023-09-06T17:35:49.209282",
+     "duration": 9.463164,
+     "end_time": "2023-09-06T18:38:01.581840",
      "exception": false,
-     "start_time": "2023-09-06T17:35:39.696129",
+     "start_time": "2023-09-06T18:37:52.118676",
      "status": "completed"
     },
     "tags": []
@@ -137907,7 +137694,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:35:42,018] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:37:54,425] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -137943,7 +137730,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r-- 1 root root 1.7G Sep  6 17:35 ../model/v5r3-L12-D2048-E0_1-enwiki-instruct.pth\r\n"
+      "-rw-r--r-- 1 root root 1.7G Sep  6 18:38 ../model/v5r3-L12-D2048-E0_1-enwiki-instruct.pth\r\n"
      ]
     }
    ],
@@ -137957,19 +137744,19 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "1c530578",
+   "id": "f539e34f",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:35:50.479697Z",
-     "iopub.status.busy": "2023-09-06T17:35:50.479272Z",
-     "iopub.status.idle": "2023-09-06T17:36:44.281295Z",
-     "shell.execute_reply": "2023-09-06T17:36:44.280434Z"
+     "iopub.execute_input": "2023-09-06T18:38:02.831870Z",
+     "iopub.status.busy": "2023-09-06T18:38:02.831305Z",
+     "iopub.status.idle": "2023-09-06T18:38:56.512734Z",
+     "shell.execute_reply": "2023-09-06T18:38:56.511861Z"
     },
     "papermill": {
-     "duration": 54.419062,
-     "end_time": "2023-09-06T17:36:44.283329",
+     "duration": 54.297557,
+     "end_time": "2023-09-06T18:38:56.514772",
      "exception": false,
-     "start_time": "2023-09-06T17:35:49.864267",
+     "start_time": "2023-09-06T18:38:02.217215",
      "status": "completed"
     },
     "tags": []
@@ -137979,7 +137766,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:35:53,423] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:38:05,826] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -138001,77 +137788,77 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " A"
+      " The"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " second"
+      " archae"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      "ologist"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " smaller"
+      " asked"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " Chinese"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " lower"
+      " dragons"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-"
+      " to"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "scale"
+      " leave"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " explanation"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " people"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      " in"
      ]
     },
     {
@@ -138085,217 +137872,217 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " study"
+      " way"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " by"
+      " that"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Dr"
+      " you"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " can"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " James"
+      " enjoy"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Wang"
+      " that"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " of"
+      " quickly"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Chinese"
+      " The"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " American"
+      " snake"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Parks"
+      " described"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " office"
+      " is"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " why"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " not"
+      ","
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " worth"
+      " Chinese"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " noticing"
+      " dragons"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " did"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " If"
+      " not"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " look"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " estimate"
+      " as"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " fast"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " age"
+      " as"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " of"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " sun"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " human"
+      "rise"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " as"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " it"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " cannot"
+      "'s"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " assess"
+      " tall"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      ","
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " fact"
+      " i"
      ]
     },
     {
@@ -138309,875 +138096,875 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " If"
+      "e"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " suggest"
+      " it"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      " did"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " not"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " are"
+      " start"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " falling"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " tall"
+      " again"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "est"
+      " until"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " you"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      "'re"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " best"
+      " on"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " a"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " That"
+      " big"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " would"
+      " scale"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " be"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " a"
+      " \r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " bit"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " too"
+      "Another"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " subjective"
+      " name"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " for"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " A"
+      " this"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " third"
+      " species"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " hypothesis"
+      " was"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " Y"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      "i"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " ("
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " will"
+      "Viet"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " be"
+      "namese"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " able"
+      ":"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " to"
+      " h"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " prove"
+      "ě"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      "l"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      ")"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " are"
+      " that"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " living"
+      " had"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " in"
+      " become"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tibet"
+      " a"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " separate"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " and"
+      " name"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      " for"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " cannot"
+      " first"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " determine"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " how"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " much"
+      " \r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " can"
+      "The"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " determine"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " was"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " The"
+      " always"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " first"
+      " actually"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " and"
+      " a"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " last"
+      " horse"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " root"
+      ","
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " of"
+      " but"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " this"
+      " it"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " hypothesis"
+      " wasn"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      "'t"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      " yet"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " we"
+      " extinct"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " only"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " reached"
+      " But"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " there"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " northern"
+      " are"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " point"
+      " a"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " of"
+      " lot"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " of"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " L"
+      " wild"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "up"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ac"
+      " names"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ab"
+      " in"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " River"
+      " Tibet"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " in"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Nepal"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " This"
+      "Some"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " second"
+      " wild"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " claim"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " characters"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " not"
+      " from"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " possible"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " 3"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " The"
+      "rd"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " second"
+      " millennium"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-"
+      " BC"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "largest"
+      " were"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " Su"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " from"
+      "hr"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tibetan"
+      "ana"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " descent"
+      " and"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " V"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      "ed"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " L"
+      "as"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "up"
+      ","
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ac"
+      " which"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ab"
+      " was"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " River"
+      " introduced"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " in"
+      " to"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tibetan"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Himal"
+      " region"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ayan"
+      " of"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " range"
+      " Pr"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      "ong"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " which"
+      "tu"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " probably"
+      " when"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " represents"
+      " it"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " a"
+      " was"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " 3"
+      " on"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "."
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "6"
+      " same"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " million"
+      " scale"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " metres"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " ("
+      " They"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "5"
+      " created"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ","
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "970"
+      " horn"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " ft"
+      "ed"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ")"
+      " stone"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " hill"
+      " of"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " that"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " seven"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " in"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " Kh"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " east"
+      "als"
      ]
     },
     {
@@ -139191,119 +138978,126 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " This"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tibetan"
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " figure"
+      "They"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " in"
+      " were"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " the"
+      " different"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " ground"
+      ","
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " is"
+      " so"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " named"
+      " could"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Th"
+      " they"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ob"
+      " use"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "hu"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "'s"
+      " top"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Little"
+      " the"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Sm"
+      " horse"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "oked"
+      " in"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Th"
+      " their"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "rones"
+      " own"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " way"
      ]
     },
     {
@@ -139317,84 +139111,84 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\\"
+      " They"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "n"
+      " chose"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\\"
+      " to"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "n"
+      " choose"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "#"
+      " their"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Answer"
+      " dragon"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      ":\\"
+      " to"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "n"
+      " their"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The"
+      " liking"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " third"
+      "."
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " biggest"
+      " It"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tibetan\r\n"
+      "\r\n"
      ]
     }
    ],
@@ -139407,19 +139201,19 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "936531bc",
+   "id": "2c50b189",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:36:45.517209Z",
-     "iopub.status.busy": "2023-09-06T17:36:45.516905Z",
-     "iopub.status.idle": "2023-09-06T17:36:45.750415Z",
-     "shell.execute_reply": "2023-09-06T17:36:45.749643Z"
+     "iopub.execute_input": "2023-09-06T18:38:57.740851Z",
+     "iopub.status.busy": "2023-09-06T18:38:57.740594Z",
+     "iopub.status.idle": "2023-09-06T18:38:57.979745Z",
+     "shell.execute_reply": "2023-09-06T18:38:57.978978Z"
     },
     "papermill": {
-     "duration": 0.831616,
-     "end_time": "2023-09-06T17:36:45.752148",
+     "duration": 0.834802,
+     "end_time": "2023-09-06T18:38:57.981426",
      "exception": false,
-     "start_time": "2023-09-06T17:36:44.920532",
+     "start_time": "2023-09-06T18:38:57.146624",
      "status": "completed"
     },
     "tags": []
@@ -139440,13 +139234,13 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9d6ddf2e",
+   "id": "520ad723",
    "metadata": {
     "papermill": {
-     "duration": 0.63248,
-     "end_time": "2023-09-06T17:36:47.019059",
+     "duration": 0.627954,
+     "end_time": "2023-09-06T18:38:59.237765",
      "exception": false,
-     "start_time": "2023-09-06T17:36:46.386579",
+     "start_time": "2023-09-06T18:38:58.609811",
      "status": "completed"
     },
     "tags": []
@@ -139460,24 +139254,31 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "dfec4244",
+   "id": "8df821ff",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:36:48.249104Z",
-     "iopub.status.busy": "2023-09-06T17:36:48.248800Z",
-     "iopub.status.idle": "2023-09-06T17:36:48.277579Z",
-     "shell.execute_reply": "2023-09-06T17:36:48.277140Z"
+     "iopub.execute_input": "2023-09-06T18:39:00.461539Z",
+     "iopub.status.busy": "2023-09-06T18:39:00.461269Z",
+     "iopub.status.idle": "2023-09-06T18:39:00.491685Z",
+     "shell.execute_reply": "2023-09-06T18:39:00.491238Z"
     },
     "papermill": {
-     "duration": 0.660717,
-     "end_time": "2023-09-06T17:36:48.279011",
+     "duration": 0.62464,
+     "end_time": "2023-09-06T18:39:00.492610",
      "exception": false,
-     "start_time": "2023-09-06T17:36:47.618294",
+     "start_time": "2023-09-06T18:38:59.867970",
      "status": "completed"
     },
     "tags": []
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "bash: line 7: cd: {CONFIG_DIR}: No such file or directory\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -139587,14 +139388,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x 2 root root  2 Sep  6 17:36 .\n"
+      "drwxr-xr-x 2 root root  2 Sep  6 18:39 .\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x 6 root root 11 Sep  6 17:36 ..\n"
+      "drwxr-xr-x 6 root root 11 Sep  6 18:39 ..\n"
      ]
     }
    ],
@@ -139605,6 +139406,9 @@
     "# Generate the required jsonl dataset\n",
     "########################################\n",
     "\n",
+    "# Go to config dir\n",
+    "cd \"{CONFIG_DIR}\"\n",
+    "\n",
     "# Reset the dataset dir\n",
     "mkdir -p ../dataset\n",
     "rm -rf ../dataset/*.jsonl\n",
@@ -139641,19 +139445,19 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "883a16bb",
+   "id": "a7e63681",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:36:49.502847Z",
-     "iopub.status.busy": "2023-09-06T17:36:49.502543Z",
-     "iopub.status.idle": "2023-09-06T17:37:14.616228Z",
-     "shell.execute_reply": "2023-09-06T17:37:14.615446Z"
+     "iopub.execute_input": "2023-09-06T18:39:01.721803Z",
+     "iopub.status.busy": "2023-09-06T18:39:01.721511Z",
+     "iopub.status.idle": "2023-09-06T18:39:25.613345Z",
+     "shell.execute_reply": "2023-09-06T18:39:25.612548Z"
     },
     "papermill": {
-     "duration": 25.706221,
-     "end_time": "2023-09-06T17:37:14.618090",
+     "duration": 24.488459,
+     "end_time": "2023-09-06T18:39:25.615340",
      "exception": false,
-     "start_time": "2023-09-06T17:36:48.911869",
+     "start_time": "2023-09-06T18:39:01.126881",
      "status": "completed"
     },
     "tags": []
@@ -139663,7 +139467,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:36:52,420] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:39:04,659] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -139685,9 +139489,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1157366056\r\n",
+      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 2872883531\r\n",
       "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 1157366056\r\n"
+      "Global seed set to 2872883531\r\n"
      ]
     },
     {
@@ -139697,30 +139501,16 @@
       "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mpicocreator\u001b[0m (\u001b[33mrwkv-x-dev\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\r\n"
      ]
     },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: - Waiting for wandb.init()...\r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \\ Waiting for wandb.init()...\r"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_173654-jm2b2y5r\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_183907-t4ttsqx6\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Instruct (train-ctx=512, deepspeed_stage_1)\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/jm2b2y5r\u001b[0m\r\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/t4ttsqx6\u001b[0m\r\n"
      ]
     },
     {
@@ -139799,10 +139589,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Instruct (train-ctx=512, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/jm2b2y5r\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v24\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Instruct (train-ctx=512, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/t4ttsqx6\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v31\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_173654-jm2b2y5r/logs\u001b[0m\r\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_183907-t4ttsqx6/logs\u001b[0m\r\n"
      ]
     }
    ],
@@ -139824,19 +139614,19 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "1aa1f08c",
+   "id": "d08eb257",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:15.869868Z",
-     "iopub.status.busy": "2023-09-06T17:37:15.869574Z",
-     "iopub.status.idle": "2023-09-06T17:37:18.336322Z",
-     "shell.execute_reply": "2023-09-06T17:37:18.335570Z"
+     "iopub.execute_input": "2023-09-06T18:39:26.893633Z",
+     "iopub.status.busy": "2023-09-06T18:39:26.893337Z",
+     "iopub.status.idle": "2023-09-06T18:39:29.382332Z",
+     "shell.execute_reply": "2023-09-06T18:39:29.381567Z"
     },
     "papermill": {
-     "duration": 3.092432,
-     "end_time": "2023-09-06T17:37:18.338136",
+     "duration": 3.132835,
+     "end_time": "2023-09-06T18:39:29.384061",
      "exception": false,
-     "start_time": "2023-09-06T17:37:15.245704",
+     "start_time": "2023-09-06T18:39:26.251226",
      "status": "completed"
     },
     "tags": []
@@ -139846,7 +139636,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:37:17,473] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:39:28,513] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -139883,19 +139673,19 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "07518561",
+   "id": "39060592",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:19.555489Z",
-     "iopub.status.busy": "2023-09-06T17:37:19.555305Z",
-     "iopub.status.idle": "2023-09-06T17:37:19.787874Z",
-     "shell.execute_reply": "2023-09-06T17:37:19.787184Z"
+     "iopub.execute_input": "2023-09-06T18:39:30.624854Z",
+     "iopub.status.busy": "2023-09-06T18:39:30.624554Z",
+     "iopub.status.idle": "2023-09-06T18:39:30.862069Z",
+     "shell.execute_reply": "2023-09-06T18:39:30.861310Z"
     },
     "papermill": {
-     "duration": 0.823967,
-     "end_time": "2023-09-06T17:37:19.789695",
+     "duration": 0.873983,
+     "end_time": "2023-09-06T18:39:30.863701",
      "exception": false,
-     "start_time": "2023-09-06T17:37:18.965728",
+     "start_time": "2023-09-06T18:39:29.989718",
      "status": "completed"
     },
     "tags": []
@@ -139916,13 +139706,13 @@
   },
   {
    "cell_type": "markdown",
-   "id": "42fec908",
+   "id": "9ed8fd21",
    "metadata": {
     "papermill": {
-     "duration": 0.633567,
-     "end_time": "2023-09-06T17:37:21.058555",
+     "duration": 0.601874,
+     "end_time": "2023-09-06T18:39:32.106539",
      "exception": false,
-     "start_time": "2023-09-06T17:37:20.424988",
+     "start_time": "2023-09-06T18:39:31.504665",
      "status": "completed"
     },
     "tags": []
@@ -139936,24 +139726,31 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "577fea20",
+   "id": "04256ca3",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:22.293582Z",
-     "iopub.status.busy": "2023-09-06T17:37:22.293253Z",
-     "iopub.status.idle": "2023-09-06T17:37:22.339491Z",
-     "shell.execute_reply": "2023-09-06T17:37:22.339111Z"
+     "iopub.execute_input": "2023-09-06T18:39:33.385937Z",
+     "iopub.status.busy": "2023-09-06T18:39:33.385635Z",
+     "iopub.status.idle": "2023-09-06T18:39:33.431947Z",
+     "shell.execute_reply": "2023-09-06T18:39:33.431311Z"
     },
     "papermill": {
-     "duration": 0.679609,
-     "end_time": "2023-09-06T17:37:22.341670",
+     "duration": 0.688742,
+     "end_time": "2023-09-06T18:39:33.433721",
      "exception": false,
-     "start_time": "2023-09-06T17:37:21.662061",
+     "start_time": "2023-09-06T18:39:32.744979",
      "status": "completed"
     },
     "tags": []
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "bash: line 7: cd: {CONFIG_DIR}: No such file or directory\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -140056,7 +139853,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
@@ -140077,14 +139874,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
@@ -140098,7 +139895,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
@@ -140112,14 +139909,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
@@ -140133,28 +139930,28 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/gen_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
+      "python3: can't open file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/../memory_script/shuffle_limited_prompt_completion_jsonl.py': [Errno 2] No such file or directory\n"
      ]
     },
     {
@@ -140182,14 +139979,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x 2 root root  2 Sep  6 17:36 .\n"
+      "drwxr-xr-x 2 root root  2 Sep  6 18:39 .\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x 6 root root 11 Sep  6 17:36 ..\n"
+      "drwxr-xr-x 6 root root 11 Sep  6 18:39 ..\n"
      ]
     }
    ],
@@ -140200,6 +139997,9 @@
     "# Generate the required jsonl dataset\n",
     "########################################\n",
     "\n",
+    "# Go to config dir\n",
+    "cd \"{CONFIG_DIR}\"\n",
+    "\n",
     "# Reset the dataset dir\n",
     "mkdir -p ../dataset\n",
     "rm -rf ../dataset/*.jsonl\n",
@@ -140240,19 +140040,19 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "5928163b",
+   "id": "1fc0cef1",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:23.574211Z",
-     "iopub.status.busy": "2023-09-06T17:37:23.573930Z",
-     "iopub.status.idle": "2023-09-06T17:37:41.229665Z",
-     "shell.execute_reply": "2023-09-06T17:37:41.228859Z"
+     "iopub.execute_input": "2023-09-06T18:39:34.676127Z",
+     "iopub.status.busy": "2023-09-06T18:39:34.675939Z",
+     "iopub.status.idle": "2023-09-06T18:39:53.301947Z",
+     "shell.execute_reply": "2023-09-06T18:39:53.301048Z"
     },
     "papermill": {
-     "duration": 18.288664,
-     "end_time": "2023-09-06T17:37:41.231690",
+     "duration": 19.230409,
+     "end_time": "2023-09-06T18:39:53.303981",
      "exception": false,
-     "start_time": "2023-09-06T17:37:22.943026",
+     "start_time": "2023-09-06T18:39:34.073572",
      "status": "completed"
     },
     "tags": []
@@ -140262,7 +140062,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:37:26,449] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:39:37,542] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -140284,9 +140084,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 4258540337\r\n",
+      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 2825309834\r\n",
       "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 4258540337\r\n"
+      "Global seed set to 2825309834\r\n"
      ]
     },
     {
@@ -140301,11 +140101,17 @@
      "output_type": "stream",
      "text": [
       "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_173728-uklb27ld\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230906_183940-f9fnknh5\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Tune ctx-512 (train-ctx=512, deepspeed_stage_1)\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/uklb27ld\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/f9fnknh5\u001b[0m\r\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "Traceback (most recent call last):\r\n",
       "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 254, in <module>\r\n",
       "    cli_main()\r\n",
@@ -140335,10 +140141,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Tune ctx-512 (train-ctx=512, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/uklb27ld\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v25\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2048-E0.1 - Mem-Tune ctx-512 (train-ctx=512, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/f9fnknh5\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v32\u001b[0m\r\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_173728-uklb27ld/logs\u001b[0m\r\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230906_183940-f9fnknh5/logs\u001b[0m\r\n"
      ]
     }
    ],
@@ -140363,19 +140169,19 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "id": "3c4e1a84",
+   "id": "f9b70eea",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:42.501242Z",
-     "iopub.status.busy": "2023-09-06T17:37:42.500756Z",
-     "iopub.status.idle": "2023-09-06T17:37:44.926179Z",
-     "shell.execute_reply": "2023-09-06T17:37:44.925416Z"
+     "iopub.execute_input": "2023-09-06T18:39:54.579000Z",
+     "iopub.status.busy": "2023-09-06T18:39:54.578746Z",
+     "iopub.status.idle": "2023-09-06T18:39:57.009190Z",
+     "shell.execute_reply": "2023-09-06T18:39:57.008417Z"
     },
     "papermill": {
-     "duration": 3.062059,
-     "end_time": "2023-09-06T17:37:44.927885",
+     "duration": 3.068353,
+     "end_time": "2023-09-06T18:39:57.010860",
      "exception": false,
-     "start_time": "2023-09-06T17:37:41.865826",
+     "start_time": "2023-09-06T18:39:53.942507",
      "status": "completed"
     },
     "tags": []
@@ -140385,7 +140191,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-09-06 17:37:44,062] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
+      "[2023-09-06 18:39:56,146] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
      ]
     },
     {
@@ -140422,19 +140228,19 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "id": "ff1e2d52",
+   "id": "01fca15c",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-06T17:37:46.169833Z",
-     "iopub.status.busy": "2023-09-06T17:37:46.169341Z",
-     "iopub.status.idle": "2023-09-06T17:37:46.403204Z",
-     "shell.execute_reply": "2023-09-06T17:37:46.402355Z"
+     "iopub.execute_input": "2023-09-06T18:39:58.256313Z",
+     "iopub.status.busy": "2023-09-06T18:39:58.256022Z",
+     "iopub.status.idle": "2023-09-06T18:39:58.488872Z",
+     "shell.execute_reply": "2023-09-06T18:39:58.488054Z"
     },
     "papermill": {
-     "duration": 0.870871,
-     "end_time": "2023-09-06T17:37:46.404923",
+     "duration": 0.874819,
+     "end_time": "2023-09-06T18:39:58.490725",
      "exception": false,
-     "start_time": "2023-09-06T17:37:45.534052",
+     "start_time": "2023-09-06T18:39:57.615906",
      "status": "completed"
     },
     "tags": []
@@ -140474,14 +140280,14 @@
   },
   "papermill": {
    "default_parameters": {},
-   "duration": 1500.445098,
-   "end_time": "2023-09-06T17:37:47.161793",
+   "duration": 1492.297607,
+   "end_time": "2023-09-06T18:39:59.213287",
    "environment_variables": {},
    "exception": null,
    "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb",
    "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb",
    "parameters": {},
-   "start_time": "2023-09-06T17:12:46.716695",
+   "start_time": "2023-09-06T18:15:06.915680",
    "version": "2.4.0"
   }
  },